{
    "exported_at": "2026-11-18 20:08:56",
    "count": 76,
    "records": [
        {
            "id": 30,
            "title": "Computer aided detection for breast lesion in ultrasound and mammography",
            "title_ar": "",
            "title_en": "Computer aided detection for breast lesion in ultrasound and mammography",
            "author": "Richa Agarwal",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; image-segmentation; medical-imaging",
            "keywords": "",
            "abstract": "In the field of breast cancer imaging, traditional Computer Aided Detection (CAD) systems were designed using limited computing resources and used scanned films (poor image quality), resulting in less robust application process. Currently, with the advancements in technologies, it is possible to perform 3D imaging and also acquire high quality Full-Field Digital Mammogram (FFDM). Automated Breast Ultrasound (ABUS) has been proposed to produce a full 3D scan of the breast automatically with reduced operator dependency. When using ABUS, lesion segmentation and tracking changes over time are challenging tasks, as the 3D nature of the images make the analysis difficult and tedious for radiologists. One of the goals of this thesis is to develop a framework for breast lesion segmentation in ABUS volumes. The 3D lesion volume in combination with texture and contour analysis, could provide valuable information to assist radiologists in the diagnosis. Although ABUS volumes are of great interest, x-ray mammography is still the gold standard imaging modality used for breast cancer screening due to its fast acquisition and cost-effectiveness. Moreover, with the advent of deep learning methods based on Convolutional Neural Network (CNN), the modern CAD Systems are able to learn automatically which imaging features are more relevant to perform a diagnosis, boosting the usefulness of these systems. One of the limitations of CNNs is that they require large training datasets, which are very limited in the field of medical imaging. In this thesis, the issue of limited amount of dataset is addressed using two strategies: (i) by using image patches as inputs rather than full sized image, and (ii) use the concept of transfer learning, in which the knowledge obtained by training for one task is used for another related task (also known as domain adaptation). In this regard, firstly the CNN trained on a very large dataset of natural images is adapted to classify between mass and non-mass image patches in the Screen-Film Mammogram (SFM), and secondly the newly trained CNN model is adapted to detect masses in FFDM. The prospects of using transfer learning between natural images and FFDM is also investigated. Two public datasets CBIS-DDSM and INbreast have been used for the purpose. In the final phase of research, a fully automatic mass detection framework is proposed which uses the whole mammogram as the input (instead of image patches) and provides the localisation of the lesion within this mammogram as the output. For this purpose, OPTIMAM Mammography Image Database (OMI-DB) is used. The results obtained as part of this thesis showed higher performances compared to state-of-the-art methods, indicating that the proposed methods and frameworks have the potential to be implemented within advanced CAD systems, which can be used by radiologists in the breast cancer screening",
            "source_url": "https:\/\/openalex.org\/W3154566879",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)",
            "source_record_id": "W3154566879",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 31,
            "title": "Transformer-based Transfer Learning for Breast Cancer Detection via Digital Breast Tomosynthesis",
            "title_ar": "",
            "title_en": "Transformer-based Transfer Learning for Breast Cancer Detection via Digital Breast Tomosynthesis",
            "author": "Mikea Dimech",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; generative-ai; medical-ai; transfer-learning; cnn; transformers; medical-imaging",
            "keywords": "",
            "abstract": "Breast cancer has emerged as the most prevalent form of cancer worldwide and the leading cause of mortality from any cancer in women, emphasising the critical need for its early detection. Traditional 2D mammography has long been the cornerstone of breast cancer screening, given its proven efficacy in early prognosis and reduction of mortality. However, the limitations of this modality have precipitated the development and adoption of more advanced imaging techniques, such as Digital Breast Tomosynthesis (DBT), which yields a 3D view of the breast. The application of deep learning to classify these scans is paramount to increasing the efficiency and efficacy of screening. However, this task presents arduous challenges such as high computational demands, scarcity of diverse data, and generalisation across varying demographics and imaging equipment. Transfer learning has proven to be effective in overcoming these challenges by enabling models to leverage pre-existing knowledge and adapt to new tasks. However, its application to DBT has been confined to Convolutional Neural Network (CNN) architectures. Meanwhile, the Transformer paradigm, which has revolutionised various deep learning domains and shown promise in traditional mammography, has yet to be explored in the context of DBT via transfer learning, highlighting a notable research gap. This study thus investigates the performance of a pre-trained Transformer model, fine-tuned on a public DBT dataset, comparing it with a fine-tuned state-of-the-art CNN. While the Transformer outperforms the convolutional architecture, the results reveal severe challenges posed by the imbalanced dataset, with models developing biases towards the majority class. Data augmentation, while beneficial, could not fully address the issue, and the need for more diverse datasets became clear. Moreover, the results underscore the importance of preserving the high resolution of DBT images, with fine-grained details, such as subtle changes in breast tissue captured at higher resolutions, proving to be pivotal for accurate diagnosis. Finally, a comparative analysis between CNNs and transformer-based models revealed that Transformers excel in recognising broader patterns across the entire image, which aids to mitigate overfitting. By using pre-trained transformers and fine-tuning them on this dataset, their effectiveness was highlighted, suggesting they can match or even surpass CNNs in breast cancer detection via DBT.",
            "source_url": "https:\/\/openalex.org\/W4385850049",
            "pdf_url": "",
            "doi": "10.5281\/zenodo.8243430",
            "handle": "",
            "repository_name": "Zenodo (CERN European Organization for Nuclear Research)",
            "source_record_id": "W4385850049",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 39,
            "title": "Breast Cancer Detection fromHistopathological Images using DeepLearning and Transfer Learning",
            "title_ar": "",
            "title_en": "Breast Cancer Detection fromHistopathological Images using DeepLearning and Transfer Learning",
            "author": "Mansi Chowkkar",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; medical-imaging",
            "keywords": "",
            "abstract": "Breast Cancer is the most common cancer in women and it's harming women's mental and physical health. Due to complexities present in Breast Cancer images, image processing technique is required in the detection of cancer. Early detection of Breast cancer required new deep learning and transfer learning techniques. In this paper, histopathological images are used as a dataset from Kaggle. Images are processed using histogram normalization techniques. This research project implements the Convolutional Neural Network(CNN) model based on deep learning and DenseNet-121 based on transfer-learning. Transfer learning uses the Imagenet pre-trained model for training. Hyper-parameter tuning is done for increasing accuracy and precision value. Research achieved 90.9 % test accuracy using the CNN model and 88.03 % accuracy by the transfer learning model.",
            "source_url": "https:\/\/openalex.org\/W3041001745",
            "pdf_url": "https:\/\/norma.ncirl.ie\/4282\/2\/mansichowkkarconfigurationmanual.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "NORMA",
            "source_record_id": "W3041001745",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 106,
            "title": "PERBANDINGAN KINERJA CNN DALAM KLASIFIKASI TUMOR OTAK DENGAN PENDEKATAN EXPLAINABLE ARTIFICIAL INTELLIGENCE (XAI)",
            "title_ar": "",
            "title_en": "PERBANDINGAN KINERJA CNN DALAM KLASIFIKASI TUMOR OTAK DENGAN PENDEKATAN EXPLAINABLE ARTIFICIAL INTELLIGENCE (XAI)",
            "author": "NIM.: 23206051017 Amin Darussalam",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Sunan Kalijaga State Islamic University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Indonesia",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; responsible-ai; transfer-learning; predictive-analytics; cnn; image-classification; medical-imaging; xai",
            "keywords": "",
            "abstract": "Brain tumors are life-threatening conditions that require accurate and timely diagnosis. In clinical practice, diagnosis is commonly performed through Magnetic Resonance Imaging (MRI) analysis by medical experts, which is time-consuming and subject to variability. Recent advances in Convolutional Neural Networks (CNN) have shown promising performance in medical image classification; however, their black-box nature limits clinical trust and interpretability. This study proposes a comparative analysis of CNN-based models integrated with Explainable Artificial Intelligence (XAI) to improve both classification performance and model transparency. A transfer learning approach is employed using two architectures, ResNet50 and MobileNetV2, on a multi-class brain tumor MRI dataset. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) is utilized to visualize discriminative regions influencing model predictions. Experimental results demonstrate that ResNet50 achieves an Accuracy of 93,7%, outperforming MobileNetV2 with 92.93%. Furthermore, Grad-CAM visualizations consistently highlight tumor-relevant regions, indicating that the models learn meaningful spatial features for classification. These findings confirm that integrating CNN with XAI not only provides high classification Accuracy but also improves model interpretability, thereby increasing its potential applicability in supporting reliable and transparent medical diagnosis.",
            "source_url": "https:\/\/openalex.org\/W7214133979",
            "pdf_url": "https:\/\/digilib.uin-suka.ac.id\/id\/eprint\/78375\/1\/23206051017_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Digital Library UIN Sunan Kalijaga (Sunan Kalijaga State Islamic University)",
            "source_record_id": "W7214133979",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 124,
            "title": "Aspect-based Sentiment Analysis for Arabic Reviews Using Deep Learning",
            "title_ar": "",
            "title_en": "Aspect-based Sentiment Analysis for Arabic Reviews Using Deep Learning",
            "author": "Nada Almani",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "The University of Surrey",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "sentiment-analysis",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; responsible-ai; transfer-learning; sentiment-analysis; arabic-nlp; xai",
            "keywords": "",
            "abstract": "Sentiment analysis is a branch of machine learning that concerns about finding and classifying the polarity for given text. Because of the availability of huge amount of opinionated data that need to be analyzed and interpreted, a lot of recent machine learning research is focused on sentiment analysis applications. it gained a lot of interest due to the. Many sentiment analysis systems are modeled by using different machine learning techniques, but recently, deep learning, by using Artificial Neural Network (ANN) architecture, has showed significant improvements with high tendency to reveal the underlying semantic meaning in the input text. However, the output of these models could not be explained and the efficiency could not be analyzed because ANN models are considered as a black box and the success of these models comes at the cost of interpretability. The main objective of the presented work is developing Arabic sentiment analysis system that understands semantics in input reviews without using any linguistic resources. The first proposed model is Deep Attention-based Review Level Sentiment Analysis model (DARLSA) that use binary classifier to detect reviews’ polarities. Different scenarios and architectures were examined to test the ability of the proposed model to extract salient words out of the input. The results proved the ability of the proposed model to understand a given review by highlighting the most informative words to the class label. The model detected Arabic natural language linguistic features, such as intensification and negation styles, efficiently. Also, the effect of applying transfer learning technique on the problem of Arabic sentiment analysis is experimented on review level model. The second proposed architecture is Deep Attention-based Aspect Level Sentiment Analysis model (DAALSA) for classifying reviews polarity with respect to an aspect into three classes, positive, negative and neutral. Different models were proposed to test the effect of using different attention scoring functions on the classification performance. The results distinguished one model with superior performance compared to other proposed models. To obtain intuitive explanation of the trained models, both models are enhanced with visualization option. The final review representation is a distributed dense vector generated after passing through multi-layers neural network. Heatmap representation is used to visualize the final review representation. In addition, the attention layer’s scoring vector is visualized as well.",
            "source_url": "https:\/\/openalex.org\/W2996475580",
            "pdf_url": "",
            "doi": "10.15126\/thesis.00852989",
            "handle": "",
            "repository_name": "Surrey Research Insight Open Access (The University of Surrey)",
            "source_record_id": "W2996475580",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:47",
            "updated_at": "2026-11-15 16:52:47"
        },
        {
            "id": 145,
            "title": "Deep Reinforcement Learning for Intrusion Detection and Response in Software-Defined Networks",
            "title_ar": "",
            "title_en": "Deep Reinforcement Learning for Intrusion Detection and Response in Software-Defined Networks",
            "author": "Trung Phan Van",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Chemnitz University of Technology",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Germany",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; deep-learning; reinforcement-learning; ai-applications; transfer-learning; ai-cybersecurity; ai-smart-cities",
            "keywords": "",
            "abstract": "This dissertation presents a unified set of learning-based solutions for improving cybersecurity in Software-Defined Networking (SDN) environments. The main objectives are to provide fine-grained traffic flow information for accurate attack detection, jointly optimize feature set and machine learning model selection for intrusion detection, develop adaptive intrusion response mechanisms that minimize disruption to legitimate traffic, and address the shortage of labeled training data for machine learning-based security applications in SDN-based networks. To achieve these objectives, the dissertation makes four main contributions: DeepMatch: A fine-grained traffic flow measurement framework based on a Partially Observable Markov Decision Process (POMDP) and a Deep Dueling Neural Network-based control algorithm. DeepMatch dynamically adjusts flow rule matching strategies to maximize traffic flow granularity while proactively preventing flow-table overflow in switches in the SDN data plane. \/\/ DeepGuard: A machine learning-based intrusion detection framework that integrates DeepMatch to preserve important runtime traffic flow features. DeepGuard formulates the joint selection of feature sets and machine learning models as a learning-based optimization problem and applies Q-Learning to identify effective configurations for accurate and efficient attack detection. \/\/ DeepAir: An adaptive intrusion response framework that models response-policy selection as a Markov Decision Process (MDP). By leveraging a Double Deep Q-Network (DDQN), DeepAir learns effective response policies that mitigate malicious traffic in real time while reducing the negative impact on benign traffic forwarding and limiting policy deployment overhead. \/\/ DeepTransfer: A selective transfer learning framework that addresses the lack of labeled SDN attack detection data. DeepTransfer applies DDQN to guide the transfer of attack detection knowledge from legacy network environments to SDN-based target domains, thereby improving detection performance while reducing the risk of negative transfer across heterogeneous network domains. \/\/ Extensive experimental evaluations validate the effectiveness of the proposed frameworks under different security scenarios, particularly Denial-of-Service and Distributed Denial-of-Service (DoS\/DDoS) attacks. The results demonstrate that the proposed solutions improve traffic flow visibility, feature set-model selection, intrusion detection accuracy, response adaptability, QoS preservation for benign traffic, and learning stability compared with existing approaches. Collectively, the contributions of this dissertation advance intelligent and adaptive cybersecurity mechanisms for SDN infrastructures.",
            "source_url": "https:\/\/openalex.org\/W7214800756",
            "pdf_url": "https:\/\/monarch.qucosa.de\/api\/qucosa%3A107046\/attachment\/ATT-0\/",
            "doi": "10.60687\/2026-0177",
            "handle": "",
            "repository_name": "Qucosa - Monarch (Chemnitz University of Technology)",
            "source_record_id": "W7214800756",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:47",
            "updated_at": "2026-11-15 16:52:47"
        },
        {
            "id": 245,
            "title": "Pump diagnostics using machine learning",
            "title_ar": "",
            "title_en": "Pump diagnostics using machine learning",
            "author": "C.J. van Ekris",
            "supervisor": "",
            "degree_type": "master",
            "degree_evidence": "نص السجل: «master»",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; medical-ai; ai-applications; transfer-learning; ai-education; ai-industry",
            "keywords": "",
            "abstract": "The master thesis shows how transfer learning can be used to train machine-learning models to automatically recognize faults in a UHPLC pump. With the developed machine-learning models it is possible to recognize faults in real-time, estimate the seriousness of a fault and to differentiate between several faults. With the help of the 20-Sim model the UHPLC pump, all kind of faults can be replayed and log data can be generated. With this generated log data, machine-learning models can be trained. Using the trained machine-learning models it should be possible for untrained users of the pump to recognize several faults and to solve them.",
            "source_url": "https:\/\/openalex.org\/W3108210491",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W3108210491",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 256,
            "title": "Comparative Performance Analysis of Deep Learning Models for Brain Tumor Classification from MRI Images",
            "title_ar": "",
            "title_en": "Comparative Performance Analysis of Deep Learning Models for Brain Tumor Classification from MRI Images",
            "author": "Hassan Khan",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Eastern Finland",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Finland",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; transformers; medical-imaging",
            "keywords": "",
            "abstract": "Brain tumors are among the most serious categories of neurological disease, with accurate classification from magnetic resonance imaging (MRI) playing a critical role in treatment planning and patient outcomes.Manual interpretation of MRI scans by radiologists is timeconsuming, subject to inter-observer variability, and constrained by the availability of specialist expertise, particularly in resource-limited settings.These factors have driven growing interest in automated deep learning solutions for brain tumor MRI classification.While convolutional neural networks (CNNs) have demonstrated strong performance on this task through transfer learning, the emergence of Vision Transformers and hybrid CNN-Transformer architectures has created a diverse model landscape whose relative merits remain poorly understood.Existing comparative studies benchmark either multiple CNN variants in isolation or transformer-based models separately, without unified head-tohead evaluation across all three architectural families under identical experimental conditions.Furthermore, deployment-relevant efficiency metrics -inference latency, model size, and GPU memory -are rarely reported alongside accuracy, limiting practical model selection guidance for clinical settings with varying hardware constraints.This thesis addresses these gaps by conducting a systematic benchmark of nine deep learning architectures -four CNN-based (VGG16, ResNet50, DenseNet121, EfficientNet-B0), three Transformer-based (ViT-B\/16, Swin Transformer, DeiT-B), and two Hybrid\/Lightweight (MobileNetV2, MaxViT-Tiny) -evaluated on the Brain Tumor MRI Dataset comprising 7,200 T1-weighted MRI images across four classes (glioma, meningioma, pituitary tumor, no tumor).All models were trained under identical conditions using ImageNet transfer learning and assessed on both classification performance (accuracy, precision, recall, F1-score, AUC-ROC) and computational efficiency (parameter count, model size, inference latency, peak GPU memory).The Swin Transformer achieves the highest test accuracy (98.52%,F1 = 0.9852), demonstrating that hierarchical transformer architectures can outperform CNNs when appropriately designed for the task.MobileNetV2 leads all models on efficiency metrics with 2.2M parameters and 7.55 ms inference latency.Pareto analysis identifies three deployment-optimal models: Swin-T for high-resource GPU environments, DenseNet121 (98.15%, 7.0M parameters) for standard workstations, and MobileNetV2 (97.04%) for edge devices.Efficiency varies by a factor of 61× in parameter count and 25× in GPU memory across the nine models, while accuracy spans only ~2 percentage points, underscoring that architectural design matters far more than raw model size.This study provides the first unified benchmark comparing CNN, Transformer, and Hybrid architectures for brain tumor MRI classification under identical conditions with both accuracy and efficiency metrics reported, yielding evidence-based model selection guidelines for clinical deployment across diverse computational environments.",
            "source_url": "https:\/\/openalex.org\/W7215551487",
            "pdf_url": "https:\/\/erepo.uef.fi\/bitstreams\/57ebe372-c179-491f-bae8-4ad920908485\/download",
            "doi": "",
            "handle": "",
            "repository_name": "UEF eRepo (University of Eastern Finland)",
            "source_record_id": "W7215551487",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 258,
            "title": "Brain Tumor Detection and Classification from MRI Images",
            "title_ar": "",
            "title_en": "Brain Tumor Detection and Classification from MRI Images",
            "author": "Anjaneya Teja Sarma Kalvakolanu",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "California State Polytechnic University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; image-segmentation; medical-imaging",
            "keywords": "",
            "abstract": "A brain tumor is detected and classified by biopsy that is conducted after the brain surgery. Advancement in technology and machine learning techniques could help radiologists in the diagnosis of tumors without any invasive measures. We utilized a deep learning-based approach to detect and classify the tumor into Meningioma, Glioma, Pituitary tumors. We used registration and segmentation-based skull stripping mechanism to remove the skull from the MRI images and the grab cut method to verify whether the skull stripped MRI masks retained the features of the tumor for accurate classification. In this research, we proposed a transfer learning based approach in conjunction with discriminative learning rates to perform the classification of brain tumors. The data set used is a 3064 T MRI images dataset that contains T1 flair MRI images. We achieved a classification accuracy of 98.83%, 96.26%, and 95.18% for training, validation, and test sets and an F1 score of 0.96 on the T1 Flair MRI dataset.",
            "source_url": "https:\/\/openalex.org\/W3158119991",
            "pdf_url": "https:\/\/digitalcommons.calpoly.edu\/cgi\/viewcontent.cgi?article=3799&context=theses",
            "doi": "10.15368\/theses.2021.16",
            "handle": "",
            "repository_name": "DigitalCommons - CalPoly (California State Polytechnic University)",
            "source_record_id": "W3158119991",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 259,
            "title": "Advancements in Automated Brain Tumor Detection Using Deep Learning on MRI Imagery",
            "title_ar": "",
            "title_en": "Advancements in Automated Brain Tumor Detection Using Deep Learning on MRI Imagery",
            "author": "Md. Sohan Biswas",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; medical-imaging",
            "keywords": "Brain tumor, Convolutional Neural Networks, Deep Learning, Transfer Learning",
            "abstract": "The goal of this thesis is to solve the significant problem of inter-observer variability-induced diagnostic delays by presenting a sophisticated deep learning system for automated brain tumor diagnosis utilizing MRI imagery. Pituitary adenoma, extra-axial meningioma, infiltrative glioma, and no-tumor controls are the four classes of brain tumors that are represented in the 7,143 T1 weighted MRI images taken from Kaggle Brain Tumor Dataset and various hospitals in Bangladesh, including Ibn Sina Medical College, Dhaka Medical College, and Comilla Medical College. Using three pretrained convolutional neural network (CNN) architectures; MobileNetV2, EfficientNetB0, and VGG16 optimized through selective layer unfreezing and on-the-fly data augmentation, including random brightness and contrast adjustments to mitigate scanner artifacts, the study applies transfer learning to improve diagnostic accuracy. With a test accuracy of 98.5%, a macro F1-score of 0.98, and an area under the curve (AUC) ≥0.99, MobileNetV2 outperformed the other models after being trained on 5,832 photos. Particularly noteworthy was the MobileNetV2 model's real-time inference ability (0.97) and quick processing times, especially in low-resource settings where prompt diagnosis can have a major impact on survival outcomes. The study highlights the clinical viability of applying AI-assisted diagnostics in various contexts, enhancing access to superior radiological evaluations and possibly cutting down on diagnostic delays in practical applications. Keywords: Brain tumor, Convolutional Neural Networks, Deep Learning, Transfer Learning, MRI Classification Source Code:GitHub: Advancements in Automated Brain Tumor Detection Using Deep Learning on MRI Imagery Author: Md. Sohan BiswasORCID: 0009-0000-5888-373X",
            "source_url": "https:\/\/openalex.org\/W7201959393",
            "pdf_url": "",
            "doi": "10.5281\/zenodo.21845324",
            "handle": "",
            "repository_name": "Zenodo (CERN European Organization for Nuclear Research)",
            "source_record_id": "W7201959393",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 260,
            "title": "Artificial Intelligence for Medical Diagnosis Using Machine Learning for Brain Tumor MRI Classification : магистерская диссертация",
            "title_ar": "",
            "title_en": "Artificial Intelligence for Medical Diagnosis Using Machine Learning for Brain Tumor MRI Classification : магистерская диссертация",
            "author": "М. Ш. С. Мако ; M. S. S. Mako",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Ural Federal University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Russia",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; responsible-ai; transfer-learning; cnn; medical-imaging; xai",
            "keywords": "",
            "abstract": "The integration of Artificial Intelligence (AI) into the domain of medical diagnostics has ushered in a new era of precision, speed, and reliability, particularly in the analysis of medical imaging. Among the most promising applications is the use of Machine Learning (ML) techniques for the classification and diagnosis of brain tumors from Magnetic Resonance Imaging (MRI) scans. Brain tumors, whether malignant or benign, pose significant health threats and require early, accurate detection to improve prognosis and treatment outcomes. Traditional methods for diagnosing brain tumors are often time-consuming, subject to inter-observer variability, and reliant on the expertise of radiologists. This thesis explores the use of AI-driven machine learning models to automate and enhance the diagnostic process by classifying brain tumor types from MRI images. This research presents a comprehensive study on the implementation of various machine learning algorithms—including Convolutional Neural Networks (CNNs), Support Vector Machines (SVM), and ensemble models—for the classification of different types of brain tumors, such as gliomas, meningiomas, and pituitary tumors. The dataset employed comprises a substantial number of pre-processed and labeled MRI images sourced from publicly available medical imaging repositories. The study begins with a detailed examination of MRI imaging modalities, the clinical characteristics of common brain tumors, and the importance of accurate classification. A robust preprocessing pipeline was designed to handle data augmentation, normalization, and artifact removal, which are critical for enhancing image quality and improving model generalization. Feature extraction techniques, both handcrafted and automated via deep learning, were analyzed to assess their effectiveness in capturing the unique spatial and textural patterns of different tumor types. Subsequently, multiple supervised learning algorithms were trained and tested using cross-validation to compare their accuracy, precision, recall, F1-score, and area under the receiver operating characteristic (ROC) curve. CNN-based architectures, particularly those leveraging transfer learning (e.g., ResNet, VGGNet, and EfficientNet), demonstrated superior performance compared to traditional classifiers, achieving classification accuracies exceeding 90% in test scenarios. In addition, model interpretability techniques such as Grad-CAM and SHAP were applied to visualize and explain the decision-making process of the neural networks, addressing one of the key challenges in deploying AI systems in clinical environments: trust and transparency.",
            "source_url": "https:\/\/openalex.org\/W7117637577",
            "pdf_url": "https:\/\/elar.urfu.ru\/bitstream\/10995\/147597\/1\/m_th_m.s.s.mako_2025.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Electronic scientific archive of UrFU (Ural Federal University)",
            "source_record_id": "W7117637577",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 263,
            "title": "Hybrid Approach for the Classification and Detection of Brain Tumor",
            "title_ar": "",
            "title_en": "Hybrid Approach for the Classification and Detection of Brain Tumor",
            "author": "Venkateshwar Rao K ; Sunny Sowmith Uppala ; Srikar Jakkena",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; responsible-ai; transfer-learning; predictive-analytics; cnn; object-detection; image-segmentation; medical-imaging; xai",
            "keywords": "",
            "abstract": "Brain tumors represent one of the most severeneurological disorders and require early detection for effectivetreatment. MRI imaging is widely used because it providesdetailed visualization of soft tissues and tumor structures withoutradiation exposure. Despite its advantages, interpreting MRIscans manually is complex and prone to inter-observer variability.Recent advancements in Artificial Intelligence (AI) and DeepLearning have enabled automated medical image analysis withhigh accuracy. Convolutional Neural Networks (CNNs) havedemonstrated strong performance in feature extraction and classification tasks. However, standalone CNN models often requirelarge datasets and may suffer from overfitting when applied tolimited medical datasets. In recent years, Artificial Intelligence(AI) and Deep Learning have significantly transformed medicalimage analysis. Convolutional Neural Networks (CNNs) havedemonstrated remarkable success in various computer visiontasks, including object detection, segmentation, and classification.In medical imaging, CNN-based architectures have been appliedto detect tumors, segment lesions, and classify disease typeswith high accuracy. Despite these advancements, standalone deeplearning models often face challenges such as overfitting, highcomputational complexity, and limited interpretability. Hybridmodels that combine deep learning feature extraction with classical machine learning classifiers have shown promising resultsin improving generalization performance. Additionally, segmentation of tumor regions before classification can significantlyimprove prediction accuracy by eliminating irrelevant background information. This work proposes a comprehensive hybridarchitecture that integrates: • U-Net for tumor segmentation• MobileNetV2 for transfer learning-based feature extraction• SVM and Random Forest for classification • Grad-CAM forexplainability The proposed approach aims to balance accuracy,computational efficiency, and interpretability in a unified framework.",
            "source_url": "https:\/\/openalex.org\/W7154615453",
            "pdf_url": "",
            "doi": "10.5281\/zenodo.19601617",
            "handle": "",
            "repository_name": "Zenodo (CERN European Organization for Nuclear Research)",
            "source_record_id": "W7154615453",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 287,
            "title": "Neural Transfer Learning for Domain Adaptation in Natural Language Processing",
            "title_ar": "",
            "title_en": "",
            "author": "Sara Meftah",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "theses.fr: الفهرس الوطني الفرنسي لأطاريح الدكتوراه",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "France",
            "governorate": "",
            "publication_year": 2021,
            "language": "fr",
            "research_domain": "nlp",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; nlp; transfer-learning",
            "keywords": "",
            "abstract": "Apprentissage par transfert neuronal pour l'adaptation aux domaines en traitement automatique de la langue Les méthodes d’apprentissage automatique qui reposent sur les Réseaux de Neurones (RNs) ont démontré des performances de prédiction qui s'approchent de plus en plus de la performance humaine dans plusieurs applications du Traitement Automatique de la Langue (TAL) qui bénéficient de la capacité des différentes architectures des RNs à généraliser à partir des régularités apprises à partir d'exemples d'apprentissage. Toutefois, ces modèles sont limités par leur dépendance aux données annotées. En effet, pour être performants, ces modèles neuronaux ont besoin de corpus annotés de taille importante. Par conséquent, uniquement les langues bien dotées peuvent bénéficier directement de l'avancée apportée par les RNs, comme par exemple les formes formelles des langues. Dans le cadre de cette thèse, nous proposons des méthodes d'apprentissage par transfert neuronal pour la construction d'outils de TAL pour les langues peu dotées en exploitant leurs similarités avec des langues bien dotées. Précisément, nous expérimentons nos approches pour le transfert à partir du domaine source des textes formels vers le domaine cible des textes informels (langue utilisée dans les réseaux sociaux). Tout au long de cette thèse nous proposons différentes contributions. Tout d'abord, nous proposons deux approches pour le transfert des connaissances encodées dans les représentations neuronales d'un modèle source, pré-entraîné sur les données annotées du domaine source, vers un modèle cible, adapté par la suite sur quelques exemples annotés du domaine cible. La première méthode transfère des représentations contextuelles pré-entraînées sur le domaine source. Tandis que la deuxième méthode utilise des poids pré-entraînés pour initialiser les paramètres du modèle cible. Ensuite, nous effectuons une série d'analyses pour repérer les limites des méthodes proposées ci-dessus. Nous constatons que, même si l'approche d'apprentissage par transfert proposée améliore les résultats du domaine cible, un transfert négatif « dissimulé » peut atténuer le gain final apporté par l'apprentissage par transfert. De plus, une analyse interprétative du modèle pré-entraîné, montre que les neurones pré-entraînés peuvent être biaisés par ce qu'ils ont appris du domaine source, et donc peuvent avoir des difficultés à apprendre des « patterns » spécifiques au domaine cible. Issu de notre analyse, nous proposons un nouveau schéma d'adaptation qui augmente le modèle cible avec des neurones normalisés, pondérés et initialisés aléatoirement qui permettent une meilleure adaptation au domaine cible tout en conservant les connaissances apprises du domaine source. Enfin, nous proposons une approche d’apprentissage par transfert qui permet de profiter des similarités entre différentes tâches, en plus des connaissances pré-apprises du domaine source.",
            "source_url": "https:\/\/openalex.org\/W7149540086",
            "pdf_url": "https:\/\/theses.hal.science\/tel-03206378\/document",
            "doi": "10.70675\/9111562bzfa37z4fd8zae6bz2e8ae8d5d403",
            "handle": "",
            "repository_name": "theses.fr (ABES)",
            "source_record_id": "W7149540086",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 358,
            "title": "Computational biology in plant tissue culture: Systematic evaluation of machine learning approaches for callus induction in Solanum L.: A thesis submitted in partial fulfilment of the requirements for the Degree of Doctor of Philosophy at Lincoln University",
            "title_ar": "",
            "title_en": "Computational biology in plant tissue culture: Systematic evaluation of machine learning approaches for callus induction in Solanum L.: A thesis submitted in partial fulfilment of the requirements for the Degree of Doctor of Philosophy at Lincoln University",
            "author": "Sadegh Mohajer",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "نص السجل: «Doctor of Philosophy»",
            "university": "Lincoln University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "New Zealand",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "xai",
            "categories": "machine-learning; deep-learning; medical-ai; responsible-ai; ai-applications; transfer-learning; predictive-analytics; optimization; xai; ai-agriculture",
            "keywords": "",
            "abstract": "Optimization of plant tissue culture systems remains a major biotechnological challenge; yet successful callus induction, the formation of unorganized, proliferating cell masses from differentiated tissues, enables transformative applications in agriculture, medicine, and fundamental research. Callus serves as a foundation for genetic transformation and genome editing, mass propagation of elite varieties, production of pharmaceutically valuable secondary metabolites, and breeding programs. However, achieving consistent callus induction is hindered by the multifactorial nature of the process, governed by intricate dependencies among environmental conditions, genetic background, hormonal composition, and explant source. Conventional trial-and-error methodologies are further constrained by the difficulty of systematically capturing and optimizing these complex interactions, resulting in protocols with poor transferability and requiring extensive empirical refinement for each new species or genotype. This study established comprehensive machine learning (ML) frameworks to model and predict callus induction rates in the Solanum genus, one of the most diverse angiosperm genera containing approximately 1,500–2,000 species. This genus includes economically significant crop species such as potato, tomato, and eggplant that sustain global food security, as well as wild relatives possessing valuable traits for disease resistance and abiotic stress tolerance. The genus also includes species of pharmaceutical interest, owing to their diverse alkaloids and secondary metabolites, which exhibit antimicrobial, antioxidant, and anticancer activities. Despite their agricultural, nutritional, and medicinal importance, many Solanum species remain recalcitrant in tissue culture, as standard protocols developed for model cultivars often perform poorly when applied to wild species and new genotypes. The ML methods developed here systematically evaluate modeling strategies ranging from global to local approaches, with the goal of addressing the protocol optimization bottleneck that constrains biotechnological applications across this economically and scientifically important genus. Five machine learning algorithms were evaluated: Random Forest and XGBoost as tree-based ensemble models, Support Vector Regression, and Gaussian Process Regression as kernel-based methods, and an artificial neural network (multilayer perceptron) with genetic algorithm optimization for hyperparameter tuning and protocol development. Model interpretability was achieved through SHAP analysis and permutation importance assessment. Genetic algorithm optimization of neural networks identified optimal protocols achieving remarkable callus induction rates, representing substantial improvements over conventional approaches. Feature optimization revealed specific strategies ranging from minimal hormone supplementation to comprehensive growth regulator networks. Sensitivity analysis confirmed that environmental precision provides primary control mechanisms, with hormonal supplementation serving as fine tuning parameters rather than primary drivers. The thesis advances both methodology and biological understanding. It establishes a rigorous methodological framework integrating systematic preprocessing, cross-validation with independent holdout data, and comprehensive interpretability analysis. The approach delivers predictive models with quantified uncertainty and clear performance boundaries. Biologically, the work demonstrates that machine learning can successfully capture complex tissue culture interactions. These findings represent a paradigm shift from empirical protocol development to data-driven optimization, with applications across plant biotechnology, crop improvement, pharmaceutical compound production, and conservation. The work may also motivate future steps that include transfer learning across species, imaging-based phenotyping with deep learning, classification of callus quality tiers, and time-resolved modeling of induction dynamics.",
            "source_url": "https:\/\/openalex.org\/W7131545409",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Lincoln University Research Archive (Lincoln University)",
            "source_record_id": "W7131545409",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 361,
            "title": "Comparative analysis of the efficacy of machine learning models in detecting cancer from medical imagery: a thesis in Computer Science",
            "title_ar": "",
            "title_en": "Comparative analysis of the efficacy of machine learning models in detecting cancer from medical imagery: a thesis in Computer Science",
            "author": "Kyle Andrew Furtado",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; medical-imaging",
            "keywords": "",
            "abstract": "According to a study performed by John Hopkins Medicine in 2023, misdiagnoses make up approximately 11.1% of total diagnoses in the United States, which result in anything from minor to fatal error for the patient. One of the main contributors to this unfortunate statistic is the heavy reliance on human-read medical scans. As a result, this study investigates the effectiveness of various Machine Learning (ML) models in classifying cancer from histopathological medical images. More specifically, Deep Learning (DL) Convolutional Neural Networks (CNNs) leveraging Transfer Learning (TL) are under analysis. For each experiment, one generic CNN is trained from scratch followed by four prominent pretrained models (i.e., DenseNet, VGG16, ResNet, and InceptionNet). The primary disease used for experimentation was colorectal cancer, while brief research was also done with lung cancer, leukemia, and breast cancer. Each model was trained across various levels of data augmentation and shuffles in data to provide a more verifiable set of findings when compared amongst each other. Results indicate optimal model selections for cancer detection under varying scenarios, such as training constraints (e.g., time and computational resources) along with dataset conditions (e.g., sizes and class balances). Overall, this research provides valuable insights on ideal CNNs for histopathological cancer detection that can be applied to developing future cancer detection software, reducing the heavy reliance on human-interpreted medical imagery diagnosis.",
            "source_url": "https:\/\/openalex.org\/W4409785731",
            "pdf_url": "",
            "doi": "10.62791\/20332",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W4409785731",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 400,
            "title": "Feature Selection and Transfer Learning in Network Data: Enhancing Anomaly Detection with Zero-Shot and Few-Shot Learning",
            "title_ar": "",
            "title_en": "Feature Selection and Transfer Learning in Network Data: Enhancing Anomaly Detection with Zero-Shot and Few-Shot Learning",
            "author": "Joideep Banerjee",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "نص السجل: «PhD»",
            "university": "Staffordshire University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "xai",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; responsible-ai; transfer-learning; few-zero-shot; predictive-analytics; xai",
            "keywords": "",
            "abstract": "The exponential growth of high-dimensional data across domains such as bioinformatics, healthcare, finance, and image processing has heightened the need for effective feature selection (FS) methods. These techniques improve model performance by identifying relevant features, reducing computational complexity, and mitigating overfitting. This PhD thesis introduces Radian, a novel feature selection method that leverages the statistical properties of range and median to identify the most influential features. Radian effectively distinguishes between relevant and redundant attributes while also detecting anomalies, enhancing both model interpretability and data quality. Radian was rigorously evaluated on multiple benchmark datasets of varying size and complexity. The results show that it consistently outperforms conventional methods such as the Pearson correlation coefficient in three key areas: classification accuracy, feature reduction, and computational efficiency. Its ability to balance performance and simplicity enables the creation of compact, interpretable models that retain or improve predictive accuracy. Beyond feature selection, this research advances transfer learning for tabular data, an area often underexplored in existing literature. Three innovative models TabLoRA, TabLoRA-ZS (zero-shot), and TabLoRA-FS (few-shot) are introduced by integrating TabNet, a deep learning architecture for tabular data, with Low-Rank Adaptation (LoRA) modules. The TabLoRA-ZS model enables generalisation to unseen tasks without prior data, while TabLoRA-FS fine-tunes efficiently with minimal data, addressing the challenges of data scarcity. A major innovation lies in integrating Radian with TabNet and LoRA, allowing dynamic feature selection during transfer learning. This integration improves model adaptability, robustness, and scalability, particularly in environments with limited labelled data. Comprehensive experiments demonstrate that these Radian-enhanced transfer learning models perform competitively with state-of-the-art approaches while maintaining interpretability and efficiency. In conclusion, this thesis contributes to machine learning by (1) proposing Radian, a statistically driven, efficient feature selection method, and (2) developing Radian-integrated TabLoRA models for few-shot and zero-shot transfer learning. Together, they provide scalable, adaptable, and high-performing solutions for data-scarce domains, bridging the gap between feature selection and transfer learning in tabular data analysis.",
            "source_url": "https:\/\/openalex.org\/W7126002433",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Staffordshire Online Repository (Staffordshire University)",
            "source_record_id": "W7126002433",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 411,
            "title": "Deep Zero- and Few-shot Learning in Computer Vision",
            "title_ar": "",
            "title_en": "Deep Zero- and Few-shot Learning in Computer Vision",
            "author": "Hongguang Zhang",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Australian National University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Australia",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "object-detection",
            "categories": "machine-learning; deep-learning; computer-vision; generative-ai; transfer-learning; few-zero-shot; cnn; object-detection; video-analysis; gan",
            "keywords": "",
            "abstract": "Most CNN models rely on the large-scale annotated training data, and the performance turns to be low when the size of training data is limited, therefore numbers of large-scale datasets are proposed for vision tasks. Though training on large-scale dataset can significantly improve the performance, creating such datasets for novel scenarios is costly. Moreover, relying on the number of samples is not consistent with human's learning abilities, as humans have the ability to understand novel concepts from limited examples. Transfer learning is a machine learning topic that addresses the above limitations in current deep models, and it studies how to make machines exploit the acquired knowledge to solve new problems, thus learning by generalizing from existing to new concepts, a trait akin to humans. Empirically, transfer learning for computer vision problems includes the following subtopics: i) zero-shot learning, ii) few-shot learning, and iii) domain adaptation. In this thesis, we study zero-shot and few-shot learning to demonstrate how to learn better from limited training samples. Zero-shot learning requires learning a mapping that associates feature vectors extracted from images with semantic annotations that describe objects and\/or scenes of interest. Our first work addresses the weakness of linear mapping in previous zero-shot learning models by learning via non-linear kernelized projections between features and attribute spaces to promote accuracy. We propose an easy learning objective inspired by the Linear Discriminant Analysis method with an incoherence mechanism. The dominant challenge in the generalized zero-shot setting is the unbalanced data distribution during training and testing, which makes it difficult for the classifier to distinguish if a testing sample is from a seen or unseen class. Inspired by GAN-based models, we propose the model selection mechanism, in which we leverage two sources of datapoints to train the model selection classifier to recognize which test datapoints come from seen and which from unseen classes. This way, generalized zero-shot learning can be decoupled into two disjoint classification tasks. Few-shot learning is a variant of knowledge transfer which is formulated as a meta-learning process. Firstly we investigate so-called second-order pooling and Power Normalizations in fine-grained classification tasks to study a proper way of using co-occurrence statistics for such tasks. Following above experiments and analysis, we propose the novel second-order similarity network, which measures image relations via co-occurrence relation descriptors, and significantly improves the performance of few-shot learning. Hallucinating auxiliary samples for training is also a popular and effective way to improve the accuracy of few-shot learning. To this end, we propose a saliency-guided hallucination strategy, which employs a saliency detector to segment foregrounds and backgrounds from sampled images forming an episode, then we mix every foreground with all available backgrounds in convolutional feature space to synthesize descriptors representing objects in various scenes. Furthermore, we note that previous few-shot learning methods fail to address the scale- and location-mismatch between support-query objects, thus leading to the performance loss. Inspired by the spatial-pyramid matching, we propose a novel spatial- and scale-matching network to explicitly match the support-query pairs over different scales and locations. Last but not least, we consider a more challenging scenario, namely few-shot action recognition, to study knowledge transfer in the video domain. Apart from the spatial information, robust aggregation over the temporal mode is fundamental in this task. To address this issue, we propose a novel action relation network with permutation-invariant attentions and auxiliary self-supervision tasks.",
            "source_url": "https:\/\/openalex.org\/W3112219073",
            "pdf_url": "",
            "doi": "10.25911\/5f5a020a5c26f",
            "handle": "",
            "repository_name": "ANU Open Research (Australian National University)",
            "source_record_id": "W3112219073",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 415,
            "title": "Meta Approaches to Few-shot Image Classification",
            "title_ar": "",
            "title_en": "Meta Approaches to Few-shot Image Classification",
            "author": "Arkabandhu Chowdhury",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Rice University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "image-classification",
            "categories": "machine-learning; deep-learning; computer-vision; responsible-ai; ai-applications; transfer-learning; few-zero-shot; cnn; image-classification; fairness; ai-smart-cities",
            "keywords": "",
            "abstract": "Since the inception of deep Convolution Neural Network (CNN) architectures, we have seen a tremendous advancement in machine image classification. However, these methods require a large amount of data, sometimes in the order of millions, but often fail to generalize when the data set is small. And so, recently a new paradigm, called `Few-Shot Learning', has been developed to tackle this problem. Essentially, the goal of few-shot learning is to develop techniques that can rapidly generalize to new tasks containing very few samples-- in extreme cases one (called one-shot) or zero (called zero-shot)-- with labels. In this work, I will be particularly tackling few-shot learning in the application of image classification. The most common approach to it is known as Meta-learning or `learning to learn' where, rather than learning to solve a particular learning problem, the goal is to solve many learning problems in an attempt to learn how to learn to solve a particular type of problem. Another way to solve the problem is to re-purpose an existing learner for a new learning problem, known as Transfer learning. In my thesis, I propose two novel approaches, based on meta-learning and transfer learning, to tackle the few-shot (or one-shot) image classification. The first approach I propose is called meta-meta classification, where one uses a large set of learning problems to design an ensemble of learners, each of which has high bias and low variance and is skilled at solving a specific type of learning problems. The meta-meta classifier learns how to examine a given learning problem and combine the various learners to solve the problem. One type of image classification is the one-vs-all (OvA) classification problem, where only one image from the positive class is available for training along with images from a number of negative classes. I evaluate my approach on a one-shot, one-class-versus-all classification task and show that it is able to outperform traditional meta-learning as well as ensembling approaches. I evaluate my method using the popular 1,000 class Imagenet data (ILSVRC2012), the 200 class Caltech-UCSD Birds dataset, the 102 class FGVC-Aircraft dataset, and the 1,200 class Omniglot hand-written character dataset. I compare my results with a popular meta-learning algorithm, called model-agnostic meta learner (MAML), as well as an ensemble of multiple MAML models, and show my approach is able to outperform them in all the problems. The second approach we investigate uses the existing concept of transfer learning, where a simple Multi-Layer Perceptron (MLP) with a hidden layer is fine-tuned on top of pre-trained CNN backbones. Surprisingly, there have been very few works in the few-shot literature that have even examined the use of an MLP for fine-tuning pre-trained models (the assumption may be be that a hidden layer would provide too many parameters for few-shot learning). In order to avoid overfitting, we simply use an L2-regularizer. We argue that a diverse feature vector made of a variety of pre-trained libraries of models trained on a diverese dataset (such as, ILSVRC2012) is sufficiently capable of being re-purposed for small-data problems. We performed a series of experiments on both classification accuracy and feature behavior on multiple few-shot problems. We carefully picked the hyperparameters after validating on Caltech-UCSD Bird dataset and did our final evaluation on FGVC-Aircraft, FC100, Omniglot, Traffic Sign, FGCVx Fungi , QuickDraw, and VGG Flower datasets. Our experimental results showed significantly better performance compared to some baselines, such as, simple ensembling, standalone best model, as well as, some other competitive meta-learning techniques.",
            "source_url": "https:\/\/openalex.org\/W7203509209",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Rice Research Repository (Rice University)",
            "source_record_id": "W7203509209",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 423,
            "title": "Neural transfer learning for natural language processing",
            "title_ar": "",
            "title_en": "Neural transfer learning for natural language processing",
            "author": "Sebastian Ruder",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Dublin Institute of Technology",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Ireland",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; nlp; transfer-learning; llm",
            "keywords": "",
            "abstract": "The current generation of neural network-based natural language processing models excels at learning from large amounts of labelled data. Given these capabilities, natural language processing is increasingly applied to new tasks, new domains, and new languages. Current models, however, are sensitive to noise and adversarial examples and prone to overfitting. This brittleness, together with the cost of attention, challenges the supervised learning paradigm. Transfer learning allows us to leverage knowledge acquired from related data in order to improve performance on a target task. Implicit transfer learning in the form of pretrained word representations has been a common component in natural language processing. In this dissertation, we argue that more explicit transfer learning is key to deal with the dearth of training data and to improve downstream performance of natural language processing models. We show experimental results transferring knowledge from related domains, tasks, and languages that support this hypothesis. We make several contributions to transfer learning for natural language processing: Firstly, we propose new methods to automatically select relevant data for supervised and unsupervised domain adaptation. Secondly, we propose two novel architectures that improve sharing in multi-task learning and outperform single-task learning as well as the state-of-the-art. Thirdly, we analyze the limitations of current models for unsupervised cross-lingual transfer and propose a method to mitigate them as well as a novel latent variable cross-lingual word embedding model. Finally, we propose a framework based on fine-tuning language models for sequential transfer learning and analyze the adaptation phase.",
            "source_url": "https:\/\/openalex.org\/W2979736514",
            "pdf_url": "",
            "doi": "10.13025\/17598",
            "handle": "",
            "repository_name": "Arrow@dit (Dublin Institute of Technology)",
            "source_record_id": "W2979736514",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 452,
            "title": "Computer Vision for Aircraft Fuselage Defect Detection: A YOLO11-Based Approach",
            "title_ar": "",
            "title_en": "Computer Vision for Aircraft Fuselage Defect Detection: A YOLO11-Based Approach",
            "author": "Pedro Afonso Bruno Arroteia",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Portugal",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "object-detection",
            "categories": "machine-learning; deep-learning; computer-vision; ai-applications; transfer-learning; self-semi-supervised; predictive-analytics; object-detection; image-segmentation; ai-industry",
            "keywords": "",
            "abstract": "Aircraft fuselages are exposed to operational and environmental stresses that generate defects such as scratches, paint peeling, rust, and rivet damage. Conventional inspection techniques, though widely used, are labor-intensive, time-consuming, and dependent on inspector expertise, which can lead to variability and overlooked anomalies. These chal- lenges highlight the need for automated solutions that ensure consistency and efficiency in quality inspection processes. This thesis presents the development of a computer vision-based system for auto- mated aircraft fuselage defect detection, combining deep learning with a user-oriented interface. The system employs the YOLO11 object detection architecture, fine-tuned on a specialized dataset to detect and classify four defect types. To mitigate data scarcity and class imbalance, data augmentation and transfer learning were applied. The model was evaluated on training, validation, and testing sets, achieving 0.814 precision and 0.735 recall on the training set, and on the validation set 0.722 precision, 0.787 recall, 0.659 accuracy, mAP@0.5 of 0.82, and mAP@0.5:0.95 of 0.524. Beyond model training, a RESTful API and web-based Human–Machine Interface were developed, enabling inspection images to be uploaded and processed, with results presented as bounding boxes, defect types, and confidence scores. This integration reflects Industry 5.0 principles of human–AI collaboration by allowing technicians to interpret, adjust, and validate predictions. The results demonstrate the feasibility of an intelligent inspection system that enhances accuracy, efficiency, and transparency in aircraft maintenance workflows. While challenges such as dataset scarcity and background variability remain, the framework establishes a solid foundation for future work in semi-supervised learning, segmentation-based approaches, and real-time deployment on edge devices. By contributing both a validated detection model and an operational platform, this study advances the application of AI in aviation quality inspection and supports safer, more efficient maintenance practices.",
            "source_url": "https:\/\/openalex.org\/W7224044969",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)",
            "source_record_id": "W7224044969",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 468,
            "title": "Real-Time Object Detection and Grasping for a Robotic Arm",
            "title_ar": "",
            "title_en": "Real-Time Object Detection and Grasping for a Robotic Arm",
            "author": "Thanh Thoi Nguyen",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "object-detection",
            "categories": "deep-learning; computer-vision; robotics; object-detection",
            "keywords": "",
            "abstract": "Research and development with robotic arms have been explored for their potential to perform various physical tasks such as sorting items by colors and shapes.Prior work and research made advancements with robotic arm systems by combining them with deep neural networks (DNN) and computer-based vision to detect and interact with objects.These systems take a massive amount of time to deploy and develop due to time-consuming DNN training costs.This training cost staggers the development of robotic arms since computer vision needs a DNN to operate.Many of these systems rely on object detection to pick up items from a fixed camera overhead within their field of vision.Fixed overhead cameras compensate for the limitation of computer vision to properly locate and estimate the distances of the object in 3D space.Such that an overhead camera will assume detected objects will be on the surfaces directly in front.Research to estimate distance with computer vision relies on well-trained DNN to estimate accurately.Computer vision distance estimation has had yet to be successful with robotic arm systems.This project aims to reduce the training cost on DNN by using Transfer-Learning, to promptly deploy a well-trained DNN to a robotic arm system to detect an object and estimate its distance from a non-fixed field of vision to grasp objects in real-time.",
            "source_url": "https:\/\/openalex.org\/W4284885449",
            "pdf_url": "http:\/\/scholarworks.calstate.edu\/downloads\/nk322m021",
            "doi": "10.46569\/20.500.12680\/6t053n59p",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W4284885449",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 472,
            "title": "Deep Learning for Plant Disease Detection Using Image Analysis",
            "title_ar": "",
            "title_en": "Deep Learning for Plant Disease Detection Using Image Analysis",
            "author": "Muhammad Butt",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Eastern Finland",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Finland",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "cnn",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; responsible-ai; ai-applications; transfer-learning; cnn; xai; ai-agriculture",
            "keywords": "",
            "abstract": "The study explores the design and execution viability of deep learning algorithms to the automated system of identifying plant diseases using leaf images.The global agricultural sector is experiencing significant losses in crop production due to late or inappropriate diagnosis of diseases caused by diseases especially in areas that lack agronomic knowledge.Four convolutional neural network architectures were tested to reduce such a problem: one of my own baseline CNN, ResNet-50, Inception-v3, and EfficientNet-B0.Training of the models was done using the PlantVillage dataset with the help of transfer learning, data augmentation, and routine preprocessing operations.The model performance was measured based on the accuracy, the precision, the recall, the F1score and ROC-AUC.Robustness testing was done by the introduction of synthetic noise, changes in light, and background complexity to simulate conditions in the realworld field.Grad-CAM visualisations were also added to increase the clarity and transparency of the model decisions.With empirical findings, it has been shown that EfficientNet-B0 gives an optimal trade-off between classification accuracy and computational efficiency, making it suitable to be deployed on a mobile or edge platform.The research offers practical results to the scalable, explainable, and resourceefficient implementation of artificial intelligence systems in the area of disease management in agriculture.",
            "source_url": "https:\/\/openalex.org\/W7215477915",
            "pdf_url": "https:\/\/erepo.uef.fi\/bitstreams\/7d1433de-a71a-45fc-b741-2ce3d525322e\/download",
            "doi": "",
            "handle": "",
            "repository_name": "UEF eRepo (University of Eastern Finland)",
            "source_record_id": "W7215477915",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 474,
            "title": "An efficient deep learning approach to detect plant diseases using image data",
            "title_ar": "",
            "title_en": "An efficient deep learning approach to detect plant diseases using image data",
            "author": "Ahmad Anis ; Babli Saha ; Maisa Tarannum Srizee",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "BRAC University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Bangladesh",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; ai-applications; transfer-learning; predictive-analytics; cnn; transformers; ai-agriculture",
            "keywords": "",
            "abstract": "Plant diseases drastically impact on the yield and quality of crops and this is a great challenge to food security and sustainable agriculture in the world and more so in countries such as Bangladesh. There is need to therefore ensure the early and accurate diagnosis of plant diseases to enhance productivity and safeguard food supplies. Plant disease classification based on images has been highly successful with the swift development of deep learning, especially Convolutional Neural Networks (CNNs).In this thesis, a lightweight hybrid CNN-Transformer model is suggested as a classification of rice leaf disease. A number of pretrained CNN models, such as ResNet50, VGG16, InceptionV3, MobileNet V3, EfficientNetB0, and DenseNet121 are tested with transfer learning to determine the baseline performance. The dataset used in the study is the 23, 265 images of rice leaf in 10 different classes including healthy and diseased. To (hopefully) bypass the shortcomings of single-architecture models, the hybrid model proposed replaces local feature extraction with EfficientNetB0 and global contextual learning with TinyViT as well as a lightweight version of MobileNet. The experimental findings indicate that the hybrid method is better than single CNN and independent Transformer models as it has an accuracy of 98.04%with high precision, recall, and F1-score and low costs of computation. The results demonstrate the usefulness of lightweight CNN-Transformer models in real-time and resource-limited agricultural disease prediction and farm health crop management.",
            "source_url": "https:\/\/openalex.org\/W7202234903",
            "pdf_url": "https:\/\/dspace.bracu.ac.bd\/bitstreams\/270bad3b-32c1-4c00-9d85-93d3776dcfb2\/download",
            "doi": "",
            "handle": "",
            "repository_name": "BRAC University Institutional Repository (BRAC University)",
            "source_record_id": "W7202234903",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 478,
            "title": "Transfer Learning-Based EfficientNetB0 Model for Multi-Crop Plant Disease Classification",
            "title_ar": "",
            "title_en": "Transfer Learning-Based EfficientNetB0 Model for Multi-Crop Plant Disease Classification",
            "author": "Mebrahtu Yohannes",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Ethiopia",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "cnn",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; ai-applications; transfer-learning; cnn; ai-agriculture",
            "keywords": "",
            "abstract": "globally. Early and accurate diagnosis of diseases is key to reducing losses and improving agricultural practices. Traditional methods of plant disease diagnosis are known for being lengthy, cumbersome, and prone to human error. Recent developments in deep learning have shown promise in the automatic diagnosis and classification of plant diseases. Namely, convolutional neural networks (CNNs) perform quite well for such problems. The purpose of this study is to present an approach to plant disease classification that is based on the use of transfer learning and utilizes the Convolutional Neural Network architecture called EfficientNetB0. Transfer learning with ImageNet pretrained weights and an efficient architecture for feature extraction was chosen because of its ability to significantly lower the computational resources required and improve performance. Moreover, plant leaf images from different datasets were taken into account to provide better training. The model achieved 99.32 % training accuracy, 99.37% validation accuracy, and 99.32% test accuracy. It also had impressive convergence capability and low computational complexity, with around 4.7 million parameters and the size of the saved model at around 34 MB. It can be concluded from the findings that the transfer learning-based EfficientNetB0 model provides a great balance between accurate classification and efficiency, while improving the practicality of the system.",
            "source_url": "https:\/\/openalex.org\/W7212441753",
            "pdf_url": "",
            "doi": "10.82589\/muir-1230",
            "handle": "",
            "repository_name": "Mekelle University Institutional Repository (MU-IR)",
            "source_record_id": "W7212441753",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 483,
            "title": "Salient map image for plant disease using deep learning",
            "title_ar": "",
            "title_en": "Salient map image for plant disease using deep learning",
            "author": "Poey Poey Quah",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "image-segmentation",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; ai-applications; transfer-learning; cnn; image-segmentation; ai-agriculture",
            "keywords": "",
            "abstract": "Plant diseases are a critical factor that impacts the yield and quality of crops and economics in the agricultural sector. This can shown in the incident of a fungal wheat disease in North Texas caused $250 million loss of revenue of the affected country in the year of 2001. Hence, there is essential in protecting the crops from diseases to ensure production quality and quantity. Early detection of the plant diseases is necessary, and it can help to prevent the spreading of the diseases by choosing an appropriate treatment for the plants. However, the process is often trailed by the lack of necessary infrastructure that offers simplicity in performing accurate classifications. Thus, rapid and accurate detection of plant disease through machine learning is essential to minimizing or averting this hardship. On top of that, the existing work does not segment the progression area of the disease on the leaf. In which, this area giving a lot of information on the disease. Especially to the pattern of disease symptoms that are very similar such as in the case of vegetable early and late blight is currently not given much consideration in the machine learning process. Hence, the objective of this project is to construct a salient map image that tracks the disease progression right from inception to manifestation following the pathological disease anatomy. Semantic segmentation with ConvolutionalNeuralNetwork (CNN) is used to construct the salient map image, through transfer learning with SegNet. In this project, 460 images of early blight and late blight diseases plants from PlantVillage dataset is used for the training and testing processes of the CNN. Next, the training parameters are fine-tuned in order to optimize the deep learning model accuracy. At the end of the project, the deep learning model will be able to segment the leaf image into several regions with the overall accuracy of 89.567% and overall IOU of 52.5448%. Also, although the transfer learning on FCN with same data-set and training parameters has slightly better performance with overall accuracy of 89.91% and IOU of 53.92%, its main drawbacks of long model training duration and consumption of huge memory size has made SegNet more preferable in this project. With the gradient map image generated, the pattern of each disease manifestation along the leaf surface can be tracked and quantified for better understanding and characterization based on their anatomy.",
            "source_url": "https:\/\/openalex.org\/W3213994822",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W3213994822",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 490,
            "title": "Android application for crop disease diagnosis using image processing and deep learning (Smart Agriculture).",
            "title_ar": "",
            "title_en": "Android application for crop disease diagnosis using image processing and deep learning (Smart Agriculture).",
            "author": "Munashe Brian Katsande",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Zimbabwe",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Zimbabwe",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "object-detection",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; ai-applications; transfer-learning; cnn; object-detection; ai-agriculture",
            "keywords": "",
            "abstract": "Plant diseases are a major threat to food security worldwide. An accurate and a faster approach to detection and diagnosis of diseases in crops will go a long way to help farmers save their crop and increase yield. Recent developments in smartphone technology and deep neural networks have allowed researchers to develop accurate and ease to use systems to help farmer in this regard. In this dissertation, we developed an android based cotton crop disease detector using deep convolutional networks and image processing. We made use of transfer learning using a pre trained Inceptionv3 model. Additional layers were added to the pretrained model and trained on our dataset. The trained model finally integrated into an android mobile app and experimental results on the developed model were able to achieve an average accuracy of 83%.",
            "source_url": "https:\/\/openalex.org\/W3201423842",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "University of Zimbabwe Institutional Repository (University of Zimbabwe)",
            "source_record_id": "W3201423842",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 494,
            "title": "Deep Learning for Early Detection, Identification, and Spatiotemporal Monitoring of Plant Diseases Using Multispectral Aerial Imagery",
            "title_ar": "",
            "title_en": "Deep Learning for Early Detection, Identification, and Spatiotemporal Monitoring of Plant Diseases Using Multispectral Aerial Imagery",
            "author": "Joseph Mbugua",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Claremont Colleges",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "image-classification",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; ai-applications; transfer-learning; cnn; image-classification; ai-agriculture",
            "keywords": "",
            "abstract": "Production of food crops is hampered by the proliferation of crop diseases which cause huge harvest losses. Current crop-health monitoring programs involve the deployment of scouts and experts to detect and identify crop diseases through visual observation. These monitoring schemes are expensive and too slow to offer timely remedial recommendations for preventing the spread of these crop-damaging diseases. There is thus a need for the development of cheaper and faster methods for identifying and monitoring crop diseases. Recent advances in deep learning have enabled the development of automatic and accurate image classification systems. These advances coupled with the widespread availability of multispectral aerial imagery provide a cost-effective method for developing crop-diseases classification tools. However, large datasets are required to train deep learning models, which may be costly and difficult to obtain. Fortunately, models trained on one task can be repurposed for different tasks (with limited data) using transfer learning technique. The purpose of this research was to develop and implement an end-to-end deep learning framework for early detection and continuous monitoring of crop diseases using transfer learning and high resolution, multispectral aerial imagery. In the first study, the technique was used to compare the performance of five pre-trained deep learning convolutional neural networks (VGG16, VGG19, ResNet50, Inception V3, and Xception) in classifying crop diseases for apples, grapes, and tomatoes. The results of the study show that the best performing crop-disease classification models were those trained on the VGG16 network, while those trained on the ResNet50 network had the worst performance. The other studies compared the performance of using transfer learning and different three-band color combinations to train single- and multiple-crop classification models. The results of these studies show that models combining red, near infrared, and blue bands performed better than models trained with the traditional visible spectral band combination of red, green, and blue. The worst performing models were those combining near infrared, green, and blue bands. This research recommends that further studies be undertaken to determine the best band combinations for training single- and multi-label classification models for both crops and plants and diseases that affect them.",
            "source_url": "https:\/\/openalex.org\/W3177001023",
            "pdf_url": "https:\/\/scholarship.claremont.edu\/cgi\/viewcontent.cgi?article=1237&context=cgu_etd",
            "doi": "10.5642\/cguetd\/218",
            "handle": "",
            "repository_name": "Scholarship - Claremont (Claremont Colleges)",
            "source_record_id": "W3177001023",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 506,
            "title": "Scalability and interpretability of graph neural networks for small molecules",
            "title_ar": "",
            "title_en": "Scalability and interpretability of graph neural networks for small molecules",
            "author": "Manjot. Sangha",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Massachusetts Institute of Technology",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "gnn",
            "categories": "machine-learning; deep-learning; responsible-ai; ai-applications; transfer-learning; predictive-analytics; gnn; xai; ai-smart-cities",
            "keywords": "",
            "abstract": "In this thesis I examine the use of graph neural networks for prediction tasks in chemistry with an emphasis on interpretable and scalable methods. I propose a novel kernel-inspired graph neural network architecture, called a subgraph matching neural network (SMNN), which is designed to have all feature representations and weights be human interpretable. I show that this network can achieve competitive performance with common graph neural network baselines. I also show that the network is capable of learning features that allow for transfer learning to larger molecules with significantly better performance than some baselines. This provides evidence the network is learning chemically useful representations. I then propose a framework for defining graph pooling operations to improve the scalability of graph neural networks with molecule size. I empirically examine some examples of these graph pooling layers and show that they can provide a significant speed-up without hurting accuracy, and even improving accuracy in some cases. Finally an instance of the SMNN network with a pooling layer is shown to achieve state-of-the-art accuracy on the Harvard Clean Energy Project dataset.",
            "source_url": "https:\/\/openalex.org\/W2962495078",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "DSpace@MIT (Massachusetts Institute of Technology)",
            "source_record_id": "W2962495078",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 558,
            "title": "Domain adaptation in Natural Language Processing",
            "title_ar": "",
            "title_en": "Domain adaptation in Natural Language Processing",
            "author": "Marina Sedinkina",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Ludwig-Maximilians-Universität München",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Germany",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "sentiment-analysis",
            "categories": "machine-learning; nlp; transfer-learning; predictive-analytics; sentiment-analysis",
            "keywords": "",
            "abstract": "Domain adaptation has received much attention in the past decade. It has been shown that domain knowledge is paramount for building successful Natural Language Processing (NLP) applications. To investigate the domain adaptation problem, we conduct several experiments from different perspectives. First, we automatically adapt sentiment dictionaries for predicting the financial outcomes “excess return” and “volatility”. In these experiments, we compare manual adaptation of the domain-general dictionary with automatic adaptation, and manual adaptation with a combination consisting of first manual, then automatic adaptation. We demonstrate that automatic adaptation performs better than manual adaptation, namely the automatically adapted sentiment dictionary outperforms the previous state of the art in predicting excess return and volatility. Furthermore, we perform qualitative and quantitative analyses finding that annotation based on an expert’s a priori belief about a word’s meaning is error-prone – the meaning of a word can only be recognized in the context that it appears in. Second, we develop the temporal transfer learning approach to account for the language change in social media. The language of social media is changing rapidly – new words appear in the vocabulary, and new trends are constantly emerging. Temporal transfer-learning allows us to model these temporal dynamics in the document collection. We show that this method significantly improves the prediction of movie sales from discussions on social media forums. In particular, we illustrate the success of parameter transfer, the importance of textual information for financial prediction, and show that temporal transfer learning can capture temporal trends in the data by focusing on those features that are relevant in a particular time step, i.e., we obtain more robust models preventing overfitting. Third, we compare the performance of various domain adaptation models in low-resource settings, i.e., when there is a lack of large amounts of high-quality training data. This is an important issue in computational linguistics since the success of NLP applications primarily depends on the availability of training data. In real-world scenarios, the data is often too restricted and specialized. In our experiments, we evaluate different domain adaptation methods under these assumptions and find the most appropriate techniques for such a low-data problem. Furthermore, we discuss the conditions under which one approach substantially outperforms the other. Finally, we summarize our work on domain adaptation in NLP and discuss possible future work topics.",
            "source_url": "https:\/\/openalex.org\/W3164246911",
            "pdf_url": "",
            "doi": "10.5282\/edoc.27831",
            "handle": "",
            "repository_name": "Elektronische Hochschulschriften der LMU München (Ludwig-Maximilians-Universität München)",
            "source_record_id": "W3164246911",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 569,
            "title": "Efficient Rare Disease Detection with Self-Supervised and Transfer Learning",
            "title_ar": "",
            "title_en": "Efficient Rare Disease Detection with Self-Supervised and Transfer Learning",
            "author": "Miftahul Jannat",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Eastern Finland",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Finland",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; self-semi-supervised; predictive-analytics; cnn; medical-imaging",
            "keywords": "",
            "abstract": "Accurate diagnosis of rare diseases by analyzing medical images is often faced with the problem of limited availability of annotated datasets, as the manual annotation process, being time-consuming, requires expert knowledge in addition to a significant time investment.The research explores the use of Self-Supervised Learning (SSL) combined with Transfer Learning as a method to reduce the dependency on labeled data without compromising diagnostic performance.The approach designed involves pretraining convolutional neural networks using large unlabeled datasets through self-supervised learning (SSL) methods.For this purpose, the CheXpert dataset of over 200000 X-ray images is employed.To enable the model to imbibe generalizable features from the unlabeled pictures, several SSL pretext tasks are applied, namely rotation prediction, jigsaw puzzles, as well as contrastive learning (SimCLR).Following the pretraining process, the models are fine-tuned using the ISIC 2018 dataset, which contains annotated dermoscopic images for the task of skin lesion classification.Feature extraction and classification performance are evaluated using different architectures, such as ResNet-50.Finetuning is performed using different percentages of labeled data (10%, 25%, 50%, and 100%) to evaluate the efficiency of annotations in semi-supervised learning (SSL).The performance and models have been assessed with respect to Accuracy, Precision, Recall, and F1 Score.From the results, it appears that SSL-pretrained models using SimCLR outperformed fully supervised models even when they were trained on significantly fewer labeled samples.It is astonishing that models which were trained with only 50% of the labeled data actually achieved over 75% accuracy in comparison to those trained on the complete dataset.This work demonstrates that the semi-supervised learning (SSL) approach made possible through transfer learning is a highly effective and efficient in terms of labeling resources for detecting rare diseases in medical images.",
            "source_url": "https:\/\/openalex.org\/W7215667449",
            "pdf_url": "https:\/\/erepo.uef.fi\/bitstreams\/9b495e9a-88c8-4914-8f52-550745585eb9\/download",
            "doi": "",
            "handle": "",
            "repository_name": "UEF eRepo (University of Eastern Finland)",
            "source_record_id": "W7215667449",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 586,
            "title": "Semi-Supervised Image Segmentation of Medical Data",
            "title_ar": "",
            "title_en": "Semi-Supervised Image Segmentation of Medical Data",
            "author": "Ove Nicolai Dalheim",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Norway",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "image-segmentation",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; self-semi-supervised; data-mining; cnn; image-segmentation",
            "keywords": "",
            "abstract": "Bladder cancer is the fourth most common cancer type in Norway, and tenth most common on a global scale. More and more tissue samples are sent to pathologists labs, increasing the workload and affecting the waiting time for patients. The corresponding increase is not seen in number of pathologists. Digitization and scanning of the tissue samples unveil the world of computational pathology, along with the many possibilities within it. Supervised approaches have been proposed within deep learning earlier, however, many express the lack of labeled data as a source for performance degradation. Convolutional neural networks have proven effective on image processing within the field of medicine. Some work based on semi-supervised approaches within computational pathology has been published in the recent years, however, most researchers are exploring supervised methods. This thesis proposes several methods to tile-wise segment histological images of bladder cancer into six different classes background, blood, damaged tissue, muscle tissue, stroma tissue and urothelium. A multiscale model is fed the tile at three different levels of magnification, and inherits capabilities from the VGG16 network through transfer learning. The proposed methods are either based on semi-supervised learning utilizing probability or clustering within a self-training process, or based on a combination of both expert and non-expert annotations. The dataset used in this thesis consists of about 360 whole-slide images, of which only 37 contain regions annotated by a pathologist, allowing for only about 10 % of the dataset to be utilized for supervised methods. Through the course of this thesis, a total of 145 new whole-slide images were introduced during training through semi-supervised learning, utilizing about 50 % of the dataset through various methods. The non-expert approach increased the F1-score for the muscle tissue class with 9.18 % from an initial 79.42 %, and the cluster-baser approach saw an increase of 1.38 % in accuracy from the initial 94.61 %. The method involving non-expert annotations outperformed both semi-supervised techniques with regards to segmentation, as a semi-supervised method will introduce new uncertain features to a deep learning model. This will have a strong impact on sensitive classes that are poorly represented in the training dataset. That said, a significant improvement is seen by using semi-supervised techniques as well, and scored better than non-expert with regards to classification.",
            "source_url": "https:\/\/openalex.org\/W3087951694",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "NORA - Norwegian Open Research Archives",
            "source_record_id": "W3087951694",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 615,
            "title": "Curriculum learning in reinforcement learning",
            "title_ar": "",
            "title_en": "Curriculum learning in reinforcement learning",
            "author": "Sanmit Narvekar",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "reinforcement-learning",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; reinforcement-learning; transfer-learning",
            "keywords": "",
            "abstract": "In recent years, reinforcement learning (RL) has been increasingly successful at solving complex tasks. Despite these successes, one of the fundamental challenges is that many RL methods require large amounts of experience, and thus can be slow to train in practice. Transfer learning is a recent area of research that has been shown to speed up learning on a complex task by transferring knowledge from one or more easier source tasks. Most existing transfer learning methods treat this transfer of knowledge as a one-step process, where knowledge from all the sources are directly transferred to the target. However, for complex tasks, it may be more beneficial (and even necessary) to gradually acquire skills over multiple tasks in sequence, where each subsequent task requires and builds upon knowledge gained in a previous task. This idea is pervasive throughout human learning, where people learn complex skills gradually by training via a curriculum. The goal of this thesis is to explore whether autonomous reinforcement learning agents can also benefit by training via a curriculum, and whether such curricula can be designed fully autonomously. In order to answer these questions, this thesis first formalizes the concept of a curriculum, and the methodology of curriculum learning in reinforcement learning. Curriculum learning consists of 3 main elements: 1) task generation, which creates a suitable set of source tasks; 2) sequencing, which focuses on how to order these tasks into a curriculum; and 3) transfer learning, which considers how to transfer knowledge between tasks in the curriculum. This thesis introduces several methods to both create suitable source tasks and automatically sequence them into a curriculum. We show that these methods produce curricula that are tailored to the individual sensing and action capabilities of different agents, and show how the curricula learned can be adapted for new, but related target tasks. Together, these methods form the components of an autonomous curriculum design agent, that can suggest a training curriculum customized to both the unique abilities of each agent and the task in question. We expect this research on the curriculum learning approach will increase the applicability and scalability of RL methods by providing a faster way of training reinforcement learning agents, compared to learning tabula rasa.",
            "source_url": "https:\/\/openalex.org\/W2742132707",
            "pdf_url": "",
            "doi": "10.26153\/tsw\/13849",
            "handle": "",
            "repository_name": "Texas Digital Library (University of Texas)",
            "source_record_id": "W2742132707",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 622,
            "title": "Reinforcement learning for argumentation",
            "title_ar": "",
            "title_en": "Reinforcement learning for argumentation",
            "author": "Sultan Alahmari",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "reinforcement-learning",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; reinforcement-learning; transfer-learning",
            "keywords": "",
            "abstract": "Argumentation as a logical reasoning approach plays an important role in improving communication, increasing agree-ability, and resolving conflicts in multi-agent-systems (MAS). The present research aims to explore the effectiveness of argumentation in reinforcement learning of intelligent agents in terms of, outperforming baseline agents, learning transfer between argument graphs, and improving relevance and coherence of dialogue quality. This research developed `ARGUMENTO+' to encourage a reinforcement learning agent (RL agent) playing abstract argument game for improving performance against different baseline agents by using a newly proposed state representation in order to make each state unique. When attempting to generalise this approach to other argumentation graphs, the RL agent was not able to effectively identify the argument patterns that are transferable to other domains. In order to improve the effectiveness of the RL agent to recognise argument patterns, this research adopted a logic-based dialogue game approach with richer argument representations. In the DE dialogue game, the RL agent played against hard-coded heuristic agents and showed improved performance compared to the baseline agents by using a reward function that encourages the RL agent to win the game with minimum number of moves. This also allowed the RL agent to adopt its own strategy, make moves, and learn to argue. This thesis also presents a new reward function that makes the RL agent's dialogue more coherent and relevant than its opponents. The RL agent was designed to recognise argument patterns, i.e. argumentation schemes and evidence support sources, which can be related to different domains. The RL agent used a transfer learning method to generalise and transfer experiences and speed up learning.",
            "source_url": "https:\/\/openalex.org\/W3091679651",
            "pdf_url": "http:\/\/etheses.whiterose.ac.uk\/27361\/1\/Alahmari_106031396_Thesis.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York)",
            "source_record_id": "W3091679651",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 677,
            "title": "Transfer Learning Methods for Object and Action Recognition",
            "title_ar": "",
            "title_en": "Transfer Learning Methods for Object and Action Recognition",
            "author": "Samitha Herath",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Australian National University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Australia",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "video-analysis",
            "categories": "machine-learning; computer-vision; generative-ai; ai-applications; transfer-learning; few-zero-shot; video-analysis; gan; ai-education",
            "keywords": "",
            "abstract": "Thanks to the advancement of machine learning and computer vision research we are observing remarkable improvements in object and action recognition. However, it can be seen that when there are differences (e.g., distributional, representations, semantic) in the training and test data, many learning algorithms fail to perform well or at times becomes infeasible. Nevertheless, problem setups dealing specifically with such differences are constantly being explored in literature. In general these problems are known as transfer learning problems. For instance, the objective of Domain Adaptation (DA) is to learn models that are invariant to distributional differences between train and test data (i.e., source and target domain data). Zero-Shot Learning (ZSL) is a framework for recognizing instances from classes never seen during training (i.e., missing classes in training data). In ZSL, the idea is to use related semantic information about data to workaround this data deficiency. In this thesis we present two solutions for Domain Adaptation and Zero-Shot Learning. First, we discuss our DA solution for learning an invariant Hilbert space for source and target domain data embedding. This is achieved by learning projections from individual domains to a latent space. We learn a Mahalanobis metric on this latent space to simultaneously minimizing domain disparity while maximizing a measure of discriminative power. We also show that the alignment of statistical properties (e.g., first and second order statistics) helps in improving our solution's performance, especially when there are no labeled samples from the target domain. We explore the effect of geometrical constraints such as orthogonality and positive definiteness for our model. Here, we use Riemannian optimization methods to seamlessly implement these constraints in our model training. Inspired by the success of statistical alignment, we further explore statistical alignment by min-max learning. Our motivation here is to avoid the trivial feature degeneration occurring when aligning two spaces by minimizing a statistical loss such as KL divergence. Here, we show that min-max statistical alignment is a promising solution for DA as well as ZSL. In fact, we show that min-max statistical alignment can reach comparable performance with state of the art adversarial solutions, including the ones using powerful Wasserstein GANs as the backbone. Lastly, we discuss our work on spatio-temporal transfer learning for human action recognition. In our survey on human action recognition from videos, we extensively study representation based and deep network based action recognition solutions. Here, we observe that one of the high-impact video action recognition solutions is the Two-Stream networks solution. However, the applicability of two-stream solution requires a temporal stream. In other words this restricts its applicability only to video data. In this work we explore use of transfer learning methods for devising two stream action recognition for still action images where there are no temporal information. We call this Temporal to Still Image Learning (or in short T2SIL). To explore the T2SIL framework we use existing still image and video datasets to form a new human action dataset of 40 classes. The data set contains still image actions and a video actions counterpart with the same set of classes. In this work, we explore three state of the art transfer learning solutions (i.e., Deep embedding learning, GANs and model distillation with Teacher-Student Networks) for T2SIL.",
            "source_url": "https:\/\/openalex.org\/W3036155538",
            "pdf_url": "",
            "doi": "10.25911\/5ee74e7c697e0",
            "handle": "",
            "repository_name": "ANU Open Research (Australian National University)",
            "source_record_id": "W3036155538",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 711,
            "title": "CNN-Based Deep Learning Models for Automated Tuberculosis Detection from Chest X-rays",
            "title_ar": "",
            "title_en": "CNN-Based Deep Learning Models for Automated Tuberculosis Detection from Chest X-rays",
            "author": "Pooja Santhosh",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "National College of Ireland",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Ireland",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; medical-imaging",
            "keywords": "",
            "abstract": "Tuberculosis (TB) remains one of the leading health concerns of the world especially in the low-resource regions where radiologists who can help one with diagnosis are scarce. Although chest X-ray imaging is prevailing examinations used in the screening of TB, it relies strongly on interpretation of experts and may prejudice performance and delay in areas that are under-privileged. Luckily, due to the advent of artificial intelligence, methods of deep learning, and Convolutional Neural Networks (CNNs) have a very high potential of automating the process of analysing medical images. The purpose of this project is to carry out the comparison of the performance of the three most popular and popular pretrained CNN architectures ResNet18, DenseNet121, and EfficientNet-B0 to see which model is more suitable in the problem of detecting TB based on a chest X-ray. We already have a publicly available dataset in Kaggle and will fine-tune the models by using transfer learning. We will use a stratified data split by training, validation and test sets to balance the set classes. All models are going to be tested in PyTorch with standard metrics such as accuracy, precision, accuracy and F1-score. The findings of the given comparison will illuminate on the trade-off between accuracy and computational efficiency of the models.",
            "source_url": "https:\/\/openalex.org\/W7204614449",
            "pdf_url": "https:\/\/norma.ncirl.ie\/9663\/2\/poojasanthoshconfigurationmanual.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "TRAP@NCI (National College of Ireland)",
            "source_record_id": "W7204614449",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 713,
            "title": "Analisis Kerentanan Model CNN terhadap Serangan PGD pada Klasifikasi Citra X-ray COVID-19",
            "title_ar": "",
            "title_en": "Analisis Kerentanan Model CNN terhadap Serangan PGD pada Klasifikasi Citra X-ray COVID-19",
            "author": "Elga Putri Tri Farma",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Maine at Machias",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; ai-applications; transfer-learning; cnn; medical-imaging; ai-cybersecurity",
            "keywords": "",
            "abstract": "Advances in deep learning have revolutionized lung disease diagnosis through chest X-ray (CXR) images, particularly since the COVID-19 pandemic. Convolutional Neural Network (CNN) architectures such as DenseNet-121 demonstrate high accuracy in distinguishing viral pneumonia, lung opacity, and normal cases. However, recent studies reveal that these models possess fundamental weaknesses against iteratively designed adversarial attacks. This study aims to analyze the robustness of the DenseNet-121 model against the Projected Gradient Descent (PGD) attack in a four-class classification task on COVID-19 chest X-ray images. The methodology involves training the model using transfer learning on the COVID-19 Radiography Dataset (21,165 images), followed by testing with PGD attacks at various epsilon levels (0.1\/255 to 0.3\/255). The results show that at epsilon 0.1\/255, global model accuracy drops drastically from 95.42% to 25.32%, with an Attack Success Rate (ASR) reaching 74.68%. The most severe degradation occurs in the Lung Opacity class (F1-score drop of 88.90%) and the COVID-19 class (F1-score drop of 82.99%). Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations reveal the phenomenon of semantic decoupling, where the model's attention shifts from diseased lung regions toward background artifacts. In conclusion, the iterative nature of PGD attacks effectively exploits gaps in high-dimensional decision manifolds, rendering unprotected CNN models unsuitable for direct deployment in attack-prone clinical environments.",
            "source_url": "https:\/\/openalex.org\/W7219288436",
            "pdf_url": "https:\/\/eprints.umm.ac.id\/id\/eprint\/34043\/1\/PENDAHULUAN.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "UMM Institutional Repository (University of Maine at Machias)",
            "source_record_id": "W7219288436",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 715,
            "title": "Deep Learning-Based Automated Pneumonia Detection from Chest X-Rays: A Comparative Study of Custom CNN and Transfer Learning Architectures",
            "title_ar": "",
            "title_en": "Deep Learning-Based Automated Pneumonia Detection from Chest X-Rays: A Comparative Study of Custom CNN and Transfer Learning Architectures",
            "author": "Ahmed Sajim",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Southern Mississippi",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; medical-imaging",
            "keywords": "",
            "abstract": "Pneumonia is a leading global cause of mortality, claiming approximately 2.5 million lives an-nually and placing exceptional diagnostic pressure on radiologists in resource-limited settings. Manual interpretation of chest X-ray (CXR) images is time-consuming, subject to inter-observer variability, and limited by radiologist availability. This thesis presents a systematic investiga-tion into deep learning-based automated pneumonia detection comparing five convolutional neural network (CNN) architectures: a custom-designed 2D CNN and four pretrained transfer learning models—ResNet, DenseNet, MobileNet, and VGG19. A targeted data augmentation pipeline addresses the severe class imbalance in the Kag-gle Chest X-Ray Pneumonia dataset, expanding the Normal class from 1,583 to 9,495 images using clinically motivated transformations. The proposed Custom CNN incorporates progres-sive multi-scale filters (128→256→512), bottleneck 1×1 convolutions, and calibrated dropout regularization—all tailored for pneumonia-specific feature patterns. Evaluated on 2,066 held-out test images, the Custom CNN achieved the highest test accuracy of 97.5%, with 0.97 precision and recall across both classes and only 52 total misclassifications—outperforming all four transfer learning baselines. These results demonstrate that domain-specific architectural design combined with principled data balancing can surpass generic pretrained models for specialized medical imag-ing tasks on limited datasets.",
            "source_url": "https:\/\/openalex.org\/W7160676225",
            "pdf_url": "https:\/\/aquila.usm.edu\/cgi\/viewcontent.cgi?article=2101&context=honors_theses",
            "doi": "",
            "handle": "",
            "repository_name": "Aquila Digital Community (University of Southern Mississippi)",
            "source_record_id": "W7160676225",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 718,
            "title": "Improving Model Generalization of Pneumonia Detection from Chest Xray Images Using Deep Learning and Transfer Learning",
            "title_ar": "",
            "title_en": "Improving Model Generalization of Pneumonia Detection from Chest Xray Images Using Deep Learning and Transfer Learning",
            "author": "Akhil Kochamparampil Anil",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Wales Trinity Saint David",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; medical-imaging",
            "keywords": "",
            "abstract": "Pneumonia continues to be a major global health threat and one of the leading causes of mortality, with chest X-rays serving as the primary diagnostic tool. Despite their promise, deep learning models for pneumonia detection often face limitations in generalization, performing strongly on familiar datasets but losing accuracy when applied to unseen data from different clinical environments. This study addresses that challenge by applying transfer learning with ResNet152 and DenseNet201 to improve generalization in pneumonia detection using chest Xray images. Publicly available datasets, including the COVID-19 Radiography Database and the Chest X-ray (COVID-19 & Pneumonia) dataset, were merged, pre-processed, and balanced prior to training. Model optimization involved freezing and unfreezing layers, adjusting learning rates, and applying various data augmentation strategies. Performance was evaluated with metrics such as accuracy, precision, recall, F1-score, error rate, and AUC-ROC, and further validated using an independent external dataset. Experimental results showed that DenseNet201 consistently outperformed ResNet152, reaching 93.2% accuracy with an AUC of 0.9916 on the main dataset and 88.3% accuracy with an AUC of 0.9742 on the external dataset. By comparison, ResNet152 achieved 86.4% accuracy (AUC 0.9665) on the main dataset and 84.6% accuracy (AUC 0.9573) on the external dataset. Confusion matrix analysis revealed that most errors occurred between Normal and Pneumonia classes, mirroring real world diagnostic challenges. In conclusion, DenseNet201 demonstrated superior robustness and generalization compared to ResNet152, highlighting its suitability for clinical application and underscoring the necessity of external validation in medical AI research.",
            "source_url": "https:\/\/openalex.org\/W7135203014",
            "pdf_url": "https:\/\/repository.uwtsd.ac.uk\/id\/eprint\/4143\/1\/Anil_Kochamparampil_A_MSc_Thesis.pdf",
            "doi": "10.82227\/repository.uwtsd.ac.uk.00004143",
            "handle": "",
            "repository_name": "University Of Wales Trinity Saint David Research Repository (University of Wales Trinity Saint David)",
            "source_record_id": "W7135203014",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 724,
            "title": "Detecting Coronavirus Disease 2019 Pneumonia in Chest X-Ray Images Using Deep Learning",
            "title_ar": "",
            "title_en": "Detecting Coronavirus Disease 2019 Pneumonia in Chest X-Ray Images Using Deep Learning",
            "author": "Ziqi Zhu",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; predictive-analytics; medical-imaging",
            "keywords": "",
            "abstract": "The coronavirus disease 2019 (COVID-19) pandemic has already become a global threat. To fight against COVID-19, effective and fast screening methods are needed. This study focuses on leveraging deep learning techniques to automatically detect COVID‐19 pneumonia in chest X-ray images. Two models are trained based on transfer learning and residual neural network. The first one is a binary classifier that separates COVID-19 pneumonia and non-COVID-19 cases. It classifies all test cases correctly. The second one is a four-class classifier that distinguishes COVID-19 pneumonia, viral pneumonia, bacterial pneumonia and normal cases. It reaches an average accuracy, precision, sensitivity, specificity, and F1-score of 93\\\\%, 93\\\\%, 93\\\\%, 97\\\\%, and 93\\\\%, respectively. To understand on how the four-class classifier detects COVID-19 pneumonia, we apply Gradient-weighted Class Activation Mapping (Grad-CAM) method and find out that the classifier is able to focus on the patchy areas in chest X-ray images and make accurate predictions.",
            "source_url": "https:\/\/openalex.org\/W3040290756",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "eScholarship (California Digital Library)",
            "source_record_id": "W3040290756",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 729,
            "title": "EVALUASI KINERJA MODEL MENGGUNAKAN CNN TRANSFER LEARNING PADA KLASIFIKASI X-RAY COVID-19 = PERFORMANCE EVALUATION OF THE MODEL USING CNN TRANSFER LEARNING ON COVID-19 X-RAY CLASSIFICATION",
            "title_ar": "",
            "title_en": "",
            "author": "Ramdan Masykuri",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Indonesia",
            "governorate": "",
            "publication_year": 2023,
            "language": "id",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; medical-ai; transfer-learning; cnn; medical-imaging",
            "keywords": "",
            "abstract": "Paru-paru merupakan bagian dari tubuh manusia yang memiliki peran penting dalam pernapasan. Masalah yang sering timbul pada paru-paru adalah kualitas udara yang masuk ke paru-paru apakah tercemar atau tidak. Pneumonia dan Covid-19 merupakan penyakit yang menyebabkan peradangan pada paru-paru dan dapat menyebabkan kematian, Covid-19 menjadi masalah besar bagi banyak negara di dunia sejak tahun 2020. Terdapat kesamaan antara Covid-19 dengan pneumonia pada gejala seperti batuk dan sesak napas. Pelaksanaan tes deteksi cepat Covid-19 tidak serta merta berjalan mulus, namun tim medis mengalami banyak kendala. Salah satu penyebabnya adalah terbatasnya jumlah alat tes Covid-19, sehingga perlu dilakukan deteksi dini untuk membedakan antara pneumonia dan Covid-19. Citra X-ray dapat digunakan untuk mendeteksi pneumonia dan Covid-19. Deteksi manual memungkinkan terjadinya kesalahan, sehingga perhitungan komputasi diperlukan untuk meminimalkan kesalahan. Salah satu metode yang digunakan adalah Transfer learning dengan menggunakan algoritma Convolutional Neural Network (CNN) beserta arsitektur Xception, Inceptionv3, dan MobileNet. Transfer learning adalah sebuah metode Machine Learning yang bekerja dengan cara meniru sistem kerja otak manusia, sistem ini disebut Neural Network. CNN merupakan salah satu jenis Neural Network yang fungsi utamanya digunakan untuk data citra. Penelitian dilakukan dengan 1200 data citra X-ray Covid-19 yang dibagi menjadi 3 kelas dengan 400 data citra untuk setiap kategori. Hasil terbaik dari semua model arsitektur yang dicoba adalah Xception mendapatkan akurasi training sebesar 96% dan akurasi validation sebesar 97%. Untuk model MobileNet mendapatkan akurasi training adalah 97% dan akurasi validation adalah 93%. Dan model InceptionV3 memiliki hasil yang paling rendah dibandingkan kedua arsitektur lainnya yaitu akurasi training sebesar 95% dan akurasi validation 93%.",
            "source_url": "https:\/\/openalex.org\/W7217499254",
            "pdf_url": "https:\/\/repository.unhas.ac.id\/id\/eprint\/45536\/2\/H071181502_skripsi_04-04-2023%201-2.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Hasanuddin University Repository",
            "source_record_id": "W7217499254",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 731,
            "title": "Use of Swin Transformer to classify chest radiographic images and diagnose COVID-19",
            "title_ar": "",
            "title_en": "Use of Swin Transformer to classify chest radiographic images and diagnose COVID-19",
            "author": "Aroldo Ferraz",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; transformers; medical-imaging",
            "keywords": "",
            "abstract": "According to data from the World Health Organization (WHO), since the beginning of 2020, the COVID-19 pandemic has infected over 770.56 million people worldwide. Of those infected, more than 6.95 million individuals have lost their lives. COVID-19 is an extremely contagious disease and can swiftly overwhelm healthcare systems if infections are not diagnosed, and if isolation measures and treatment for deteriorating conditions are not promptly implemented. The primary screening test used to diagnose COVID-19 has been the Real Time Reverse Transcription-Polymerase Chain Reaction (RT-PCR). Although it is accurate and reliable, it takes a significant amount of time to deliver a definitive diagnosis. Since the onset of the pandemic, several researchers have demonstrated the feasibility of employing various Deep Learning (DL) techniques based on Convolutional Neural Networks (CNN), which have shown promising performance in diagnosing COVID-19 from X-rays and CT scans. However, some authors argue that existing DL methods, based on CNN, are being challenged by newer DL architectures and models. Motivated by this, in this study, we propose the use of the Swin Transformer (instead of CNN) for COVID-19 screening using X-ray images from four original datasets: COVID-QU-Ext Dataset, SARS-COV2-CT Dataset, HUST-19, and HCV-UFPR-COVID-19. These datasets were merged using different strategies, resulting in a total of 9 distinct datasets. We employed transfer learning to address the issue of data scarcity. Moreover, we assessed whether the models have a high generalization capability, based on the learned features, allowing training on one dataset, and testing on another, aiming to evaluate if there are significant losses in the metric values obtained. Upon analyzing the cumulative results from experiments across all datasets and strategies, the Swin Transformer stands out. In terms of sensitivity\/recall, it performed 107% and 80% better than ViT and CNN, respectively. In the HUST-19 dataset, the Swin Transformer achieved the maximum score (1 or 100%) for all metrics and continued to show notable performance in other datasets. Compared to the state of the art, the results reveal a promising and highly competitive performance for the Swin Transformer. Additionally, statistical tests were conducted which showed, in several instances, that there are statistically significant differences in the metrics obtained by the Swin Transformer when compared to CNN and ViT.",
            "source_url": "https:\/\/openalex.org\/W7120831202",
            "pdf_url": "http:\/\/repositorio.utfpr.edu.br:8080\/jspui\/bitstream\/1\/32649\/1\/swintransformerimagensradiograficas.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)",
            "source_record_id": "W7120831202",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 733,
            "title": "Performance Enhancement of Convolution Neural Network for COVID-19 Classification",
            "title_ar": "",
            "title_en": "Performance Enhancement of Convolution Neural Network for COVID-19 Classification",
            "author": "Bikash Ghimirey ; Roshan Chitrakar",
            "supervisor": "",
            "degree_type": "master",
            "degree_evidence": "نص السجل: «Master»",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; image-classification; medical-imaging",
            "keywords": "",
            "abstract": "This Master’s thesis investigates a deep learning–based approach for accurate detection of COVID-19 from chest X-ray (CXR) images using Convolutional Neural Networks (CNNs). Accurate and timely identification of COVID-19 cases from radiographic images is essential for effective clinical decision-making, particularly in situations where laboratory testing resources are limited. The study focuses on improving CNN performance through systematic hyperparameter optimization and transfer learning techniques. A VGG16 architecture pretrained on ImageNet was used as the base model, enabling effective feature extraction from medical images while reducing training complexity. A large-scale dataset of approximately 15,000 chest X-ray images was utilized. Comprehensive preprocessing steps including normalization, resizing, and data augmentation were applied to improve model robustness and generalization. Key hyperparameters — including batch size, learning rate, dropout rate, and dataset size — were systematically tuned through extensive experimentation. Model performance was evaluated using standard classification metrics such as accuracy, precision, recall (sensitivity), F1-score, ROC-AUC, and confusion matrices. The models were implemented using Python with TensorFlow\/Keras and trained on Google Colaboratory to leverage high-performance computational resources. The optimized VGG16 model achieved a classification accuracy of 98.5% and sensitivity of 97.8%, significantly reducing false negatives — a critical factor in medical diagnosis. Experimental results demonstrate that appropriate hyperparameter selection, particularly a learning rate of 0.001 and batch size of 64, provides the best balance between performance and stability. This research confirms that systematic hyperparameter tuning can substantially enhance CNN performance for medical image classification and supports the development of reliable AI-assisted diagnostic systems for real-time COVID-19 screening. The methodology can be extended to other medical imaging applications and disease detection tasks.",
            "source_url": "https:\/\/openalex.org\/W7131246595",
            "pdf_url": "",
            "doi": "10.5281\/zenodo.18758362",
            "handle": "",
            "repository_name": "Zenodo (CERN European Organization for Nuclear Research)",
            "source_record_id": "W7131246595",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 735,
            "title": "Adaptive Deep Learning for Vision and Multimodal Understanding with Heterogeneous Data",
            "title_ar": "",
            "title_en": "Adaptive Deep Learning for Vision and Multimodal Understanding with Heterogeneous Data",
            "author": "Youwei Liang",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; medical-ai; transfer-learning; few-zero-shot; predictive-analytics; transformers; multimodal; image-segmentation; llm",
            "keywords": "",
            "abstract": "Large-scale pretraining has produced powerful deep learning representations, but real-world data rarely match the clean, uniform assumptions of standard transfer learning. This dissertation uses heterogeneous data to describe settings in which information differs in modality, representation, relevance, quality, or frequency across inputs, outputs, tasks, or supervision. Examples include molecules represented as graphs, images, strings, and text; images containing both informative and redundant regions; noisy or incomplete labels; and rare but important classes. Applying pretrained models in these settings requires deciding which information to process, how to connect different forms of information, and how much to trust each supervision signal. This dissertation develops adaptive learning as a unifying approach through three paradigms: adaptive selection focuses computation on useful input components; adaptive alignment maps heterogeneous modalities, tasks, and outputs into a shared predictive space; and adaptive supervision adjusts imperfect or imbalanced training signals. The first contribution, EViT, demonstrates adaptive selection for efficient Vision Transformers. Standard Vision Transformers devote equal computation to all image patches despite substantial redundancy. EViT uses class-token attention to identify important tokens, preserves them in subsequent layers, and fuses inattentive tokens into a compact representation rather than discarding their context. This progressive token reorganization reduces computation while maintaining accurate visual recognition. The second contribution, DrugChat, demonstrates adaptive alignment for multimodal molecular prediction. Molecules can be represented as chemical graphs, rendered images, SMILES strings, and natural-language prompts, while predictions may require labels, probabilities, categorical decisions, or free-form descriptions. DrugChat encodes molecular graphs and images with pretrained encoders, projects them into the latent space of an instruction-following language model, and conditions generation on molecular structure and task prompts. It thereby aligns heterogeneous inputs in a shared representation space and expresses diverse prediction targets through a common language-generation interface. The third contribution, RobPicker, demonstrates adaptive supervision for cryo-electron tomography particle picking, where annotations are expensive, incomplete, noisy, and highly imbalanced across macromolecular species. Its meta-learning framework jointly trains a segmentation network, a label correction network, and a data reweighting network. Guided by cleaner validation data, these components refine imperfect labels and adapt each subtomogram's contribution to the loss, giving greater influence to rare or small particle classes. Together, EViT, DrugChat, and RobPicker apply adaptation at complementary levels of the learning pipeline: selecting what data to process, aligning heterogeneous representations and outputs, and learning from imperfect supervision.",
            "source_url": "https:\/\/openalex.org\/W7222391945",
            "pdf_url": "https:\/\/escholarship.org\/content\/qt3h17286t\/qt3h17286t.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "eScholarship (California Digital Library)",
            "source_record_id": "W7222391945",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:52",
            "updated_at": "2026-11-15 16:52:52"
        },
        {
            "id": 786,
            "title": "Federated transfer learning in smart homes pattern recognition for privacy preservation",
            "title_ar": "",
            "title_en": "Federated transfer learning in smart homes pattern recognition for privacy preservation",
            "author": "Su Shun Lei May",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "LUT University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Finland",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "rnn",
            "categories": "machine-learning; deep-learning; responsible-ai; transfer-learning; rnn; fairness",
            "keywords": "",
            "abstract": "Smart homes collect continuous sensor data about how people live, including when they sleep, cook, work, and move around the house. Training AI models on this data has traditionally required sending it to a central server, which creates serious privacy risks and conflicts with laws like the General Data Protection Regulation. This thesis builds and tests a Federated Transfer Learning framework that trains a shared AI model across ten smart homes without any raw data ever leaving the local device. The system uses a two-layer Long Short-Term Memory network trained through the Federated Averaging algorithm across ten distinct household types. The model is split into two parts. The shared body learns general activity patterns from all ten homes and is the only part transmitted between clients and the server. The private head stays on each device throughout all 60 rounds of training, is never transmitted to the server, and adapts privately to each household's specific activity distribution. Testing showed that eight of ten clients' private heads achieved 100.00% macro F1 on their own local validation data, Client 4 achieved 99.63%, and Client 10 achieved 99.67%, confirming that private head training across 60 rounds produces strong household-specific classification without any head information leaving the local device. On a shared test set evaluated as the average across all ten client models, the FTL-LSTM framework achieved 90.86% macro F1. This lower figure reflects the combined effect of head privacy and household specialization: nine of the ten private heads were trained on households other than the test home. Standard FedAvg, which transmits full model weights including head parameters every round across the same 60 rounds, achieved 99.61% on the same shared test set using a single globally averaged head. The 3.7% communication saving from body-only transmission was confirmed with FTL-LSTM transmitting 575.39 MB compared to 597.41 MB for standard FedAvg over identical 60-round durations. In the cold start scenario evaluated on 865 windows from Home 11, the pretrained body provided a transfer advantage in all four labeled sample conditions: +9.80 percentage points at 10 samples, +8.33 at 20 samples, +12.18 at 50 samples, and +8.31 at 100 samples, with peak FTL performance of 52.29% at 100 samples. These results show that body only head private federation produces near perfect local performance for each household while carrying a measurable difference on shared external test evaluations, a difference that reflects both head privacy and household specialization rather than privacy cost alone.",
            "source_url": "https:\/\/openalex.org\/W7203565195",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "LUTPub (LUT University)",
            "source_record_id": "W7203565195",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 836,
            "title": "Deep Learning in Medical Image Analysis: Alzheimer’s Disease Classification & Whole Fetal Brain Segmentation.",
            "title_ar": "",
            "title_en": "Deep Learning in Medical Image Analysis: Alzheimer’s Disease Classification & Whole Fetal Brain Segmentation.",
            "author": "Jesús Alejandro Valdés Valdés",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Tecnológico de Monterrey",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Mexico",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; generative-ai; medical-ai; transfer-learning; cnn; image-segmentation; gan; medical-imaging",
            "keywords": "",
            "abstract": "During the last couple years there has been a growing interest in Deep Learning (DL), thanks in part to an increasing availability of computational power and of massive labeled datasets. This work presents two different Deep Learning applications for medical image analysis related tasks. The first application is the classification of Alzheimer Disease (AD) using MRI. AD is the most common form of dementia. However, it’s difficult to diagnose. During this work three different DL models are proposed to classify subjects into either AD or Normal Control (NC) groups. The models proposed are a custom CNN model, vgg16 + Transfer Learning and vgg16 + Fine Tuning. The vgg16 based methods make use of pre-learned weights trained on the ImageNet dataset. All of the models used as an input a single 2D MRI slice. This helped reduced model complexity and training times. After performing a 10 times repeated 5-Fold cross validation it was discovered that the best model was vgg16 with Fine Tuning. It reached an accuracy of 80% and an AUC of 0.86. The obtained results proved that the use of weights learned from different domains could be useful in medical image applications. The main contributions of this section were the use of a single MRI slice to classify patients, the model validation technique and the use of transfer learning. The second application is the fully automatization of the Whole Fetal Brain Segmentation in maternal MRI scans. For this U-Net [41] and other segmentation networks were compared. The U-Net model was also modified to include two types of attention components. Squeeze and Excitation module [16] and Attention Gates [39]. To avoid overfitting the models were trained using rigorous regularization (channel wise dropout, weight decay and data augmentation). They were also trained using different loss functions, including a Hybrid (BCE+Dice) loss function. The results of the 10-fold cross validation experiments showed statistically that no model was able to outperform the vanilla U-Net (DSC of 0.93 and HD 7.59mm). The proposed Attention Gated U-Net trained with the Hybrid loss reached a 0.95 DSC and 5.03mm HD (no significant difference). However, results on challenging data show a better performance for the Attention Gated models. This led to the conclusion that the possible advantage of using attention gates outweighed the cost of adding the attention module. The results were also improved by the use of a post processing step based on traditional computer vision techniques. The main contributions to this problem were the use of 10-fold cross validation, the statistical comparison between models, the use of the Hausdorff distance metric, the post processing step and the addition of attention components. This work also provides an overview of other deep learning applications also used within a medical setting. The techniques mentioned include image labeling, autoencoders and GANs for data augmentation. It also provides an overview of the current challenges and limitations DL faces and the most common way of mitigating them. Thanks to the research conducted during this thesis it can be concluded that the use of DL can be used in a medical setting focused on the analysis of images. Particularly on classification and segmentation tasks. However, certain challenges such as having a large enough data set and availability of the required hardware to carry out research must be considered before attempting to solve a problem with DL.",
            "source_url": "https:\/\/openalex.org\/W3014475976",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Repositorio del Tecnológico de Monterrey (Tecnológico de Monterrey)",
            "source_record_id": "W3014475976",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 851,
            "title": "Deep Learning for Pneumothorax Segmentation and Quantification",
            "title_ar": "",
            "title_en": "Deep Learning for Pneumothorax Segmentation and Quantification",
            "author": "Wannipa Sae-Lim",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Prince of Songkla University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Thailand",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; predictive-analytics; cnn; transformers; image-segmentation; medical-imaging",
            "keywords": "",
            "abstract": "This thesis investigates the role of deep learning, focusing on convolutional neural networks and encoder-decoder architectures, to enhance medical image segmentation, specifically for pneumothorax identification in chest X-ray images. Pneumothorax, a critical condition characterized by lung collapse, requires precise diagnostics for effective management and treatment. Traditional image segmentation methods sometimes underperform due to the complexity and variability of chest X-ray images. In this study, we proposed PTXSeg-Net, a novel deep learning model for accurate and efficient pneumothorax segmentation. This model incorporates residual blocks and attention mechanisms to improve learning capabilities and is further enhanced by deep supervision, which allows for more effective gradient utilization across all network layers, significantly enhancing its performance over existing segmentation methods. Additionally, transfer learning with pre-trained models on extensive chest X-ray datasets improves feature extraction, addressing imbalanced datasets. Data refinement techniques are also employed to optimize the training outcomes. The performance of PTXSeg-Net outperforms the existing segmentation model in terms of accuracy, dice and Jaccard coefficients, demonstrating significant improvement in the field of pneumothorax segmentation. Moreover, leveraging the predicted masks of pneumothorax, this thesis proposes an algorithm that calculates the pneumothorax ratio. This algorithm provides a quantitative measure of the appearance of pneumothorax relative to the total lung area, offering a metric for radiologists to assess the severity of the condition more accurately. This integration of deep learning models and practical quantification algorithm underscores the significant contribution to the field of medical image analysis.",
            "source_url": "https:\/\/openalex.org\/W7201935903",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "PSU Knowledge Bank (Prince of Songkla University)",
            "source_record_id": "W7201935903",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 873,
            "title": "Variational methods and deep learning for semantic image segmentation",
            "title_ar": "",
            "title_en": "",
            "author": "Miguel Chicchón",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Pontifical Catholic University of Peru",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Peru",
            "governorate": "",
            "publication_year": 2025,
            "language": "es",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; transfer-learning; transformers; image-segmentation",
            "keywords": "",
            "abstract": "Actualmente, las aplicaciones de visión por computadora, que incluyen la conducción autónoma, la detección de fallas, la imagenología médica y la teledetección, son cada vez más frecuentes y necesitan mecanismos de segmentación o clasificación de píxeles más precisos. Recientemente, las técnicas de aprendizaje profundo que utilizan redes neuronales se han convertido en la estrategia dominante para resolver diversos problemas en visión por computadora; sin embargo, existen limitaciones y problemas aún por resolver. Es por ello que una integración adecuada con técnicas tradicionales, como los métodos variacionales, con sus propias ventajas y limitaciones, resulta de interés para mejorar la precisión y robustez de la segmentación semántica. Esta tesis se centra en la implementación y validación de algoritmos de segmentación de imágenes que combinan métodos variacionales y aprendizaje profundo en cuatro escenarios diferentes. En el primer escenario, que implica la segmentación de peces en entornos subacuáticos, se compararon métodos variacionales integrados utilizando enfoques de post-procesamiento, extremo a extremo (end-to-end) y una función de pérdida combinada. En el segundo escenario, que aborda la segmentación de baches y grietas en pavimentos de carreteras, se entrenaron tres arquitecturas de redes neuronales SOTA (del estado del arte) utilizando una función de pérdida de entropía cruzada combinada y contornos activos. En el tercer escenario, enfocado en la segmentación de techos de edificios en imágenes satelitales, se entrenó una red neuronal U-Net con diferentes redes SOTA en la ruta del codificador (encoder path) mediante aprendizaje por transferencia (transfer learning), y el mejor modelo fue seleccionado para ser entrenado utilizando una función combinada con pérdida de entropía cruzada y pérdida de contornos activos. Finalmente, en el cuarto escenario, que se refiere a la segmentación de cobertura terrestre en imágenes aéreas, se emplearon aprendizaje por transferencia y la función de contornos activos en el entrenamiento de redes neuronales convolucionales y transformadores (transformers). Los resultados cuantitativos consolidados demuestran mejoras significativas: la función de pérdida combinada logró aumentos promedio de4-6% en el mIoU (mean Intersection over Union) en comparación con los enfoques que solo utilizaban entropía cruzada o Dice. Específicamente, para la segmentación de peces, el modelo U-Net-scSE con un codificador ResNeSt-269e alcanzó 73.1% de mIoU; para la detección de baches, 87.45% de mIoU con una reducción de HD95 a 23.40 mm; para la segmentación de techos, se logró una mejora del 14% en IoU utilizando aprendizaje por transferencia; y para la cobertura terrestre, el modelo U-Net-scSE con un codificador MiT- B4 obtuvo 80.4% de mIoU. Estas validaciones a través de cuatro dominios heterogéneos demuestran que la integración sistemática de métodos variacionales en redes profundas proporciona mejoras cuantificables y transferibles en la exactitud de la segmentación.",
            "source_url": "https:\/\/openalex.org\/W7138825433",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Communities in DSpace (Pontifical Catholic University of Peru)",
            "source_record_id": "W7138825433",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 894,
            "title": "Multidimensional Transfer Learning in Natural Language Processing: Domain, Task, Language, and Expertise Adaptation",
            "title_ar": "",
            "title_en": "Multidimensional Transfer Learning in Natural Language Processing: Domain, Task, Language, and Expertise Adaptation",
            "author": "Nghia Ngo",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Oregon",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; nlp; medical-ai; transfer-learning; predictive-analytics; llm",
            "keywords": "",
            "abstract": "Transfer learning in Natural Language Processing (NLP) mirrors a fundamental human cognitive ability: applying prior knowledge to learn new skills efficiently. Rather than training models from scratch for every new task, domain, or language, transfer learning enables systems to use knowledge from previous learning experiences. This capability is essential for addressing two critical challenges in modern NLP: the scarcity of labeled data affecting the vast majority of the world’s languages and specialized domains, and the prohibitive computational cost of training large-scale models from scratch. This dissertation presents a comprehensive investigation of transfer learning in NLP, organized around two distinct phases. The first phase, Adaptive Transfer Learning, addresses horizontal knowledge transfer across contexts through three research directions: unsupervised domain adaptation, where models must transfer across data distributions without target labels; task adaptation for structured prediction, where multiple interdependent tasks such as joint information extraction must be learned and transferred simultaneously across domains; and cross-lingual transfer, where knowledge from high-resource languages is shared to low-resource languages across typologically diverse language families. The second phase, Specialization Transfer Learning, addresses the emerging challenge of vertically refining general-purpose large language models for reliable deployment in high-stakes expert domains. This phase focuses on developing comprehensive evaluation frameworks for Retrieval-Augmented Generation systems in the medical domain, assessing critical dimensions beyond standard accuracy such as knowledge sufficiency, multi-document integration, and robustness to noisy or misleading retrieved content. Together, these contributions advance the understanding of how NLP models can be systematically transferred and specialized across domains, tasks, languages, and levels of expertise, spanning the full spectrum from data-limited to data-engineered paradigms. This dissertation includes both previously published and co-authored material.",
            "source_url": "https:\/\/openalex.org\/W7165425966",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Scholars' Bank (University of Oregon)",
            "source_record_id": "W7165425966",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 895,
            "title": "A Comprehensive Framework for Targeted Transfer Learning: Privacy-Preserving, Secure, and Efficient Domain Adaptation",
            "title_ar": "",
            "title_en": "A Comprehensive Framework for Targeted Transfer Learning: Privacy-Preserving, Secure, and Efficient Domain Adaptation",
            "author": "Sayyed Farid Ahamed",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Old Dominion University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "image-classification",
            "categories": "machine-learning; computer-vision; responsible-ai; ai-applications; transfer-learning; few-zero-shot; image-classification; federated-learning; fairness; ai-cybersecurity; ai-smart-cities",
            "keywords": "",
            "abstract": "Machine learning models deployed in tactical environments rely on high-quality labeled datasets, which are often challenging, expensive, and time-consuming to obtain. In addition, formal techniques for assuring model performance under dynamic conditions remain limited. Transfer learning has emerged as a promising solution, but its effectiveness is limited by domain coverage and similarity between source and target datasets. This dissertation presents a comprehensive, modelagnostic Targeted Transfer Learning (TTL) framework that addresses transferability challenges between domains with minimal data, demonstrating how targeted sample selection improves adaptation across image classification, network security, and privacy-preserving collaborative settings. First, we develop the TTL framework for scenarios where direct access to datasets is restricted. This metadata-driven approach applies to a combinatorial coverage method to estimate domain correlation and guide sample selection. Evaluation on a satellite imagery dataset showed that targeted selection outperformed zero-shot transfer and random selection while conserving computational resources. Second, we investigate the TTL framework in settings where both datasets are directly available. This data-driven approach uses optimal transport distance to quantify distributional differences and guide selection of informative target samples. Validation across a broad set of benchmark image classification datasets demonstrated consistent improvements over conventional transfer learning. Third, we address network malware classification through Selective Targeted Transfer Learning (STTL), projecting source and target traffic data into a shared latent feature space and selecting relevant samples using a Kullback–Leibler divergence-based similarity measure. Experimental results across multiple attack-family scenarios showed that STTL achieved higher performance than conventional transfer learning, confirming that targeted selection generalizes across data types and domains. Finally, we extend the TTL framework through two decentralized privacy-preserving mechanisms. In a federated learning setting, clients share only summary statistics, and a server computes aggregation weights that enable knowledge transfer without exposing local data. In a blockchain-based setting, cryptographic verification secures model weights throughout the transfer process, while a smart-contract mechanism rewards high-quality participation. Both mechanisms consistently outperformed non-targeted baselines while preserving data confidentiality and integrity. This research establishes targeted transfer learning as a practical framework that enables machine learning models to adapt reliably, securely, and efficiently across image classification, network security, and distributed collaborative environments.",
            "source_url": "https:\/\/openalex.org\/W7225739907",
            "pdf_url": "https:\/\/digitalcommons.odu.edu\/context\/ece_etds\/article\/1622\/viewcontent\/_Sayyed__PhD_Dissertation.pdf",
            "doi": "10.25777\/e3fd-gd70",
            "handle": "",
            "repository_name": "ODU Digital Commons (Old Dominion University)",
            "source_record_id": "W7225739907",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 896,
            "title": "Domain-Specific Adaptation of General-Purpose Embeddings for Email Similarity Detection: A Transfer Learning Approach",
            "title_ar": "",
            "title_en": "",
            "author": "Michal Bělohlávek",
            "supervisor": "",
            "degree_type": "master",
            "degree_evidence": "نص السجل: «Diplomová práce»",
            "university": "Czech Technical University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Czech Republic",
            "governorate": "",
            "publication_year": 2026,
            "language": "cs",
            "research_domain": "machine-learning",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; transfer-learning",
            "keywords": "",
            "abstract": "Diplomová práce zkoumá dodatečnou adaptaci detektoru e-mailů postaveného na fixním encoderu vět a klasifikaci podle nejbližších sousedů v referenční databázi. Možné modifikace se dělí na úpravy reprezentace a úpravy rozhodovacího pravidla a posuzují se ve třech rodinách metod: geometrické transformace embeddingů, využití metadat zpráv a komprese referenční databáze. Smysluplná adaptace je dosažitelná jen výběrově -- klíčové je místo zásahu, nikoli složitost zvolené metody. Z transformací reprezentace vychází nejlépe centrování, metadata jsou užitečná především v rozhodovacím pravidle a výraznou kompresi databáze lze provést teprve po geometrické stabilizaci reprezentace. Práce přispívá rozkladem dodatečné adaptace na transformační a rozhodovací složku, použitelným v jakémkoli vyhledávacím systému s neměnným encoderem, a návodem ukazujícím, kde jednotlivé modifikace pomáhají a kde nikoli.",
            "source_url": "https:\/\/openalex.org\/W7200525814",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Cvut DSpace (Czech Technical University)",
            "source_record_id": "W7200525814",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 897,
            "title": "Transfer learning for language model adaptation",
            "title_ar": "",
            "title_en": "Transfer learning for language model adaptation",
            "author": "Bari M. Saiful",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Nanyang Technological University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Singapore",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; transfer-learning; self-semi-supervised; predictive-analytics; llm; sentiment-analysis; machine-translation",
            "keywords": "",
            "abstract": "Language is the pathway to democratize the boundary of land and culture. Bridging the gap between languages is one of the biggest challenges of Artificial Intelligent (AI) systems. The current success of AI systems is dominated by the supervised learning paradigm where gradient-based learning algorithms (i.e., SGD, Adam) are designed to optimize complex high-dimensional planes. These algorithms learn from statistical observations that are typically collected with the intention of a specific task (i.e., product review, sentiment analysis). The use of task-dependent samples makes the learning procedure tedious as it requires manually annotated data. On the contrary, without having a sufficient amount of samples to represent the distribution, deep learning models tend to suffer from the lack of robustness. Due to the natural puzzle of randomness, not all sets of observations are observed in the data collection procedure, thus creating Out-of-Distribution (OOD) problem in learning algorithms. In the search of a generic task agnostic distribution, a large collection of text over various domains can be considered as - Standard Natural Text Distribution (SNTD). The generic idea of Transfer Learning for Natural Language Processing (NLP) is to utilize the SNTD knowledge for any other task-dependent training. Learning SNTD, followed by a task-adaptation method with a smaller volume of annotated data has yielded state-of-the-art (SOTA) results in various supervised NLP tasks. However, annotated data for every task in every language is rare. In language models, there are many kinds of distributional variance. One of the most common ways that distributional variance is encoded into a language model is when it is trained with mono-lingual text and learned dis-jointly. Word embeddings produced from these language models are then used as pre-trained embedding vectors to adapt to a downstream task. We propose adversarial training to project two monolingual distributions into the same space and then improve the robustness of the model by augmented fine-tuning with parameter sharing. By projecting mono-lingual language distribution into the same cross-lingual space, the distribution of the language become aware of each other. These projected distribution are semantically aware of each other in the latent space. Thus when we train one distribution the other distribution automatically adapt to the training data, making it easier to transfer (exchange) knowledge. On top of that, the proposed novel self-training architecture improves cross-lingual transfer by a large margin. Then, we focus on the jointly trained multi-lingual language model, where there is no pre-dominant distributional variance. In the multi-lingual language model, we put more focus on downstream task adaptation. We found that semi-supervised learning with pseudo-augmented data from a pre-trained language model can greatly improve the performance of tasks further down the line. In the end, we introduce a new novel data augmentation framework that uses the neighboring (vicinal) samples of the original training data without explicitly using any parallel text corpora or machine translation system. Our proposed method performs simultaneous self-training with data augmentation and unsupervised sample selection. It also proposes curriculum strategies for different domain samples. With extensive experiments on three different cross-lingual tasks spanning many language pairs, we have demonstrated the effectiveness of our proposed method. While all of the work done above focused on improving task adaptation in multiple languages without supervision, we further investigate how adding a few samples affects multi-lingual task adaptation. To this end, we leverage a small number of support samples from each language and propose an inference-time transductive nearest neighbor-based approach which utilizes the entropy of the query samples for predictions. We show that our proposed method outperforms full model\/full head fine-tuning as well as cross-task fine-tuning. We also show impressive performance gain (~37x) in computational costs for the full inference prediction. However, as the language models grow bigger, it becomes increasingly difficult to perform efficient inferences, especially for multiple tasks. The jointly optimized multi-lingual distribution helps transfer knowledge from a high-resource language to a low-resource language. While working on transductive nearest neighbor inference, we observe that language models are significantly prone to task distributions. Unless we use an extremely large language model (>100B), a model used for a specific task adaptation cannot be used for another task. In this dissertation, our final proposed method addresses this issue by multitask prompted learning.",
            "source_url": "https:\/\/openalex.org\/W4386409617",
            "pdf_url": "https:\/\/dr.ntu.edu.sg\/bitstream\/10356\/169892\/2\/sbmaruf_thesis.pdf",
            "doi": "10.32657\/10356\/169892",
            "handle": "",
            "repository_name": "DR-NTU (Nanyang Technological University)",
            "source_record_id": "W4386409617",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 899,
            "title": "Deep Learning Domain Adaptation in Brain MRI: Investigating Motion Mitigation in Adult and Neonatal Scans",
            "title_ar": "",
            "title_en": "Deep Learning Domain Adaptation in Brain MRI: Investigating Motion Mitigation in Adult and Neonatal Scans",
            "author": "Saad Bin Ashraf",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; image-segmentation; medical-imaging",
            "keywords": "",
            "abstract": "Magnetic Resonance Imaging (MRI) is a vital non-invasive tool for high-resolution brain imaging, yet its long acquisition time frequently results in patient movement leading to motion artifacts, particularly among non-compliant patients like newborns. While Deep Learning (DL) models have emerged as powerful retrospective solutions for motion mitigation, their performance is expected to degrade when applied to data from different scanners, protocols, or patient populations. This thesis investigates the generalizability of DL-based motion correction across heterogeneous adult and neonatal brain MRI domains. The research is conducted through three primary aims. First, the study evaluates the domain generalization of a 3D U-Net model across multi-center adult datasets - IXI, Calgary-Campinas, and OASIS-3, comprising 11 imaging centers with diverse scanner vendors and field strengths. Results indicate that models generalize effectively to unseen adult datasets from various centers, while superior performance is achieved when training incorporates broader intensity distributions. Second, the thesis explores cross-domain transfer learning by applying adult-trained models to the neonatal domain, utilizing the dHCP dataset, which contains real motion from neonatal subjects. Results indicate that adult-pretrained models learn domain-agnostic structural priors, allowing them to reconstruct neonatal brain anatomy despite significant shifts in contrast, size, and motion characteristics. Crucially, fine-tuning with as few as three neonatal scans was shown to substantially improve the mitigation of neonatal-specific artifacts, demonstrating an efficient adaptation strategy for data-scarce domains. Third, the study critically assesses the reliability of common image quality metrics (IQMs). The analysis reveals that traditional metrics are often insensitive to subtle motion and can even yield paradoxical results, where motion-corrupted images appear higher in quality than corrected ones. Overall, this work highlights the potential for deploying robust motion-mitigation frameworks in diverse clinical settings. By leveraging transfer learning, this thesis provides a foundation for more reliable and scalable deep learning–based motion correction in pediatric and adult neuroimaging.",
            "source_url": "https:\/\/openalex.org\/W7140225405",
            "pdf_url": "",
            "doi": "10.11575\/prism\/51192",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W7140225405",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 901,
            "title": "Study of transfer learning and domain adaptation for language modeling in end-to-end speech recognition",
            "title_ar": "",
            "title_en": "Study of transfer learning and domain adaptation for language modeling in end-to-end speech recognition",
            "author": "卓 龔",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Japan",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; nlp; transfer-learning; llm; speech-recognition",
            "keywords": "",
            "abstract": "Automatic Speech Recognition (ASR) has become a technical foundation for a natural human-machine interface: speech input.Recently, there have been various daily applications based on ASR: 1) transcription in dictation as smartphone input method, in automatically generated subtitles, as upstream task of speech translation (ST); 2) speech command recognition in a personal assistant like Siri, Alex, Cortana or intent recognition: booking flight, etc; and 3) QA systems like auto attendant phone systems.Deep neural network-based end-to-end (E2E) ASR systems have gained popularity in recent years due to the fast development of deep learning technologies since they can leverage gigantic speech training data with high performance and high efficiency which outperformed human for domains with sufficient data.For conventional ASR systems, independent modules can be trained on audio signals and textual sequences which gives the ASR system the capability to easily be adapted to different scenarios by only changing one of those modules.Compared to conventional ASR systems, E2E ASR systems usually have a single indivisible module for transforming speech to text.If adaptation is necessary, sufficient data from target domain should be prepared or an external language model can be integrated into the system.However, labeled speech data can always be insufficient for a specific domain while text data are much more easily obtained from web pages, books, journals, etc.Because of these reasons, Language models (LM) have been essential in enhancing the performance of end-to-end (E2E) automatic speech recognition (ASR) systems.There are two dimensions of LM integrations: 1) space dimension, how deep LM should be integrated into an E2E ASR model (combining outputs or neural networks); 2) time dimension, when to integrate LM (training stage; decoding stage; or both).This thesis starts from introducing crucial methodologies for modern E2E, then present several contributions considering above dimensions.",
            "source_url": "https:\/\/openalex.org\/W7144031295",
            "pdf_url": "https:\/\/repository.dl.itc.u-tokyo.ac.jp\/record\/2011417\/files\/A40245.pdf",
            "doi": "10.15083\/0002011417",
            "handle": "",
            "repository_name": "Institutional Repositories DataBase (IRDB)",
            "source_record_id": "W7144031295",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 902,
            "title": "Enhancing Domain-Specific Automated Audio Captioning: A Study on Adaptation Techniques and Transfer Learning",
            "title_ar": "",
            "title_en": "Enhancing Domain-Specific Automated Audio Captioning: A Study on Adaptation Techniques and Transfer Learning",
            "author": "Charith Raghavaraju",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Tampere University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Finland",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; nlp; transfer-learning; transformers; speech-recognition",
            "keywords": "",
            "abstract": "Automated audio captioning is a challenging cross-modal task that takes an audio sample as input to analyze it and generate its caption in natural language as output.The existing datasets for audio captioning such as AudioCaps and Clotho encompass a diverse range of domains, with current proposed systems primarily focusing on generic audio captioning.This thesis delves into the adaptation of generic audio captioning systems to domain-specific contexts, simultaneously aiming to enhance generic audio captioning performance.The adaptation of the generic models to specific domains has been explored using two different techniques: complete fine-tuning of neural model layers and layer-wise fine-tuning within transformers.The process involves initial training with a generic captioning setup, followed by adaptation using domain-specific training data.In generic captioning, the process for training starts with training the model on the Audio-Caps dataset followed by fine-tuning it using the Clotho dataset.This is accomplished through the utilization of a transformer-based architecture, which integrates a patchout fast spectrogram transformer (PaSST) for audio embeddings and a BART transformer.Word embeddings are generated using a byte-pair encoding (BPE) tokenizer tailored to the training datasets' unique words, aligning the vocabulary with the generic captioning task.Experimental adaptation mainly focuses on audio clips related to animals and vehicles.The results demonstrate notable improvements in the performance of the generic and domain adaptation systems.Generic captioning has demonstrated an improvement in SPIDEr scores, increasing from 0.291 during fine-tuning to 0.301 with layer-wise fine-tuning.Specifically, we observed a notable increase in SPIDEr scores, from 0.315 to 0.323 for animal-related audio clips and from 0.298 to 0.308 for vehicle-related audio clips.",
            "source_url": "https:\/\/openalex.org\/W7133068187",
            "pdf_url": "https:\/\/trepo.tuni.fi\/bitstream\/10024\/153190\/2\/RaghavarajuCharitha.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Tampere University Institutional Repository (Tampere University)",
            "source_record_id": "W7133068187",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 903,
            "title": "Towards transfer learning in e-discovery :finding the optimal classifier and evaluating domain adaptation methods",
            "title_ar": "",
            "title_en": "Towards transfer learning in e-discovery :finding the optimal classifier and evaluating domain adaptation methods",
            "author": "J.L. Pebesma",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "responsible-ai",
            "research_subdomain": "xai",
            "categories": "machine-learning; responsible-ai; ai-applications; transfer-learning; xai; ai-cybersecurity",
            "keywords": "",
            "abstract": "Once fraud is suspected, an e-discovery process can be started. Currently, this process starts with the scoping the case, whereby filters and search terms are identified to limit the search results. These results are then manually reviewed on their relevance to the case, which is expensive due to the number of hours people needed for review. Machine learning has shown potential for this task, whereby both the content and metadata of communication seem to help the classification. However, not much research has been done on the use of machine learning in e-discovery. Ideally, a classification model is trained, in a way that requires no further input, except the emails themselves. Apart from limited available research into the most optimal machine learning model, there are two other major limitations to the use of machine learning in e-discovery. One is that the datasets are relatively small, thus some patterns may not be picked up on. Knowledge about finding relevant documents may be transferred between different fraud cases. By using the knowledge learnt from each case and applying transfer learning, the knowledge can be strengthened and findings can be solidified. Another limitation is that the machine learning model may act as a black box, which is inconvenient for tasks that focus on creating transparency, such as fraud investigations. This limitation is further discussed and possible solutions are considered, such as the implications of using XAI in e-discovery. This aim of this thesis is to optimise a classification model and create more insight into the transferability between cases while considering the implications of applying explainable AI in the legal domain.",
            "source_url": "https:\/\/openalex.org\/W3107203640",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W3107203640",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 906,
            "title": "Transfer Learning for Cross-domain Visual Recognition",
            "title_ar": "",
            "title_en": "Transfer Learning for Cross-domain Visual Recognition",
            "author": "Jing Zhang",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Wollongong",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Australia",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; computer-vision; transfer-learning",
            "keywords": "",
            "abstract": "Machine learning algorithms usually require a huge amount of training examples to learn a new model from scratch and often fail to apply the learned model to test data acquired from the scenarios different from those of the training data mainly due to domain divergence and task divergence. Transfer learning tries to use previously available data, models or knowledge effectively for a new domain or task with scarce data. This thesis focuses on addressing the cross-domain visual recognition using transfer learning. First, a comprehensive literature review of transfer learning methods for cross-dataset visual recognition is presented by taking a problem-oriented perspective. Second, though there has been extensive research on unsupervised domain adaptation, the performance on the target domain is still far from comparable to that without distribution shift. Hence, a novel feature transformation-based method on unsupervised domain adaptation is proposed by taking both geometrical and statistical shift into consideration, and the performance is improved compared to previous methods. Third, a novel classifier-based unsupervised domain adaptation method is proposed by presenting a new perspective that the unsupervised domain adaptation can be formulated as a multi-task learning problem. This formulation removes the commonly used shared classifier assumption in previous methods and proposes unshared classifiers for the source and target domains for exploiting more domain specific features. Fourth, an important weighted adversarial nets-based method for partial domain adaptation is proposed, where the target domain has less number of classes compared to the source domain. Different from previous domain adaptation methods that generally assume the identical label spaces, a more realistic scenario that requires adaptation from a larger and more diverse source domain to a smaller target domain with less number of classes is considered. Last, a new research topic called multi-source domain expansion (MSDE) is introduced, which expands the source domains to include the new domain, such that the learned model is capable to perform well on both the new target domain and the old source domains. The MSDE is different from traditional domain adaptation whose target domain is defined only as the new domain excluding the source domains. MSDE is also different from multi-task learning, lifelong Learning, and incremental learning all of which assume no domain shift among different tasks. Specifically, a novel method is proposed for unsupervised MSDE without source data.",
            "source_url": "https:\/\/openalex.org\/W2950193837",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Research Online (University of Wollongong)",
            "source_record_id": "W2950193837",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 908,
            "title": "Domain adaptive learning with disentangled features",
            "title_ar": "",
            "title_en": "Domain adaptive learning with disentangled features",
            "author": "Xingchao Peng",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Boston University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; deep-learning; computer-vision; robotics; transfer-learning",
            "keywords": "",
            "abstract": "Recognizing visual information is crucial for many real artificial-intelligence-based applications, ranging from domestic robots to autonomous vehicles. However, the success of deep learning methods on visual recognition tasks is highly dependent on access to large-scale labeled datasets, which are expensive and cumbersome to collect. Transfer learning provides a way to alleviate the burden of annotating data, which transfers the knowledge learned from a rich-labeled source domain to a scarce-labeled target domain. However, the performance of deep learning models degrades significantly when testing on novel domains due to the presence of domain shift. To tackle the domain shift, conventional domain adaptation methods diminish the domain shift between two domains with a distribution matching loss or adversarial loss. These models align the domain-specific feature distribution and the domain-invariant feature distribution simultaneously, which is sub-optimal towards solving deep domain adaptation tasks, given that deep neural networks are known to extract features in which multiple hidden factors are highly entangled. This thesis explores how to learn effective transferable features by disentangling the deep features. The following questions are studied: (1) how to disentangle the deep features into domain-invariant and domain-specific features? (2) how would feature disentanglement help to learn transferable features under a synthetic-to-real domain adaptation scenario? (3) how would feature disentanglement facilitate transfer learning with multiple source or target domains? (4) how to leverage feature disentanglement to boost the performance in a federated system? To address these needs, this thesis proposes deep adversarial feature disentanglement: a class\/domain identifier is trained on the labeled source domain and the disentangler generates features to fool the class\/domain identifier. Extensive experiments and empirical analysis demonstrate the effectiveness of the feature disentanglement method on many real-world domain adaptation tasks. Specifically, the following three unsupervised domain adaptation scenarios are explored: (1) domain agnostic learning with disentangled representations, (2) unsupervised federated domain adaptation, (3) multi-source domain adaptation.",
            "source_url": "https:\/\/openalex.org\/W3137379704",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "OpenBU (Boston University)",
            "source_record_id": "W3137379704",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 909,
            "title": "Transfer learning in Takagi-Sugeno fuzzy models",
            "title_ar": "",
            "title_en": "Transfer learning in Takagi-Sugeno fuzzy models",
            "author": "Hua Zuo",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Technology Sydney",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Australia",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; expert-systems; transfer-learning; predictive-analytics",
            "keywords": "",
            "abstract": "In classical data-driven machine learning methods, massive amounts of labeled data are required to build a high-performance prediction model. However, the amount of labeled data in many real-world applications is insufficient, so establishing a prediction model is impossible. Transfer learning has recently emerged as a way of exploiting previously acquired knowledge to solve new yet similar problems much more efficiently and effectively. It exploits the knowledge accumulated in auxiliary domains to help construct prediction models in a target domain with inadequate training data. Most existing methods on transfer learning address classification tasks, but studies on transfer learning in the case of regression problems, which is an important category in prediction models, are still scarce. In addition, the existing works ignore the inherent phenomenon of uncertainty - a crucial factor during the knowledge transfer process. To fill these gaps, this research develops algorithms and methods to deal with transfer learning in homogeneous and heterogeneous spaces using fuzzy rule-based models. Fuzzy rules are first generated from the source domain through a learning process. These rules, as acquired knowledge, are then transferred to the target domain. First, a novel fuzzy rule-based domain adaptation method is proposed to transfer knowledge between domains in homogeneous spaces. It utilizes the existing fuzzy rules of source domain and modifies the input space with nonlinear mappings to adapt to the current regression tasks in the target domain. Second, a granular fuzzy domain adaptation framework, comprising three methods, is developed to handle the knowledge transfer problems based on the idea of granular computing. Thirdly, a fuzzy domain adaptation method is developed to handle the case that the numbers of fuzzy rules in two domains do not match. In addition, the proposed methods are also used to solve the classification problems in transfer learning. Fourthly, an innovative method that combines an infinite Gaussian mixture model with active learning is presented to discover the structure of data and actively augment information in a target domain. Fifthly, a fuzzy heterogeneous domain adaptation method is proposed to transfer knowledge in heterogeneous spaces. The proposed algorithms and methods are validated in each step of development using experiments performed on both synthetic and real-world datasets. The results show that this study significantly improve the performance of existing models when solving new tasks in the target domain in both homogeneous and heterogeneous domain adaptation settings.",
            "source_url": "https:\/\/openalex.org\/W2894269285",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "UTS ePRESS (University of Technology Sydney)",
            "source_record_id": "W2894269285",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 911,
            "title": "Unleashing the power of transfer learning for visual applications",
            "title_ar": "",
            "title_en": "Unleashing the power of transfer learning for visual applications",
            "author": "Chang Liu",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Northeastern University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; computer-vision; transfer-learning",
            "keywords": "",
            "abstract": "Transfer learning is a prominent paradigm in machine learning, addressing the challenges of model generalization across different domains. This dissertation delves into two fundamental aspects: domain generalization and domain adaptation. In the context of domain generalization, the objective is to build models capable of effectively generalizing to unseen target domains by leveraging information from multiple source domains during training. Conversely, domain adaptation focuses on adapting a model trained on a specific source domain to a distinct target domain, assuming the availability of data from the target domain during training. Furthermore, this work explores close-set and open-set settings in transfer learning. The close-set setting assumes a fixed set of known target classes, while the open-set setting handles the challenge of novel, unseen classes in the target domain during inference. Understanding these settings' nuances is crucial for developing versatile transfer learning strategies that cater to diverse real-world scenarios and data distributions. The primary goals of transfer learning in this study include enhancing the model's performance on the target domain and reducing training costs by leveraging knowledge from a related source domain. However, achieving these goals comes with challenges, including addressing domain shift, preventing negative transfer, and handling unknown classes in open-set settings. By investigating these challenges and developing innovative transfer-learning techniques, this dissertation contributes to the broader field of transfer-learning by offering a comprehensive exploration of domain generalization, domain adaptation, and close-set, and open-set settings. The insights gained from this research provide a foundation for developing effective transfer learning strategies, enabling the deployment of adaptable and high-performance models in real-world scenarios with varying domain characteristics and data availability.--Author's abstract",
            "source_url": "https:\/\/openalex.org\/W4388761286",
            "pdf_url": "https:\/\/repository.library.northeastern.edu\/files\/neu:4f21nv77f\/fulltext.pdf",
            "doi": "10.17760\/d20581914",
            "handle": "",
            "repository_name": "Digital Repository Service (Northeastern University)",
            "source_record_id": "W4388761286",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 914,
            "title": "Learning to recognize objects by adaptive knowledge transfer",
            "title_ar": "",
            "title_en": "Learning to recognize objects by adaptive knowledge transfer",
            "author": "Qingyi Tao",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Nanyang Technological University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Singapore",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; object-detection; medical-imaging",
            "keywords": "",
            "abstract": "When humans learn new knowledge and skills, we can naturally transfer them to other domains. Along with the learning procedures, we learn knowledge and skills for certain tasks and transfer them to similar tasks; we also can use the old knowledge to facilitate the learning of new knowledge. While effective knowledge transfer is a congenital and important learning ability of humans, it is not easy for machine learning mechanisms to adopt the ability of knowledge transfer. In recent years, there are plenty of works studying transfer learning in deep learning. There are still some practical challenges that remain undiscovered, especially under different problem settings encountered in real situations. In this thesis, we explore how to adopt knowledge transfer mechanisms in deep learning approaches in several practical scenarios. Four different works are proposed to study knowledge transfer across different domains and tasks via domain adaptation and model transfer. In particular, we study the web knowledge transfer for object detection task by adapting the web data to the real target dataset, which aims at reducing the human annotation effort for training object detector. In the incremental learning scenario, we study the cross-utilization of the old and new knowledge to overcome the catastrophic forgetting during the incremental and progressive learning process. Lastly, we explore transfer learning in the medical imaging domain by transferring the model pre-trained on normal images. Overall, the major contributions are summarized as follows: - A web knowledge transfer method to enhance the learning of weakly supervised object detection. The proposed method includes an effective web data collection pipeline and a curriculum learning scheme to achieve more effective model optimization during multi-instance learning. - An annotation-effective object detection method by adapting web data to the target data for object detection. This work attempts to learn an object detector from web supervision by adversarial domain adaptation. - An incremental learning scheme that adapts an old model to a new model without forgetting the old knowledge. A systematic study is performed to explore different class incremental methods. Furthermore, we propose a graph-based method to mine the old sample forgettability along with the training of the new tasks, and dynamically select samples that are more forgettable to overcome the catastrophic forgetting. - A lesion detection method for 3D CT images by utilizing model weights that are pre-trained on normal 2D RGB images. Furthermore, an attention-based feature aggregation method is proposed to adaptively transfer the information from neighboring slices to the key slices for more discriminative representation. Through this thesis, we demonstrate three different paradigms of knowledge transfer, including (1) the cross-domain knowledge transfer for adapting web data to an application with real unconstrained data, (2) the continual knowledge transfer from old tasks to new tasks without forgetting the old knowledge, and (3) the model transfer from the normal image domain to the medical domain. Under several practical tasks, the experiments are conducted to demonstrate the effectiveness of the proposed knowledge transfer approaches.",
            "source_url": "https:\/\/openalex.org\/W3177101414",
            "pdf_url": "https:\/\/dr.ntu.edu.sg\/bitstream\/10356\/151507\/4\/thesis_oneside_2021_taoqingyi.pdf",
            "doi": "10.32657\/10356\/151507",
            "handle": "",
            "repository_name": "DR-NTU (Nanyang Technological University)",
            "source_record_id": "W3177101414",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 916,
            "title": "Exploring Transfer Learning Focused on Physiological Signals for Emotion Recognition",
            "title_ar": "",
            "title_en": "Exploring Transfer Learning Focused on Physiological Signals for Emotion Recognition",
            "author": "Cameron Lopez",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Texas A&M University Libraries",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "sentiment-analysis",
            "categories": "machine-learning; nlp; transfer-learning; sentiment-analysis",
            "keywords": "",
            "abstract": "Recent work in the area of automatic emotion recognition has leveraged a large amount of publicly available data with transfer learning techniques to detect emotion on low-resource data. Previous work demonstrated that the use of maximum independence domain adaptation and transfer component analysis show promise in generalizing on unseen domains. While the accuracy increases are significant, they remain below within-dataset models. Other research concluded that a subspace alignment auto-encoder (SAAE) is useful for domain adaptation and is more effective than current techniques. Despite the encouraging results of these studies, more work needs to be done to extend this to real world brain computer interaction (BCI) applications. The primary goal of this thesis is to develop transfer learning techniques that leverage existing data and attempt to generalize them on unseen domains accurately enough for real-world applications. If the proposed endeavor is successful, emotion recognition for real-life applications will not need to include large amounts of data from the target domain since transfer learning techniques will be able to accurately generalize on unseen domains.",
            "source_url": "https:\/\/openalex.org\/W3094441479",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "OakTrust (Texas A&M University Libraries)",
            "source_record_id": "W3094441479",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 945,
            "title": "Catalan Text Simplification with Large Language Models",
            "title_ar": "",
            "title_en": "Catalan Text Simplification with Large Language Models",
            "author": "Arnau Ayguadé Domingo",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Universitat Pompeu Fabra",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Spain",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; nlp; transfer-learning; llm",
            "keywords": "",
            "abstract": "Automatic text simplification (ATS) is crucial for accessibility, yet it remains underexplored for low-resource languages. This thesis investigates sentence-level ATS for Catalan using large language models (LLMs). A performance analysis of three LLMs is conducted using the iDEM corpus as a benchmark and SARI as the ATS evaluation metric. Diverse prompt engineering techniques are employed to examine their impact on simplification quality. This work introduces a novel reward function that combines SARI with specific penalty terms to achieve better alignment. The reward function is designed for Group Relative Policy Optimization (GRPO) to guide LLMs toward a targeted simplification style. The effectiveness of GRPO with this reward function is demonstrated by post-training IberianLLM-7B-Instruct on the ASSET dataset. Following post-training, the model’s ATS performance improves, while also successfully suppressing negative behaviors. Cross-lingual transfer learning is explored by translating ASSET into Catalan and Spanish and post-training the model on them.",
            "source_url": "https:\/\/openalex.org\/W7214133122",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Repositori digital de la UPF (Universitat Pompeu Fabra)",
            "source_record_id": "W7214133122",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:55",
            "updated_at": "2026-11-15 16:52:55"
        },
        {
            "id": 1001,
            "title": "Deep Learning Based Face Detection and Recognition in MWIR and Visible Bands",
            "title_ar": "",
            "title_en": "Deep Learning Based Face Detection and Recognition in MWIR and Visible Bands",
            "author": "Suha Reddy Mokalla",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "West Virginia University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "face-recognition",
            "categories": "machine-learning; deep-learning; computer-vision; generative-ai; transfer-learning; face-recognition; gan",
            "keywords": "",
            "abstract": "In non-favorable conditions for visible imaging like extreme illumination or nighttime, there is a need to collect images in other spectra, specifically infrared. Mid-Wave infrared (3-5 microm) images can be collected without giving away the location of the sensor in varying illumination conditions. There are many algorithms for face detection, face alignment, face recognition etc. proposed in visible band till date, while the research using MWIR images is highly limited. Face detection is an important pre-processing step for face recognition, which in turn is an important biometric modality. This thesis works towards bridging the gap between MWIR and visible spectrum through three contributions. First, a dual band based deep face detection model that works well in visible and MWIR spectrum is proposed using transfer learning. Different models are trained and tested extensively using visible and MWIR images and the one model that works well for this data is determined. For this model, experiments are conducted to learn the speed\/accuracy trade-off. Following this, the available MWIR dataset is extended through augmentation using traditional methods and generative adversarial networks (GANs). Traditional methods used to augment the data are brightness adjustment, contrast enhancement, applying noise to and de-noising the images. A deep learning based GAN architecture is developed and is used to generate new face identities. The generated images are added to the original dataset and the face detection model developed earlier is once again trained and tested. The third contribution is the proposal of another GAN that converts given thermal ace images into their visible counterparts. A pre-trained model is used as discriminator for this purpose and is trained to classify the images as real and fake and an identity network is used to provide further feedback to the generator. The generated visible images are used as probe images and the original visible images are used as gallery images to perform face recognition experiments using a state-of-the-art visible-to-visible face recognition algorithm.",
            "source_url": "https:\/\/openalex.org\/W3024705230",
            "pdf_url": "https:\/\/researchrepository.wvu.edu\/cgi\/viewcontent.cgi?article=8577&context=etd",
            "doi": "10.33915\/etd.7632",
            "handle": "",
            "repository_name": "The Research Repository @ WVU (West Virginia University)",
            "source_record_id": "W3024705230",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:57",
            "updated_at": "2026-11-15 16:52:57"
        },
        {
            "id": 1002,
            "title": "Face recognition enhancement through the use of depth maps and deep learning",
            "title_ar": "",
            "title_en": "Face recognition enhancement through the use of depth maps and deep learning",
            "author": "Yaser Saleh",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Loughborough University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2017,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "object-detection",
            "categories": "machine-learning; deep-learning; computer-vision; transfer-learning; cnn; multimodal; object-detection; face-recognition",
            "keywords": "",
            "abstract": "Face recognition, although being a popular area of research for over a decade has still many open research challenges. Some of these challenges include the recognition of poorly illuminated faces, recognition under pose variations and also the challenge of capturing sufficient training data to enable recognition under pose\/viewpoint changes. With the appearance of cheap and effective multimodal image capture hardware, such as the Microsoft Kinect device, new possibilities of research have been uncovered. One opportunity is to explore the potential use of the depth maps generated by the Kinect as an additional data source to recognize human faces under low levels of scene illumination, and to generate new images through creating a 3D model using the depth maps and visible-spectrum \/ RGB images that can then be used to enhance face recognition accuracy by improving the training phase of a classification task.. With the goal of enhancing face recognition, this research first investigated how depth maps, since not affected by illumination, can improve face recognition, if algorithms traditionally used in face recognition were used. To this effect a number of popular benchmark face recognition algorithms are tested. It is proved that algorithms based on LBP and Eigenfaces are able to provide high level of accuracy in face recognition due to the significantly high resolution of the depth map images generated by the latest version of the Kinect device. To complement this work a novel algorithm named the Dense Feature Detector is presented and is proven to be effective in face recognition using depth map images, in particular under wellilluminated conditions. Another technique that was presented for the goal of enhancing face recognition is to be able to reconstruct face images in different angles, through the use of the data of one frontal RGB image and the corresponding depth map captured by the Kinect, using faster and effective 3D object reconstruction technique. Using the Overfeat network based on Convolutional Neural Networks for feature extraction and a SVM for classification it is shown that a technically unlimited number of multiple views can be created from the proposed 3D model that consists features of the face if captured real at similar angles. Thus these images can be used as real training images, thus removing the need to capture many examples of a facial image from different viewpoints for the training of the image classifier. Thus the proposed 3D model will save significant amount of time and effort in capturing sufficient training data that is essential in recognition of the human face under variations of pose\/viewpoint. The thesis argues that the same approach can also be used as a novel approach to face recognition, which promises significantly high levels of face recognition accuracy base on depth images. Finally following the recent trends in replacing traditional face recognition algorithms with the effective use of deep learning networks, the thesis investigates the use of four popular networks, VGG-16, VGG-19, VGG-S and GoogLeNet in depth maps based face recognition and proposes the effective use of Transfer Learning to enhance the performance of such Deep Learning networks.",
            "source_url": "https:\/\/openalex.org\/W2779335121",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Loughborough University Institutional Repository (Loughborough University)",
            "source_record_id": "W2779335121",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:57",
            "updated_at": "2026-11-15 16:52:57"
        },
        {
            "id": 1028,
            "title": "Statistical Machine Learning on Time Series with Applications to Manufacturing and Healthcare",
            "title_ar": "",
            "title_en": "Statistical Machine Learning on Time Series with Applications to Manufacturing and Healthcare",
            "author": "Ying Liao",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Texas Tech University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; deep-learning; medical-ai; ai-applications; transfer-learning; predictive-analytics; ai-industry",
            "keywords": "",
            "abstract": "Predictive analysis in time series is critical to making informed decision-making and has been extensively studied in a wide range of fields including manufacturing and healthcare. The temporal patterns contained in time series hold the promise of making predictions on future behaviors as those patterns often reflect the health state evolution. However, developing such predictive models is a challenging problem because (1) the actual health state is typically not directly observable and can only be assessed from the health condition monitoring data (e.g., sensor measurements of the engineering system, physiological signals of the patient); (2) the health state transition may depend heavily on historical states due to complicated failure mechanisms or complex disease progression; (3) the health evolution trends generally exist significant variability due to some critical exogenous factors (e.g., operational and environmental conditions of the engineering systems, gender and age of the patients) and heterogeneity; and (4) when making predictions at an early stage, the temporal patterns may be too subtle to be detected by traditional methods (e.g., abnormality in early ECGs associated with future cardiac diseases). This dissertation addresses these challenges by developing novel and flexible statistical models and leveraging machine learning algorithms, and investigating the performance of the proposed methods in simulation studies as well as real-world applications. We first develop a flexible prognostics framework based on a higher-order hidden semi-Markov model (HOHSMM) for systems or components with unobservable health states and complex transition dynamics. The HOHSMM extends the basic hidden Markov model (HMM) by allowing the hidden state to depend on its more distant history and assuming generally distributed state duration. An effective Gibbs sampling algorithm is designed for model inference and is evaluated by a simulation study. We design a decoding algorithm to estimate the hidden health states and use a simulation approach to predict the remaining useful life for a functioning system in operation. A case study on the NASA turbofan engines demonstrates the practical utility of the proposed prognostics framework. To further capture the variability among time series due to some critical factors and patient-level heterogeneity, we propose a novel and flexible Bayesian mixed-effect higher-order HMM (MHOHMM) to predict patients' future events based on their electronic health records. A range of MHOHMMs are designed to capture different data structures and the optimal one is identified by using the $k$-fold cross-validation. An effective two-stage MCMC sampling algorithm is designed for MHOHMM inference. A simulation study is conducted to evaluate the performance of the proposed sampling algorithm and the MHOHMM-based classifier. The results show that considering the impacts of mixed effects and higher-order transition dynamics significantly improves prediction performance when such impacts present in the data. Furthermore, we conduct a case study on acute hypotensive episode prediction using real-world clinical data to demonstrate the effectiveness and advantage of the proposed prediction framework. For problems of making predictions at an early stage, we adapt state-of-the-art deep learning techniques to detect subtle patterns. To investigate whether mutant mice present subtle abnormalities in their early ECGs before severe arrhythmias occur, we propose a deep transfer learning (TL) model, DeepMiceTL, to predict cardiac conduction diseases using early mouse ECGs. We further apply the Bayesian optimization and $k$-fold cross-validation methods to tune the hyperparameters of the DeepMiceTL. Our results show that DeepMiceTL achieves promising performance to identify ECG patterns during the early course of cardiac conduction disease in mice. Our study also suggests the feasibility for early clinical diagnosis of human cardiac conduction diseases and other types of cardiac arrhythmias using deep learning in the future.",
            "source_url": "https:\/\/openalex.org\/W7134143582",
            "pdf_url": "https:\/\/ttu-ir.tdl.org\/bitstreams\/1817fc56-24a6-49bd-b8bd-56b6016bab98\/download",
            "doi": "",
            "handle": "",
            "repository_name": "ThinkTech (Texas Tech University)",
            "source_record_id": "W7134143582",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:57",
            "updated_at": "2026-11-15 16:52:57"
        },
        {
            "id": 1035,
            "title": "Contributions on Deep Transfer Learning",
            "title_ar": "",
            "title_en": "Contributions on Deep Transfer Learning",
            "author": "Chetak Kandaswamy",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Portugal",
            "governorate": "",
            "publication_year": 2016,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "cnn",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn",
            "keywords": "",
            "abstract": "Machine Learning (ML) is reshaping our world by building machines that can see, read, listen, talk, and write (Marr, 2015).For example, imagine you want to eat your favorite food and ask a mobile app what are the nearby restaurants that serve your favorite food.The app uses a ML algorithm to analyze the information of your location and time to provide better service.Imagine a startup that wants to use ML algorithm optimize their resources and requirements.Envision a scenario where a breast cancer patient and a surgeon want to plan a surgery.Generally, it takes a highly trained surgeon's subjective evaluation of the breast cancer surgery to make treatment decisions.Employing ML algorithms allows an objective evaluation of the surgery with a sense of femininity (aesthetic metric by (Beadle et al., 1984)), using 3D imaging that helps the patient and the doctor to visualize and collectively decide what they are seeing, and then make a informed decision about the surgery (Oliveira, 2013).The ability of ML algorithms to automatically understand the contents of images opened new ways to tackle prominent computer vision challenges like view point variation, illumination, occlusion, scale, deformation, background clutter, and intra-class variation.Especially, Deep learning algorithms like Stacked Denoising Autoencoders, Convolutional Neural Networks, and Deep Belief Nets have addressed these challenges with state-of-the-art results and have surpassed human performance.The salient attribute of Deep learning algorithms is that they automatically learn features from a large number of data samples without overfitting the model.Deep learning provides a partial solution to the research statement how to get computer programs to self-learn patterns from data.We consider machine learning as a broadening field which integrates interdisciplinary knowledge of learning processes from other fields such as psychology, biology, neuroscience, and economy.From this we attempt to answer questions such as: what kind of process can lead to learning, under what conditions, and for what kind of data?(Mitchell, 2006) In this thesis we integrated knowledge of deep learning with transfer learning where the learning is inspired from human-like learning processes to build our Deep Transfer Learning framework: \"how to get computer programs to self-learn patterns in data-efficient and domaingeneral way?\"Our survey on the state-of-the-art machine learning methods that use self-learn patterns lead to deep learning models.The subsequent question is about how learning algorithms can be inspired from human-like learning processes.For the sake of simplicity, we narrowed our scope down to human like knowledge transfer from one scenario to another.It is interesting to study the various possible cases of transfer learning settings based on the distributions, posterior probabilities, learning function and the classification tasks.We have designed three main mechanisms that harness the advantages of our proposed Deep Transfer Learning (DTL) framework: 1) Layerwise Transfer Learning (LTL), 2) Source-Target-Source (STS) and 3) Deep Transfer Learning Ensemble.First, we developed two approaches based on LTL mechanism : a) Transfer Learning unsupervised (TLu) and b) Transfer Learning supervised (TLs).On de conhecimento do ser-humano.Como simplificação, reduzimos o espectro de interesse na transferência de conhecimento entre duas tarefas de modo a utilizar conhecimento adquirido numa para resolver outra.É interessante estudar uma série de possíveis variações no processo de transferência de aprendizagem, quer ao nível das distribuições, probabilidades posteriores, funções de aprendizagem e também tarefas de classificação.Foram criados três mecanismos base da framework de deep transfer learning: 1) Layerwise Transfer Learning (LTL), 2) Source-Target-Source (STS) e 3) Deep Transfer Learning Ensemble.Relativamente à primeira metodologia, duas abordagens foram tomadas: a) Transferência de conhecimento não-supervisionada (TLu) e b) Transferência de conhecimento supervisionada (TLs).Por outro lado, os mecanismos de STS desenvolvidos foram testados tanto em problemas com uma fonte de informação como em problemas de múltiplas fontes.Finalmente, foram também desenvolvidas e testadas metodologias ensemble de várias abordagens LTL.De modo a analisar a eficácia dos métodos desenvolvidos, testes práticos foram levados a cabo ao nível de descoberta de fármacos e também de biometria inter-sensor.Um software de DTL baseado em interface interativa para algoritmos de AC baseados em GPU foi também implementado.Este software fornece uma interface para problemas baseline e outras metodologias de transferência de conhecimento.viii A special word of thanks to my friends without whose encouragement and unconditional support it would be a challenge: Saravanan Kandasamy, Kumaresa Vanji, Abhishek Chatterjee, Balamurugan Varadharajan, Herlina Jayadianti and Merle Planten.I would like to…",
            "source_url": "https:\/\/openalex.org\/W2592277968",
            "pdf_url": "https:\/\/repositorio-aberto.up.pt\/bitstream\/10216\/85509\/2\/145323.pdf",
            "doi": "10.34626\/bjwn-t886",
            "handle": "",
            "repository_name": "Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)",
            "source_record_id": "W2592277968",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:57",
            "updated_at": "2026-11-15 16:52:57"
        },
        {
            "id": 1045,
            "title": "Classification of ulcer images using convolutional neural networks",
            "title_ar": "",
            "title_en": "Classification of ulcer images using convolutional neural networks",
            "author": "Charlotta Aguirre Nilsson ; Medina Velic",
            "supervisor": "",
            "degree_type": "master",
            "degree_evidence": "نص السجل: «master»",
            "university": "Chalmers University of Technology",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Sweden",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; transfer-learning; cnn; image-classification; medical-imaging",
            "keywords": "",
            "abstract": "The use of artificial intelligence has increased within a variety of different fields the last decade, including the area of health care.Machine learning algorithms have already been successfully used in e.g.skin cancer detection in images, indicating its potential for being applied to wound treatment by automatically classifying wound images.In addition to reducing patient discomfort, a machine learning based solution for wound image classification could lower the costs for treatment of wounds.Today, this cost corresponds to the third biggest health care cost for Västra Götalandsregionen, the health care sector in Västra Götaland.This master thesis is a collaboration between the electronics and software development company QRTECH and Västra Götalandsregionen with the aim of creating an image-based aid to be used in the diagnosis of venous leg ulcers.A total of 300 manually annotated images depicting various ulcers for training a network have been provided by Alexandra Forssgren, specialist in dermatology and head of the dermatology department at Skaraborg Hospital.A deep learning based algorithm, using a pre-trained version of the VGG19 convolutional neural network, has been implemented to perform automated binary classification in order to separate venous leg ulcers from other ulcers.Since the annotated ulcer data set was limited, transfer learning was used by pre-training on ImageNet as well as on a set of dermoscopic skin images.The network was implemented in Python using the deep learning library Keras with TensorFlow as backend.To improve performance and reduce overfitting, methods such as dropout, L1\/L2 regularisation and data augmentation were applied.Augmentation included rotation, flipping, contrast enhancement as well as added noise and modified brightness.The best set-up was selected based on the performance metrics accuracy, precision and recall.For the test set, the final network reached an accuracy, precision and recall of approximately 85 %, 82 % and 75 %, respectively.Most certainly, the limited size of the data set affected the results negatively and a larger data set would increase the variety of the training examples, possibly leading to better performance.However, the performance metrics are still promising considering the small data set which proves the potential of a machine learning based solution for ulcer image classification.",
            "source_url": "https:\/\/openalex.org\/W2889535768",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Chalmers Publication Library (Chalmers University of Technology)",
            "source_record_id": "W2889535768",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:57",
            "updated_at": "2026-11-15 16:52:57"
        },
        {
            "id": 1057,
            "title": "Convolutional neural networks for multi- and hyper-spectral image classification",
            "title_ar": "",
            "title_en": "Convolutional neural networks for multi- and hyper-spectral image classification",
            "author": "Jacob Senecal",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "image-classification",
            "categories": "machine-learning; deep-learning; computer-vision; ai-applications; transfer-learning; predictive-analytics; cnn; image-classification; ai-agriculture",
            "keywords": "",
            "abstract": "While a great deal of research has been directed towards developing neural network architectures for classifying RGB images, there is a relative dearth of research directed towards developing neural network architectures specifically for multi-spectral and hyper-spectral imagery. The additional spectral information contained in a multi-spectral or hyper-spectral image can be valuable for land management, agriculture and forestry, disaster control, humanitarian relief operations, and environmental monitoring. However, the massive amounts of data generated by a multi-spectral or hyper- spectral instrument make processing this data a challenge. Machine learning and computer vision techniques could automate the analysis process of these rich data sources. With these benefits in mind, we have adapted recent developments in small efficient convolutional neural networks (CNNs), to create a small CNN architecture capable of being trained from scratch to classify 10 band multi-spectral images, using much fewer parameters than popular deep architectures, such as the ResNet or DenseNet architectures. We show that this network provides higher classification accuracy and greater sample efficiency than the same network using RGB images. We also show that it is possible to employ a transfer learning approach and use a network pre-trained on multi-spectral satellite imagery to increase accuracy on a second much smaller multi-spectral dataset, even though the satellite imagery was captured from a much different perspective (high altitude, overhead vs. ground based at close stand-off distance). These results demonstrates that it is possible to train our small network architectures on small multi-spectral datasets and still achieve high classification accuracy. This is significant as labeled hyper-spectral and multi-spectral datasets are generally much smaller than their RGB counterparts. Finally, we approximate a Bayesian version of our CNN architecture using a recent technique known as Monte Carlo dropout. By keeping dropout in place during test time we can perform a Monte Carlo procedure using multiple forward passes of our network to generate a distribution of network outputs which can be used as a measure of uncertainty in the predictions a network is making. Large variance in the network output corresponds to high uncertainty and vice versa. We show that a network that is capable of working with multi-spectral imagery significantly reduces the uncertainty associated with class predictions compared to using RGB images. This analysis reveals that the benefits of an architecture that works effectively with multi-spectral or hyper-spectral imagery extends beyond higher classification accuracy. Multi-spectral and hyper-spectral imagery allows us to be more confident in the predictions that a deep neural network is making.",
            "source_url": "https:\/\/openalex.org\/W3180804842",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W3180804842",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:57",
            "updated_at": "2026-11-15 16:52:57"
        },
        {
            "id": 1134,
            "title": "Neural machine translation with limited resources",
            "title_ar": "",
            "title_en": "Neural machine translation with limited resources",
            "author": "Tasnim Mohiuddin",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Nanyang Technological University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Singapore",
            "governorate": "",
            "publication_year": 2022,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "machine-translation",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; transfer-learning; predictive-analytics; machine-translation",
            "keywords": "",
            "abstract": "With the advent of deep neural networks in recent years, Neural Machine Translation (NMT) systems have achieved state-of-the-art performance on standard translation benchmarks. NMT is a way to translate from one language to another with a single neural network in an end-to-end manner. The NMT models have emerged quickly, and within a few years of research, they have outperformed the traditional statistical systems with impressive performance. Despite the success of NMT models in standard benchmarks, there are some notable limitations. One of them is that NMT models are known to be data-hungry, i.e., they tend to work very well only when a massive amount of parallel training data (a.k.a. bitext) is available, but perform poorly when the data is limited. Except for some mainstream languages, e.g., English, French, or Chinese, most natural languages are low-resourced and lack large parallel data. Moreover, acquiring large bitext corpora is not viable in most scenarios, especially with resource-constrained conditions like low-resource languages. Researchers have made numerous endeavors to expand the success of NMT from high-resource to low-resource languages like transfer learning, data augmentation, and pivoting. However, they still require strong cross-lingual signals, i.e., lots of parallel data. One solution to this problem might be transferring cross-lingual signals through cross-lingual word embeddings (CLWEs), which can be learned from monolingual data in an unsupervised way or with the help of a small seed dictionary. CLWEs seem to be very promising in resource-constrained machine translation (MT). Most of the successful and predominant CLWE methods (a.k.a. word translation methods) learn a linear mapping function based on the isomorphic assumption, which is problematic. We hypothesize to learn the cross-lingual mapping in a projected latent space which would give the model enough flexibility to induce the required geometric structures such that it would be easier to align the embeddings. Based on this hypothesis, we propose two novel models for learning CLWEs. We empirically show that our methods are particularly very effective for low-resource languages. We then turn our attention from word- to sentence-level translation with limited resources. Specifically, we focus on data augmentation strategies widely used in NLP and Computer Vision to increase the robustness of the models in resource-constrained scenarios. We investigate the domain-mismatch issue thoroughly that hinders the all-embracing success of the existing techniques in NMT. Eventually, we introduce a novel data augmentation framework for low-resource NMT that leverages the neighboring samples of the original parallel data without explicitly using additional monolingual data. Our framework can diversify the in-domain parallel data in a controlled way. We perform extensive experiments on four low-resource language pairs comprising data from different domains. We have shown that our method is comparable to the traditional back-translation that uses extra in-domain monolingual data. Typically, NMT systems are trained on heterogeneous data from different domains, sources, topics, styles, and modalities. The quality of the data also varies a lot. Usually, during training, all the data are concatenated and randomly shuffled. However, not all of them may be useful, some data may be redundant, and some might even be noisy and detrimental to the final NMT system performance. These problems are more acute in low-resource languages compared to the high-resource ones. Consequently, we explore the possibilities of curriculum training for NMT systems, i.e., presenting the data to the NMT systems in a systematic order during training. We introduce a two-stage curriculum training framework for NMT where we fine-tune a base NMT model on subsets of data. To select the data subsets, we propose two scoring approaches --- deterministic scoring using pre-trained methods and online scoring that considers prediction scores of the emerging NMT model. Our curriculum strategies consistently demonstrate better translation quality and faster convergence (approximately 50% fewer updates) on both high- and low-resource languages.",
            "source_url": "https:\/\/openalex.org\/W4281623321",
            "pdf_url": "https:\/\/dr.ntu.edu.sg\/bitstream\/10356\/157475\/2\/Thesis-Tasnim.pdf",
            "doi": "10.32657\/10356\/157475",
            "handle": "",
            "repository_name": "DR-NTU (Nanyang Technological University)",
            "source_record_id": "W4281623321",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "id": 1135,
            "title": "Approximating neural machine translation for efficiency",
            "title_ar": "",
            "title_en": "Approximating neural machine translation for efficiency",
            "author": "Alham Fikri Aji",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; nlp; transfer-learning; transformers; machine-translation",
            "keywords": "",
            "abstract": "Neural machine translation (NMT) has been shown to outperform statistical machine translation. However, NMT models typically require a large number of parameters and are expensive to train and deploy. Moreover, its large model size makes parallel training inefficient due to costly network communication. Likewise, distributing and locally running the model for a client-based NMT model such as a web browser or mobile device remains challenging. This thesis investigates ways to approximately train an NMT system by compressing either the gradients or the parameters for faster communication or reduced memory consumption. We propose a gradient compression technique that exchanges only the top 1% of the most significant gradient values while delaying the rest to be considered for the next iteration. This method reduces the network communication cost by 50-fold but causes noisy gradient updates. We also find that Transformer–the current state-of-the-art NMT architecture–is highly sensitive to noisy gradients. Therefore, we extend the compression technique by restoring the compressed gradient with locally-computed gradients. We obtained a linear scale-up in parallel training without sacrificing model performance. We also explore transfer learning as a better method of initialising the training. With transfer learning, the model converges faster and can be trained with more aggressive hyperparameters. Lastly, we propose a log-based quantisation method to compress the model size. Models are quantised to 4-bit precision with no noticeable quality degradation after re-training combined with reserving the quantisation errors as feedback.",
            "source_url": "https:\/\/openalex.org\/W3108682037",
            "pdf_url": "",
            "doi": "10.7488\/era\/533",
            "handle": "",
            "repository_name": "ERA",
            "source_record_id": "W3108682037",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "id": 1207,
            "title": "A study of Machine Learning for Predictive Maintenance - A topic and programming guidance",
            "title_ar": "",
            "title_en": "A study of Machine Learning for Predictive Maintenance - A topic and programming guidance",
            "author": "Kåre Hartlapp Lærum",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Norway",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; deep-learning; ai-applications; transfer-learning; predictive-analytics; ai-industry",
            "keywords": "",
            "abstract": "A significant potential and interest is found for Predictive Maintenance (PdM) and Machine Learning (ML). Both fields are under development and need further research. Through collaboration with the Norwegian maintenance company, Karsten Moholt, two areas of special significance for this thesis where found. Firstly, finding more information regarding the ML approach and especially the potential of Transfer Learning (TL), and secondly, understanding and building an ML model for PdM. This thesis aims to provide an introduction and to be practical start guide for those interested in using ML for PdM. To achieve this, necessary background information has been collected, and to further learn about ML, several online courses has been completed. The online course, books and several web-guides are used to build and develop two ML models to find Remaining Useful Life (RUL) on the Turbofan Engine Degradation Data Set provided by NASA. The information and code are presented to enable the reader to understand ML and to provide tool to start building ML models. PdM is presented as a technique for monitoring operating condition to provide data that can ensure the maximum interval between repairs and minimize the number and cost of unscheduled machine failures. ML is con sidered as an important and powerful tool for finding patterns and make predictions from a vast amount of data where Neural Networks (NN) is the main technique for implementing ML. TL is considered as a powerful idea, where knowledge from one NN can be transferred to another. Further, the topic of NN is presentment and explained with examples. To enable the reader to start programming, needed tools such as Python, Jupyter, Numpy, Pandas and Keras are presented, used and recommended. The first model provides a guide on how to program an NN oneself, and includes the elements; prepare data , initialize weights and biases , forward propagation , calculating cost , backpropagation and update parameters . The second model presents how to program the same model with Keras, a NN framework, also enabling one to build a ML model with few lines of code. This guide provides examples and tools that can be used for simple demonstrations of ML for regression problems. The thesis provides arguments and justification for the need for further research. It enables a foundation for further development of ML models for different PdM RUL scenarios.",
            "source_url": "https:\/\/openalex.org\/W2900613942",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "NORA - Norwegian Open Research Archives",
            "source_record_id": "W2900613942",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:59",
            "updated_at": "2026-11-15 16:52:59"
        },
        {
            "id": 1266,
            "title": "Pre-training model based on the transfer learning in natural language processing",
            "title_ar": "",
            "title_en": "Pre-training model based on the transfer learning in natural language processing",
            "author": "Jiayi Tang",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Nanyang Technological University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Singapore",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; nlp; transfer-learning; predictive-analytics; cnn; transformers; llm",
            "keywords": "",
            "abstract": "Transfer learning is to apply knowledge or patterns learned in a particular field or task to different but related areas or problem. It is very prominent in terms of scarcity of data and heterogeneity of domain distribution. In the field of natural language processing, transfer learning is embodied in the pre-training model. There are two existing strategies for applying pre-trained language representations to downstream tasks: feature-based (ELMO) and fine-tuning (GPT、BERT). In 2018, Google released a large-scale pre-training language model BERT, which stands for Bidirectional Encoder Representations from Transformer. Compared with other pre-training model ELMO and GPT, and the classical model CNN, BERT is the latest and best-performing model up until now. Its highlights are (1) Bidirectional Transformer (2) Mask-Language Model (3) Next Sentence Prediction (4) A more general input layer and output layer. BERT model can efficiently learn text information and apply it to various NLP tasks. In this report, we use the BERT model in two way. The first is to use the pre-training model released by Google directly and then pass the fine-tuning stage. The second is to use the BERT-as-service to use the BERT model as a sentence encode followed by a DNN classifier. Then we horizontally compare BERT with ELMO and GPT; then vertically compare BERT with different parameters.",
            "source_url": "https:\/\/openalex.org\/W2953559479",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "DR-NTU (Nanyang Technological University)",
            "source_record_id": "W2953559479",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:53:00",
            "updated_at": "2026-11-15 16:53:00"
        },
        {
            "id": 1269,
            "title": "Comparison of sequence classification techniques with BERT for named entity recognition",
            "title_ar": "",
            "title_en": "Comparison of sequence classification techniques with BERT for named entity recognition",
            "author": "Erik Rosvall",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "KTH Royal Institute of Technology",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Sweden",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; nlp; transfer-learning; transformers",
            "keywords": "",
            "abstract": "This thesis takes its starting point from the recent advances in Natural Language Processing being developed upon the Transformer model. One of the significant developments recently was the release of a deep bidirectional encoder called BERT that broke several state of the art results at its release. BERT utilises Transfer Learning to improve modelling language dependencies in texts. BERT is used for several different Natural Language Processing tasks, this thesis looks at Named Entity Recognition, sometimes referred to as sequence classification. This thesis compares the model architecture as it was presented in its original paper with a different classifier in the form of a Conditional Random Field. BERT was evaluated on the CoNLL-03 dataset, based on English news articles published by Reuters. The Conditional Random Field classifier overall outperforms the original Feed Forward classifier on the F1-score metric with a small margin of approximately 0.25 percentage points. While the thesis fails to reproduce the original report’s results it compares the two model architectures across the hyperparameters proposed for fine-tuning. Conditional Random Fields proves to perform better scores at most hyperparameter combination and are less sensitive to which parameters were chosen, creating an incentive for its use by reducing the effect of parameter search compared to a Feed Forward layer as the classifier. Comparing the two models shows a lower variance in the results for Conditional Random Fields.",
            "source_url": "https:\/\/openalex.org\/W2986482033",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "KTH Publication Database DiVA (KTH Royal Institute of Technology)",
            "source_record_id": "W2986482033",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:53:00",
            "updated_at": "2026-11-15 16:53:00"
        },
        {
            "id": 1272,
            "title": "Cyberbullying identification and classification using transformer models",
            "title_ar": "",
            "title_en": "Cyberbullying identification and classification using transformer models",
            "author": "Wachiraporn Tapaopong",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; nlp; ai-applications; transfer-learning; predictive-analytics; transformers; ai-cybersecurity",
            "keywords": "",
            "abstract": "The widespread use of social media platforms has made cyberbullying an increasingly prevalent issue, causing physical, emotional, and mental harm to victims. This study focuses on utilizing Natural Language Processing techniques to enhance the identification and analysis of cyberbullying in hazardous social media messages. To achieve this goal, we utilized the transfer learning and fine-tuning techniques with the Transformer models, specifically BERT, RoBERTa, ALBERT, DistilBERT, and ConvBERT, to compare the effectiveness of category prediction. The study tested two methods to evaluate the effectiveness of automated cyberbullying detection. The first involves six categories: religion, age, ethnicity, gender, not cyberbullying, and other types of cyberbullying. The second method did not include \"other types of cyberbullying.\" The findings revealed that DistilBERT was the model with the best performance for multi-class text classification with the least amount of training time. This research emphasized the value of automated cyberbullying detection by using the potential of Natural Language Processing techniques to reduce the negative consequences of cyberbullying. Overall, this study contributed to the development of effective and efficient approaches for identifying and classifying cyberbullying in order to prevent and intervene in cyberbullying. Implication of thematic paper: The implications of this research are significant in terms of addressing the issue of cyberbullying, which is becoming increasingly prevalent due to the widespread use of social media platforms. The use of Transformer models for cyberbullying identification and classification has the potential to significantly improve the accuracy and efficiency of automated detection systems. These models can learn to recognize and categorize cyberbullying behaviors in a way that is more nuanced and accurate than traditional machine learning approaches by utilizing deep learning. This could help social media platforms more effectively identify and address instances of cyberbullying, ultimately leading to a more secure and encouraging online environment for all users. Furthermore, the use of Transformer models for cyberbullying detection could also have broader implications for the fields of natural language processing and machine learning, as it demonstrates the potential for these models to effectively analyze and understand complex, human-generated text data.",
            "source_url": "https:\/\/openalex.org\/W7220849862",
            "pdf_url": "",
            "doi": "10.67546\/mu.th.6437949",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W7220849862",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:53:00",
            "updated_at": "2026-11-15 16:53:00"
        },
        {
            "id": 1278,
            "title": "Deep Learning Macroeconomics",
            "title_ar": "",
            "title_en": "Deep Learning Macroeconomics",
            "author": "Rafael Rockenbach da Silva Guimarães",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2022,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; deep-learning; transfer-learning; predictive-analytics",
            "keywords": "",
            "abstract": "Limited datasets and complex nonlinear relationships are among the challenges that may emerge when applying econometrics to macroeconomic problems. This research proposes deep learning as an approach to transfer learning in the former case and to map relationships between variables in the latter case. Although macroeconomists already apply transfer learning when assuming a given a priori distribution in a Bayesian context, estimating a structural VAR with signal restriction and calibrating parameters based on results observed in other models, to name a few examples, advance in a more systematic transfer learning strategy in applied macroeconomics is the innovation we are introducing. We explore the proposed strategy empirically, showing that data from different but related domains, a type of transfer learning, helps identify the business cycle phases when there is no business cycle dating committee and to quick estimate a economic-based output gap. Next, since deep learning methods are a way of learning representations, those that are formed by the composition of multiple non-linear transformations, to yield more abstract representations, we apply deep learning for mapping low-frequency from high-frequency variables. The results obtained show the suitability of deep learning models applied to macroeconomic problems. First, models learned to classify United States business cycles correctly. Then, applying transfer learning, they were able to identify the business cycles of out-of-sample Brazilian and European data. Along the same lines, the models learned to estimate the output gap based on the U.S. data and obtained good performance when faced with Brazilian data. Additionally, deep learning proved adequate for mapping low-frequency variables from high-frequency data to interpolate, distribute, and extrapolate time series by related series.",
            "source_url": "https:\/\/openalex.org\/W4226128270",
            "pdf_url": "",
            "doi": "10.48550\/arxiv.2201.13380",
            "handle": "",
            "repository_name": "LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)",
            "source_record_id": "W4226128270",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:53:00",
            "updated_at": "2026-11-15 16:53:00"
        },
        {
            "id": 1298,
            "title": "PLACE-BASED NAVIGATION FOR AUTONOMOUS VEHICLES WITH DEEP LEARNING NEURAL NETWORKS",
            "title_ar": "",
            "title_en": "PLACE-BASED NAVIGATION FOR AUTONOMOUS VEHICLES WITH DEEP LEARNING NEURAL NETWORKS",
            "author": "Magee, Ashleigh",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Naval Postgraduate School",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "image-classification",
            "categories": "machine-learning; deep-learning; computer-vision; robotics; transfer-learning; cnn; image-classification",
            "keywords": "",
            "abstract": "Accurate navigation is crucial to successfully deploying autonomous vehicles but is often limited by GPS reliance. The purpose of this thesis was to develop an image-based navigation solution that does not require GPS. This work builds on an ongoing research project, which is to develop a mobile robot that can navigate anywhere on the Naval Postgraduate School campus, inside and outside of buildings. This work focused on indoor navigation using image classification, and images were classified using a convolutional neural network (CNN). Transfer learning was used to reduce CNN training time and increase learning efficiency. The trained CNN was integrated into a waypoint loop algorithm that ran autonomously on the robot, stopping when it had correctly identified its desired location. Tests of the CNN classification showed a high success rate, but that it was also susceptible to variations in light and similar types of images. Increasing the data set will improve the classification results and allow for use in a variety of applications. This system will also benefit from improved indoor localization techniques.",
            "source_url": "https:\/\/openalex.org\/W7112451897",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Calhoun: The Naval Postgraduate School Institutional Archive (Naval Postgraduate School)",
            "source_record_id": "W7112451897",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:53:00",
            "updated_at": "2026-11-15 16:53:00"
        }
    ]
}