{
    "exported_at": "2026-11-16 23:06:49",
    "count": 54,
    "records": [
        {
            "id": 25,
            "title": "Deep Learning-Based Breast Cancer Detection with IoMT",
            "title_ar": "",
            "title_en": "Deep Learning-Based Breast Cancer Detection with IoMT",
            "author": "Bo Li",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Auckland",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "New Zealand",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "deep-learning; computer-vision; generative-ai; medical-ai; cnn; transformers; gan; medical-imaging",
            "keywords": "",
            "abstract": "Breast cancer remains a leading cause of cancer-related mortality among women worldwide, which demands innovations in early detection and diagnostic efficiency. Existing approaches often neglect peri-tumoral contextual features, rely on limited or unrealistic synthetic data, and impose latency bottlenecks in distributed healthcare settings. We propose a reserved-space strategy for Region of Interest (ROI) extraction that achieves 97.5% True Positive Rate (TPR) while preserving contextual features, thereby capturing diagnostically critical tumour margins that rigid bounding boxes overlook. To address data scarcity, we develop an enhanced Generative Adversarial Network (GAN) model incorporating Efficient Multi-scale Attention (EMA) modules and Hinge loss, which generates high-fidelity (15.2 Fréchet Inception Distance (FID)) ROI images that maintain anatomical plausibility in lesions and microcalcification diversity, resolving the over smoothing and pathological irrelevance of conventional GAN architectures. This GAN-augmented dataset improves classification AUC by 10% compared to traditional augmentation methods. Through systematic comparison, we demonstrate that the Swin Transformer outperforms the Convolutional Neural Network (CNN) and standard Vision Transformers (ViT) models in mammography classification with 86.8% Area Under the Curve (AUC). Finally, we design a distributed edge-fog-cloud Internet of Medical Things (IoMT) framework that implements our workflow to mitigate computational bottlenecks in clinical deployment.",
            "source_url": "https:\/\/openalex.org\/W7135345431",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "ResearchSpace (University of Auckland)",
            "source_record_id": "W7135345431",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 29,
            "title": "Convolutional neural networks for mammograph analysis",
            "title_ar": "",
            "title_en": "Convolutional neural networks for mammograph analysis",
            "author": "A. Pereira",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "deep-learning; computer-vision; medical-ai; cnn; image-segmentation; medical-imaging",
            "keywords": "",
            "abstract": "The main theme of this study is the application of advanced artificial intelligence techniques, especially Convolutional Neural Networks (CNN), for early detection of breast cancer. With the increasing importance of automated medical image analysis, this study aims to evaluate the effectiveness of CNN in the analysis of mammograms, focusing particularly on segmentation and anomaly detection. To achieve this objective, images from renowned public databases such as the Digital Database for Screening Mammography (DDSM) and INbreast were analyzed. The study also involves the preprocessing of these images to ensure the quality of the input data and the implementation of different CNN architectures, comparing their performance in terms of accuracy and reliability. The methodology adopted included a comprehensive literature review and the implementation of data augmentation and preprocessing techniques to optimize CNN performance. The data were collected from public databases and renowned scientific journals, ensuring the relevance and timeliness of the information. The analysis of the results showed that CNNs can outperform traditional methods, offering greater accuracy in the segmentation of tumors and other anomalies, promoting faster and more reliable diagnoses. The results show that CNN EfficientNet and InceptionResNetV2 achieved greater accuracy, while CNN MobileNet and MultiResUNet achieved satisfactory accuracy and with lower processing consumption than the other implemented networks.",
            "source_url": "https:\/\/openalex.org\/W7120406163",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)",
            "source_record_id": "W7120406163",
            "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": 45,
            "title": "IMPLEMENTASI MODEL CONVOLUTIONAL RECURRENT NEURAL NETWORK (CRNN) DENGAN BIDIRECTIONAL LONG SHORT-TERM MEMORY (BI-LSTM) UNTUK PENGENALAN EMOSI PADA SUARA",
            "title_ar": "",
            "title_en": "",
            "author": "ADHIRAJASA M. RADITYA",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Lampung University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Indonesia",
            "governorate": "",
            "publication_year": 2025,
            "language": "id",
            "research_domain": "nlp",
            "research_subdomain": "sentiment-analysis",
            "categories": "deep-learning; nlp; cnn; rnn; sentiment-analysis; speech-recognition",
            "keywords": "Speech Emotion Recognition, CRNN, BiLSTM, Log-Mel Spectrogram, Data Augmentation.",
            "abstract": "Pengenalan emosi pada suara merupakan tugas kompleks yang krusial untuk interaksi manusia-mesin. Penelitian ini mengimplementasikan dan mengevaluasi model Convolutional Recurrent Neural Network (CRNN) yang menggabungkan keunggulan Convolutional Neural Network (CNN) untuk ekstraksi fitur spasial dengan Bidirectional Long Short-Term Memory (BiLSTM) untuk analisis dependensi temporal. Model ini dilatih dan diuji menggunakan dataset CREMA-D, yang mencakup enam kelas emosi: marah, jijik, takut, bahagia, netral, dan sedih. Fitur diekstraksi dari sinyal audio menggunakan log-Mel spectrogram untuk merepresentasikan karakteristik suara yang relevan dengan persepsi manusia. Untuk meningkatkan variasi data dan generalisasi model, diterapkan teknik augmentasi data berupa pitch shifting dan time stretching. Hasil evaluasi menunjukkan bahwa model CRNN yang didukung dengan augmentasi data berhasil mencapai akurasi validasi sebesar 68.23%, sebuah peningkatan dari 66.08% yang dicapai oleh model tanpa augmentasi. Model ini menunjukkan performa yang menjanjikan, terutama dalam mengklasifikasikan emosi marah dan netral. Penelitian ini menyimpulkan bahwa arsitektur CRNN dengan BiLSTM efektif untuk tugas pengenalan emosi suara, dan augmentasi data berperan penting dalam meningkatkan kinerjanya. Kata Kunci: Pengenalan Emosi Suara, CRNN, BiLSTM, Log-Mel Spectrogram, Augmentasi Data. Speech emotion recognition is a complex task crucial for human-machine interaction. This study implements and evaluates a Convolutional Recurrent Neural Network (CRNN) model that combines the advantages of a Convolutional Neural Network (CNN) for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) for temporal dependency analysis. The model is trained and tested using the CREMA-D dataset, which includes six emotion classes: anger, disgust, fear, happiness, neutral, and sadness. Features are extracted from the audio signals using log-Mel spectrograms to represent sound characteristics relevant to human perception. To enhance data variation and model generalization, data augmentation techniques such as pitch shifting and time stretching were implemented. The evaluation results show that the CRNN model with data augmentation achieved a validation accuracy of 68.23%, an increase from the 66.08% achieved by the model without augmentation. The model shows promising performance, especially in classifying the anger and neutral emotions. This study concludes that the CRNN architecture with BiLSTM is effective for the task of speech emotion recognition, and that data augmentation plays a crucial role in enhancing its performance. Keywords: Speech Emotion Recognition, CRNN, BiLSTM, Log-Mel Spectrogram, Data Augmentation.",
            "source_url": "https:\/\/openalex.org\/W7126365563",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Digilib Repository Unila (Lampung University)",
            "source_record_id": "W7126365563",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 88,
            "title": "Semi-Supervised Deep Learning using Consistency-Based Methods for Segmentation of Medical Images",
            "title_ar": "",
            "title_en": "Semi-Supervised Deep Learning using Consistency-Based Methods for Segmentation of Medical Images",
            "author": "Axel Rönnberg",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "KTH Royal Institute of Technology",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Sweden",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; ai-applications; self-semi-supervised; predictive-analytics; image-segmentation; medical-imaging; ai-education",
            "keywords": "",
            "abstract": "In radiation therapy, a form of cancer treatment, accurately locating the anatomical structures is required in order to limit the impact on healthy cells. The automatic task of delineating these structures and organs is called segmentation, where each pixel in an image is classified and assigned a label. Recently, deep neural networks have proven to be efficient at automatic medical segmentation. However, deep learning requires large amounts of training data. This is a restricting feature, especially in the medical field due to factors such as patient confidentiality. Nonetheless, the main challenge is not the image data itself but the lack of high-quality annotations. It is thus interesting to investigate methods for semi-supervised learning, where only a subset of the images re- quires annotations. This raises the question if these methods can be acceptable for organ segmentation, and if they will result in an increased performance in comparison to supervised models. A category of semi-supervised methods applies the strategy of encouraging consistency between predictions. Consistency Training and Mean Teacher are two methods in which the network weights are updated in order to minimize the impact of input perturbations such as data augmentations. In addition, the Mean Teacher method trains two models, a Teacher and a Student. The Teacher is updated as an average of consecutive Student models, using Temporal Ensembling. To resolve the question whether semi-supervised learning could be beneficial, the two mentioned techniques are investigated. They are used in training deep neural networks with an U-net architecture to segment the bladder and anorectum in 3D CT images. The results showed signs of promise for Consistency Training and Mean Teacher, with nearly all model configurations having improved segmentations. Results also showed that the methods caused a reduction in performance variance, primarily by limiting poor delineations. With these results in hand, the use of semi-supervised learning should definitely be considered. However, since the segmentation improvement was not repeated in all experiment configurations, more research needs to be done.",
            "source_url": "https:\/\/openalex.org\/W3111652972",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "KTH Publication Database DiVA (KTH Royal Institute of Technology)",
            "source_record_id": "W3111652972",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 94,
            "title": "A Novel Explainable Artificial Intelligence Framework with Improved Learning Mechanisms",
            "title_ar": "",
            "title_en": "A Novel Explainable Artificial Intelligence Framework with Improved Learning Mechanisms",
            "author": "Kabir, Sami",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "نص السجل: «doctoral thesis»",
            "university": "Luleå University of Technology",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Sweden",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "cnn",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; responsible-ai; expert-systems; ai-applications; transfer-learning; self-semi-supervised; predictive-analytics; optimization; cnn; multimodal; xai; fairness; ai-smart-cities",
            "keywords": "",
            "abstract": "Artificial Intelligence (AI) models are increasingly being deployed in various critical domains, such as healthcare, finance, law, and autonomous systems, resulting in remarkable benefits for the society. Due to black-box (sub-symbolic) nature, these AI models do not provide explanation of the predictive output. This lack of explanation results in lack of transparency between human and machine. Such opacity of black-box AI models, particularly deep learning architectures, is a significant concern. To address this concern, Explainable Artificial Intelligence (XAI) has emerged as a vital research area. The aim of XAI is to enhance transparency, trust, and accountability of AI models. Various post-hoc XAI tools explain the outputs of black-box AI models based on training datasets. However, the use of training datasets, rather than domain knowledge, makes such explanations proxy. A biased training dataset may lead to a misleading post-hoc explanation as well. In contrast, an explanation based on domain knowledge will be more trustworthy to an end user. Motivated by this, we propose a novel XAI framework, consisting of Belief Rule Based Expert System (BRBES), to predict output and explain it with reference to domain knowledge. BRBES represents domain knowledge with its rule base. It outperforms other knowledge-driven AI models to handle uncertainty due to ignorance. To improve the accuracy of BRBES, we fine-tune its parameters and structure through evolutionary learning. Moreover, to overcome the scarcity of labeled dataset in this learning mechanism, we integrate semi-supervised and self-supervised learning with BRBES. We explain the output of BRBES with respect to the most influential rule of the rule base of BRBES. Thus, the output of our proposed XAI framework becomes not only accurate, but also explainable. This doctoral thesis delves into the challenges and opportunities surrounding XAI in order to provide a comprehensive understanding of the AI output. It presents a novel XAI framework to provide domain knowledge based energy consumption prediction with improved accuracy, and explain this predictive output in non-technical human language. Then it deals with multi-modal air quality data by integrating deep learning model with BRBES. Moreover, to reduce dependence on labeled data for evolutionary learning, this thesis integrates semi-supervised and self-supervised learning with BRBES. This thesis presents six significant contributions. First, we conduct a Systematic Literature Review (SLR) on XAI using the PRISMA guidelines, delving into the numerous challenges and opportunities of XAI. Extensive research is conducted to explore the definition, terminologies, taxonomy, and application domains of XAI. It highlights various challenges of XAI, such as, no universal definition, trade-off between accuracy and explainability, and lack of standardized evaluation metrics. To address this lack of standardized evaluation metrics, we also propose a unified framework to evaluate XAI. Secondly, we present an innovative explainable BRBES (eBRBES) framework, which offers accurate prediction of building energy consumption phenomenon, while providing insightful explanation and counterfactual based on domain knowledge. As part of eBRBES framework, we also present a novel Belief Rule Based adaptive Balance Determination (BRBaBD) algorithm to assess the optimal balance of the proposed framework between explainability and accuracy. Thirdly, we propose a mathematical model to integrate BRBES with the Convolutional Neural Network (CNN). We leverage the domain knowledge of BRBES, and image data patterns discovered by CNN with this integrated approach. We predict air quality with this integrated model using outdoor ground images and numerical sensor data. Fourth, we integrate two-layer BRBES with CNN to monitor air quality using satellite images, and relevant environmental parameters, such as, cloud, relative humidity, temperature, and wind speed. The two-layer BRBES showcases the strength of BRBES in conducting reasoning across multiple layers. Fifth, we enhance the learning mechanism of BRBES by utilizing the extensive unlabeled energy data, along with limited labeled data. For this purpose, we synthetically generate unlabeled data through weak and strong augmentation. We then pseudo-label these unlabeled data by integrating semi-supervised self-training model with BRBES. By learning from both labeled and pseudo-labeled data, initial BRBES transitions to semi-supervised BRBES. Sixth, to conduct the learning mechanism of BRBES without relying on any labeled data, we integrate self-supervised learning with it. To this effect, we pseudo-label the synthetically generated unlabeled energy data with BRBES in the pretext tasks of self-supervised learning. Then, the initial BRBES learns deeper representation from these pseudo-labeled data, and transitions to self-supervised BRBES.",
            "source_url": "https:\/\/openalex.org\/W7112031890",
            "pdf_url": "https:\/\/ltu.diva-portal.org\/smash\/get\/diva2:2007851\/FULLTEXT01",
            "doi": "",
            "handle": "",
            "repository_name": "DiVA (Luleå University of Technology)",
            "source_record_id": "W7112031890",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 104,
            "title": "Applications of artificial intelligence for explainability and uncertainty quantification for performance-based design and damage classification in civil engineering",
            "title_ar": "",
            "title_en": "Applications of artificial intelligence for explainability and uncertainty quantification for performance-based design and damage classification in civil engineering",
            "author": "Shabbir, Khurram",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Aalto University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Finland",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; responsible-ai; ai-applications; predictive-analytics; transformers; xai; fairness; ai-smart-cities",
            "keywords": "",
            "abstract": "Structural resilience and safety are critical concerns in modern infrastructure, particularly in the face of increasing seismic risks and aging buildings. While advanced artificial intelligence (AI) techniques offer promising solutions for structural design, damage assessment, and retrofitting, the \"black-box\" nature of many AI models limits their trustworthiness and adoption in safety-critical fields. This research integrates explainable AI (XAI) techniques to bridge the gap between complex machine learning models and engineering practice, developing innovative frameworks for enhanced interpretability in civil engineering applications. A primary contribution is Seismo-XAI, a web-based tool that delivers transparent, interpretable insights into building performance under seismic loads, empowering engineers to optimize designs and retrofits. The study also introduces a novel hybrid framework combining microstructure-informed finite element modelling with computer vision to advance damage classification in concrete, synergizing vision transformers' computational efficiency with physics-based finite element analysis. To address data limitations, a synthetic dataset of concrete microstructures was generated using stochastic Monte Carlo augmentation. For uncertainty quantification in seismic assessment, this research employs artificial neural networks with the quality-driven lower upper bound estimation method to establish prediction intervals for long-term ground motion effects. This distribution-free machine learning approach provides both local and global levels probabilistic damage assessment, enhancing reliability in post-earthquake evaluations and early warning systems. Validation through benchmark structures and real-world case studies demonstrates the frameworks’ effectiveness in promoting reliable design practices for seismic resilience and damage assessment. The findings highlight the potential of XAI to transform structural engineering by providing transparent, interpretable, and actionable insights, fostering trust in AI-driven solutions. This research lays the foundation for future advancements in and development of AI applications for structural health monitoring and disaster management for urban infrastructure.",
            "source_url": "https:\/\/openalex.org\/W7115275889",
            "pdf_url": "https:\/\/aaltodoc.aalto.fi\/bitstreams\/22ee9f47-ed26-415f-8ef3-c22a3082d694\/download",
            "doi": "",
            "handle": "",
            "repository_name": "Aaltodoc (Aalto University)",
            "source_record_id": "W7115275889",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 208,
            "title": "Towards Fair and Explainable Machine Learning Modeling in Mental Health",
            "title_ar": "",
            "title_en": "Towards Fair and Explainable Machine Learning Modeling in Mental Health",
            "author": "Gizem Soğancıoğlu",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Utrecht University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Netherlands",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "xai",
            "categories": "machine-learning; medical-ai; responsible-ai; predictive-analytics; xai; fairness",
            "keywords": "",
            "abstract": "As machine learning continues to evolve, its integration into mental health practices promises to provide more effective, efficient, and accessible care. However, addressing ethical considerations remains important to harnessing the full potential of machine learning in mental health. In this thesis, we focus on two challenges of responsible machine learning; fairness and explainability within the mental health domain. Our work involves developing and validating concept-based models to improve explainability in mental health applications, as well as identifying, evaluating, and mitigating bias in AI models within this field. This thesis is organized around five sub-research questions designed to address the main research question: `How can we develop algorithmic fairness and explainability methods to address the specific needs of the mental health domain?' We begin by exploring a range of concept-bottleneck models, demonstrating their potential in affective computing (Chapter 2) and mental health applications (Chapter 3). These findings motivate future research to integrate higher-level, clinically validated concepts into complex models, enabling clinicians to justify and correct model predictions. Despite promising results, we identify gender bias in these models. To address this, we further investigate existing gender biases in training datasets, pre-trained word embeddings, and machine learning models in the mental health domain (Chapter 4). We demonstrate how even accurate prevalence rate differences in training data can negatively impact downstream models and recommend a counterfactual data augmentation approach as a bias mitigation strategy. Next, we seek to bridge the gap between clinicians and mathematical fairness objectives by conducting interviews with clinicians, showing how clinical insights can inform the selection of fairness measures for real-world applications (Chapter 5). Based on their input, we introduce a gain-based model selection method that prioritizes the performance of individual groups over parity-based fairness measures. Finally, we present new bias mitigation techniques, ProxyMute and ProxyROAR, which automatically remove sensitive information (e.g., gender-related features) from the feature space using explainability methods (Chapter 6). We show that these approaches provide a viable alternative when dictionary-based methods are not suitable. Collectively, these studies make a significant contribution by highlighting both the potential and the challenges of applying fairness and explainability methods in the mental health domain, while also proposing novel approaches to address the limitations of existing methods to ensure the responsible use of AI models in this field. All the codes of experiments are made publicly available to speed up the research in this field.",
            "source_url": "https:\/\/openalex.org\/W4409017205",
            "pdf_url": "",
            "doi": "10.33540\/2843",
            "handle": "",
            "repository_name": "Utrecht University Repository (Utrecht University)",
            "source_record_id": "W4409017205",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:47",
            "updated_at": "2026-11-15 16:52:47"
        },
        {
            "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": 285,
            "title": "Automatic Detection and Verification System for Arabic Rumor News on Twitter",
            "title_ar": "",
            "title_en": "Automatic Detection and Verification System for Arabic Rumor News on Twitter",
            "author": "Sami Karali",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "نص السجل: «doctoral research»",
            "university": "University of Technology Sydney",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Australia",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; nlp; ai-applications; cnn; rnn; llm; arabic-nlp; ai-education",
            "keywords": "",
            "abstract": "anguage models have been extensively studied and applied in various fields in recent years.However, the majority of the language use models are designed for and perform significantly better in English compared to other languages, such as Arabic.The differences between English and Arabic in terms of grammar, writing, and word-forming structures pose significant challenges in applying English-based language models to Arabic content.Therefore, there is a critical need to develop and refine models and methodologies that can effectively process Arabic content.This research aims to address the gaps in Arabic language models by developing innovative machine learning (ML) and natural language processing (NLP) methodologies.We apply the developed model to Arabic rumor detection on Twitter to test its effectiveness.To achieve this, the research is divided into three fundamental phases: 1) Efficiently collecting and pre-processing a comprehensive dataset of Arabic news tweets; 2) The refinement of ML models through an enhanced Convolutional Neural Network (ECNN) equipped with N-gram feature maps for accurate rumor identification; 3) The augmentation of decision-making precision in rumor verification via sophisticated ensemble learning techniques.In the first phase, the research meticulously develops a methodology for the collection and pre-processing of Arabic news tweets, aiming to establish a dataset optimized for rumor detection analysis.Leveraging a blend of automated and manual processes, the research navigates the intricacies of the Arabic language, enhancing the dataset's quality for ML applications.This foundational phase ensures removing irrelevant data and normalizing text, setting a precedent for accuracy in subsequent detection tasks.The second phase is to develop an Enhanced Convolutional Neural Network (ECNN) model, which incorporates N-gram feature maps for a deeper linguistic analysis of tweets.This innovative ECNN model, designed specifically for the Arabic language, marks a significant departure from traditional rumor detection models by harnessing the power of spatial feature extraction alongside the contextual insights provided by N-gram analysis.Empirical results underscore the ECNN model's superior performance, demonstrating a marked improvement in detecting and classifying rumors with heightened accuracy and efficiency.The culmination of the study explores the efficacy of ensemble learning methods in enhancing the robustness and accuracy of rumor detection systems.By synergizing the ECNN model with Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU) networks within a stacked ensemble framework, the iii research pioneers a composite approach that significantly outstrips the capabilities of singular models.This innovation results in a state-of-the-art system for rumor verification that outperforms accuracy in identifying rumors, as demonstrated by empirical testing and analysis.This research contributes to bridging the gap between English-centric language models and Arabic language processing, demonstrating the importance of tailored approaches for different languages in the field of ML and NLP.These contributions signify a monumental step forward in the field of Arabic NLP and ML and offer practical solutions for the real-world challenge of rumor proliferation on social media platforms, ultimately fostering a more reliable digital environment for Arabic-speaking communities.n the journey that has been my doctoral research, I have been fortunate to be guided by individuals whose impact has been profound and far-reaching.At the forefront of these cherished relationships is Prof. CT Lin, whose guidance and support have been the beacon that navigated me through the complexities and challenges inherent in this rigorous academic endeavor.Prof. Lin's readiness to engage, discuss, and explore solutions with me, irrespective of the time or day, has been a testament to his dedication to academia and the growth of his students.His wisdom, coupled with an unwavering belief in my potential, provided me with the confidence to pursue this project with vigor and determination.To Prof.",
            "source_url": "https:\/\/openalex.org\/W7225354344",
            "pdf_url": "https:\/\/opus.lib.uts.edu.au\/bitstream\/10453\/187339\/1\/thesis.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "OPUS - Open Publications of UTS Scholars (University of Technology Sydney)",
            "source_record_id": "W7225354344",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "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": 408,
            "title": "Inductive and Transductive Learning with Vision-Language Models in Low-Shot Regimes",
            "title_ar": "",
            "title_en": "Inductive and Transductive Learning with Vision-Language Models in Low-Shot Regimes",
            "author": "Maxime Zanella",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Belgium",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; transfer-learning; few-zero-shot; predictive-analytics; multimodal; llm",
            "keywords": "",
            "abstract": "Vision-Language Models (VLMs) have revolutionized open-vocabulary recognition, yet adapting them to specialized domains under data-scarce conditions remains a significant challenge. This thesis investigates efficient strategies to bridge the gap between inductive fine-tuning and transductive inference, focusing on minimizing supervision and computational costs. We first address inductive few-shot learning with CLIP-LoRA, a parameter-efficient fine-tuning method. By injecting trainable low-rank matrices into the encoder, it outperforms existing approaches while eliminating dataset-specific hyperparameter tuning. For scenarios restricted to single-sample inference, we propose MTA (MeanShift for Test-time Augmentation). Formulated as a robust variation of the MeanShift algorithm, this training-free method refines predictions through iterative mode-seeking and automatic importance weighting of augmented views. Expanding into the transductive paradigm, we introduce TransCLIP. This framework explicitly models the underlying structure of unlabeled test batches by fitting a Gaussian Mixture Model (GMM), constrained by a text-driven Kullback-Leibler (KL) regularization term. This dual objective dynamically aligns visual statistics with textual priors, achieving substantial gains in both zero-shot and few-shot settings. Finally, to address realistic deployment challenges, we propose StatA (Statistical Anchor). We demonstrate that existing transductive methods fail under non-i.i.d. data streams and introduce a regularization technique based on the KL divergence with respect to initial text priors. Collectively, this work provides a suite of transparent, low-compute algorithms that, through the use of fixed hyperparameters, ensure operational simplicity and robust performance across challenging and diverse benchmarks.",
            "source_url": "https:\/\/openalex.org\/W7134152075",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B))",
            "source_record_id": "W7134152075",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 409,
            "title": "Zero\/Few-Shot Dark Kinase-Phosphosite Associatıon Predictıon With Biologically Grounded Data Augmentation",
            "title_ar": "",
            "title_en": "Zero\/Few-Shot Dark Kinase-Phosphosite Associatıon Predictıon With Biologically Grounded Data Augmentation",
            "author": "Mert Pekey",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Turkey",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "transfer-learning",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; responsible-ai; transfer-learning; few-zero-shot; predictive-analytics",
            "keywords": "",
            "abstract": "Protein phosphorylation, a fundamental cellular process mediated by kinases, iscrucial for signaling, and its dysregulation is implicated in numerous human diseases.A significant challenge persists in identifying substrate phosphosites for the vastnumber of understudied ’dark’ kinases, for which conventional supervised machinelearning methods are ineffective due to data scarcity. To address this gap, thisthesis develops a zero- and few-shot learning framework and introduces biologicallygrounded data augmentation strategies, all evaluated on the DARKIN benchmark.We introduce two novel deep learning architectures: DARKIN-FT, a compatibilitybasedmodel that enhances performance through end-to-end fine-tuning of phosphositeencoder, and DARKIN-Interact, a binary classification model that directlycaptures kinase–substrate interactions via joint attention over sequence pairs. Thecentral contribution is a systematic investigation into biologically grounded dataaugmentation, evaluating three distinct strategies: (i) kinase-conditional phosphositegeneration via a fine-tuned ProGen2 model, (ii) weak supervision using predictionsfrom the Kinase Substrate Specificity Atlas (KSSA), and (iii) augmentationwith homologous sequences. Our results demonstrate that DARKIN-FT and DARKIN-Interact significantly outperformexisting baselines on the DARKIN benchmark. The investigation intodata augmentation yielded mixed results: while kinase conditional generation withProGen2 and weak labeling with KSSA degraded the performance, augmentationwith homologous sequences improved the Macro Average Precision of the DARKINInteractmodel. While the results are promising, challenges persist in disambiguatingkinases with high sequence similarity.Overall, this thesis establishes a framework for kinase–phosphosite interaction predictionin low-data regimes and provides valuable insights into the strengths andlimitations of data augmentation in the dark kinase-phosphosite association task.",
            "source_url": "https:\/\/openalex.org\/W7124522292",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Sabanci University",
            "source_record_id": "W7124522292",
            "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": 471,
            "title": "Enhancing Plant Disease Detection in Smart Agriculture Using Deep Learning Models and Advanced Data Augmentation Techniques",
            "title_ar": "",
            "title_en": "Enhancing Plant Disease Detection in Smart Agriculture Using Deep Learning Models and Advanced Data Augmentation Techniques",
            "author": "Nurbol Mukhametzhan",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Nazarbayev University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Kazakhstan",
            "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; few-zero-shot; cnn; ai-agriculture",
            "keywords": "",
            "abstract": "Deep learning for automatic detection of plant diseases has emerged as an innova- tive method to address agricultural productivity and food security issues. While deep CNNs have achieved near-ceiling performance on benchmark datasets under controlled conditions, the results do not necessarily translate to real-world agricultural environments. The reason for this is domain shift: models are typically trained on clean laboratory images. Field images include background clutter, illumination variations, occlusions, and inconsistent capture conditions [1, 2, 10, 11]. This thesis investigates cross-domain plant disease classification under a controlled- to-field setting using transfer-learned CNN architectures, namely EfficientNet-B0, MobileNetV3-Large, and ResNet-50 [21, 22, 20]. PlantVillage is used as the source domain for training, while PlantDoc is used as the target domain for evaluation and adaptation. The study evaluates a 12-class controlled-to-field transfer task using a harmonized subset of overlapping classes from both datasets. The implemented framework compares four training pipelines: P1, which uses preprocessing only and no augmentation; P2, which applies basic geometric and photometric augmentation; P3, which applies stronger environmental augmentation together with mixed-image regularization using MixUp and CutMix; and P4, which serves as an ablation study by applying P3’s environmental transforms without image mixing. [24, 26, 27]. The results show that source-domain validation performance does not translate into strong field performance. In the zero-shot cross-domain setting, where models are trained on PlantVillage and evaluated directly on PlantDoc without target-domain training, the best configuration reaches only 24.84% accuracy on the filtered PlantDoc FULL evaluation set of 1405 images, confirming a substantial lab-to-field generalization gap. When target-domain supervision is introduced through fine-tuning on the filtered PlantDoc training split and evaluation on the untouched filtered PlantDoc test split, performance improves substantially, reaching up to 59.32% accuracy and 0.5734 macro-F1. The results further show that basic augmentation is more reliable than the most aggressive augmentation setting for zero-shot transfer, while supervised fine-tuning on target-domain data provides the largest reduction in the deployment gap. Furthermore, a target-domain data efficiency ablation reveals that supervised adaptation scales logarithmically. Models recover the majority of their fine-tuned performance using only a fraction of the target dataset, demonstrating that bridging the lab-to-field gap does not strictly require massive field-collected datasets. Overall, this research studies plant disease recognition using field data. It shows that while domain adaptation improves robustness and makes models more deployable, augmenting the source training data alone is not sufficient to solve the controlled- to-field generalization problem.",
            "source_url": "https:\/\/openalex.org\/W7199181336",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Nazarbayev University Repository (Nazarbayev University)",
            "source_record_id": "W7199181336",
            "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": 473,
            "title": "Plant Disease Detection and Classification Using Deep Learning Techniques",
            "title_ar": "",
            "title_en": "Plant Disease Detection and Classification Using Deep Learning Techniques",
            "author": "Mazhar Iqbal",
            "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": "cnn",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; ai-applications; transfer-learning; cnn; ai-agriculture",
            "keywords": "",
            "abstract": "The early and accurate detection of plant diseases is very important in protecting crop yield and ensuring food security.This thesis is going to explore how deep learning methods, especially Convolutional Neural Networks (CNNs) and ResNet-50, can help identify and classify diseases in Tomato, Potato, and Pepper plants.A dataset of over 38,000 images of both healthy and diseased leaf samples were collected.Different data augmentation techniques like rotation, shearing, zooming, and flipping were used to increase the efficiency of models and balance the number of images in each class.This research looks at how well a custom CNN and a fine-tuned ResNet-50 model perform on the three crops by checking their training, validation, and test results.The result shows that the CNN model's performance was reasonably well, and it achieved test accuracy of 94.12% (Tomato), 92.83% (Potato), and 91.98% (Pepper), while the ResNet-50 model has shown much better results, with an accuracy score of 99.37% and has shown a strong performance across all datasets.Diseases like Late Blight and Yellow Leaf Curl Virus, that are very difficult to visually distinguish but ResNet-50 was very precise at identifying these diseases.This work shows how deep learning is very effective in plant disease detection but also explores that these models could be used in real farming environments to help farmers take quick action and reduce crop losses.By decreasing dependence on manual inspection and helping in early disease detection, the research helps to support greener, technology-driven agriculture.",
            "source_url": "https:\/\/openalex.org\/W7215253019",
            "pdf_url": "https:\/\/erepo.uef.fi\/bitstreams\/396f0104-78e4-40da-ba0b-543e36d34d00\/download",
            "doi": "",
            "handle": "",
            "repository_name": "UEF eRepo (University of Eastern Finland)",
            "source_record_id": "W7215253019",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 482,
            "title": "Plant recognition, detection, and counting with deep learning",
            "title_ar": "",
            "title_en": "Plant recognition, detection, and counting with deep learning",
            "author": "Pornntiwa Pawara",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Groningen \/ Centre for Information Technology",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Netherlands",
            "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; predictive-analytics; image-classification; ai-education; ai-agriculture",
            "keywords": "",
            "abstract": "In agricultural and farm management, plant recognition, plant detection, and plant counting systems are crucial. We can apply these tasks to several applications, for example, plant disease detection, weed detection, fruit harvest system, and plant species identification. Plants can be identified by looking at their most discriminating parts, such as a leaf, fruit, flower, bark, and the overall plant, by considering attributes as shape, size, or color. However, the identification of plant species from field observation can be complicated, time-consuming, and requires specialized expertise. Computer vision and machine-learning techniques have become ubiquitous and are invaluable to overcome problems with plant recognition in research. Although these techniques have been of great help, image-based plant recognition is still a challenge. There are several obstacles, such as considerable species diversity, intra-class dissimilarity, inter-class similarity, and blurred resource images. Recently, the emerging of deep learning has brought substantial advances in image classification. Deep learning architectures can learn from images and notably increase their predictive accuracy. This thesis provides various techniques, including data augmentation and classification schemes, to improve plant recognition, plant detection, and plant counting system.",
            "source_url": "https:\/\/openalex.org\/W3118912755",
            "pdf_url": "https:\/\/pure.rug.nl\/ws\/files\/156115980\/Complete_thesis.pdf",
            "doi": "10.33612\/diss.156115978",
            "handle": "",
            "repository_name": "University of Groningen research database (University of Groningen \/ Centre for Information Technology)",
            "source_record_id": "W3118912755",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 486,
            "title": "Deep learning approaches for yield prediction and crop disease recognition",
            "title_ar": "",
            "title_en": "Deep learning approaches for yield prediction and crop disease recognition",
            "author": "Luning Bi",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Iowa State University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2022,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; generative-ai; medical-ai; ai-applications; predictive-analytics; optimization; cnn; rnn; transformers; gan; ai-agriculture",
            "keywords": "",
            "abstract": "The increase of the world population has brought significant challenges to the agriculture production system. Although mechanization has been realized in agriculture, many tasks (e.g., breeding, field inspection) are still labor-intensive and time-consuming. Therefore an automatic and intelligent solution is needed for the advancement of agricultural production. During this process, the biggest challenge is how to teach computers to understand the concepts in the real world. For example, an experienced expert can easily determine whether a plant is diseased or healthy. However, this may be challenging for the computer. Thus, the motivation of this dissertation study is to tackle these challenges in precision agriculture. This dissertation consists of four papers that propose different deep learning methods for the most challenging problems in agriculture. In the first paper, a genetic algorithm (GA)-assisted deep neural network was built for yield prediction using genetic information and environmental factors. In the global search phase, the GA was introduced to help determine the best initial weights of the neural network. In the local phase, random perturbation was used to avoid the local optimum. By using the proposed method, the root mean square error can be reduced by up to 10%. In the second paper, we proposed a generative adversarial network (GAN)-based approach to generate additional images for the classification of plant species and diseases using limited data. CNN was used as the basic network to classify species and diseases. GAN and label smoothing regularization (LSR) were combined to generate additional training images. Regular data augmentation techniques were also used to expand the dataset. The results showed that compared with using the real dataset only, the proposed method can improve the prediction accuracy by 6%. In the third paper, the potential of using satellite imagery for plant disease detection was explored. A gated recurrent units (GRU)-based model was presented for early detection of soybean sudden death syndrome (SDS) through time-series satellite imagery. The results showed that, compared to XGBoost and fully connected deep neural network (FCDNN), the GRU-based can improve the overall prediction accuracy by 7%. In addition, the proposed method can also be adapted to predict the future development of SDS. In the fourth paper, a transformer-based approach was proposed for soybean yield prediction using time-series camera images and seed treatments information. First, a vision transformer (ViT) base model was designed to extract features from the images. Then another transformer-based model was established to predict the yield using the time-series features. A case study was been conducted using a data set that was collected during the 2020 soybean-growing seasons in Canada. The experiment results show that compared to non-time series prediction and other baseline models, the proposed approach can reduce the mean squared error by 25%-40%. In conclusion, this dissertation aims to apply different state-of-art deep learning methods in agriculture. The study covers different topics, which range from yield prediction, species classification, to plant disease classification and prediction. At the model level, the application of linear models, tree-based methods, fully connected neural networks, convolutional neural networks, time-series models and transformers to different tasks have been investigated. In terms of the learning type, both unsupervised learning and supervised learning have been utilized. The experimental results have shown that appropriate deep learning methods can achieve better performance than traditional methods on specific tasks. Based on our work, more applications of deep learning techniques can be developed in the future.",
            "source_url": "https:\/\/openalex.org\/W7135318077",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Iowa State University Digital Repository (Iowa State University)",
            "source_record_id": "W7135318077",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 556,
            "title": "Data Augmentation methods in natural language processing.",
            "title_ar": "",
            "title_en": "",
            "author": "Taynan Maier Ferreira",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Universidade de São Paulo",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Brazil",
            "governorate": "",
            "publication_year": 2021,
            "language": "pt",
            "research_domain": "nlp",
            "research_subdomain": "sentiment-analysis",
            "categories": "nlp; sentiment-analysis",
            "keywords": "",
            "abstract": "Métodos de aumento de dados (AD) -uma família de técnicas desenhada para a geração de dados de treino sintéticos -têm demonstrado resultados notáveis em diversas tarefas de Aprendizado Profundo e Aprendizado de Máquina.Apesar de sua adoção ampla e bem-sucedida dentro da comunidade de visão computacional, técnicas de AD desenhados para tarefas de Processamento de Linguagem Natural (PLN) têm demonstrado avanço muito mais lento e limitado sucesso em ganho de desempenho.Como consequência, com a exceção da adoção de Back-Translation em tarefas de tradução, essas técnicas não tem sido exploradas tão profundamente e de forma ampla pela comunidade de PLN.Não há uma visão unificada ou análise comparativa entre os vários métodos de AD disponíveis.Além disso, ainda não se tem um entendimento prático adequado sobre o relacionamento entre AD e diversos outros aspectos importantes do desenho de um modelo, como dados de treino e parâmetros de regularização.Nesse trabalho, realizamos um profundo estudo de técnicas de AD em PLN, comparando seus desempenhos relativos sob diferentes cenários em tarefas de Análise de Sentimentos.Também propomos Deep Back-Translation, uma nova técnica de AD para PLN.Nós realizamos uma análise qualitativa e quantitativa do dado sintético, avaliamos seu ganho de desempenho e comparamos todos esses aspectos com procedimentos prévios de AD.",
            "source_url": "https:\/\/openalex.org\/W3214297092",
            "pdf_url": "http:\/\/www.teses.usp.br\/teses\/disponiveis\/3\/3141\/tde-04112021-162156\/publico\/TaynanMaierFerreiraCorr21.pdf",
            "doi": "10.11606\/d.3.2021.tde-04112021-162156",
            "handle": "",
            "repository_name": "Digital Library of Theses and Dissertations (Universidade de São Paulo)",
            "source_record_id": "W3214297092",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 568,
            "title": "Improving Human Behavior Understanding with Semi-supervised Learning",
            "title_ar": "",
            "title_en": "Improving Human Behavior Understanding with Semi-supervised Learning",
            "author": "Bruno Manuel Degardin",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Portugal",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; generative-ai; responsible-ai; self-semi-supervised; cnn; transformers; multimodal; video-analysis; gan; diffusion; fairness",
            "keywords": "",
            "abstract": "Recent advancements in Computer Vision (CV) and Machine Learning (ML) have fundamentally revolutionized the field of human behaviour understanding, enabling intelligent systems to move beyond simple motion detection to the interpretation of complex, semantic actions from vast streams of visual data. This paradigm shift has been driven by the exponential growth of Deep Learning algorithms, particularly the evolution from 3D Convolutional Neural Networks (3D CNNs) to modern Vision Transformers (ViTs) , which have achieved remarkable success in modeling long-range spatiotemporal dependencies in RGB videos and multimodal signals. However, despite their impressive performance on controlled benchmarks, the deployment of these pixel-based models in real-world scenarios remains heavily constrained. Their reliance on high-dimensional visual data often incurs prohibitive computational costs that hinder real-time application on edge devices. Furthermore, these methods exhibit significant sensitivity to background clutter and viewpoint variations , and the processing of raw video raises critical privacy concerns by capturing unnecessary appearance details such as identity and clothing. Maximizing the potential of this modality presents a significant set of challenges that hinder widespread deployment. The heavy reliance on massive, high-quality annotated datasets creates a prohibitive bottleneck for supervised learning, while existing generative models used for data augmentation often lack physical plausibility or controllability. Furthermore, self-supervised methods borrowed from video domains frequently fail to capture the fine-grained dynamics of skeletal motion, and current evaluation metrics for synthetic data struggle to distinguish between realistic kinematics and artifacts. Addressing these limitations requires a fundamental shift toward more label-efficient, physically aware, and generative approaches to behaviour analysis. In this thesis, we proposed a comprehensive suite of novel solutions to mitigate these problems by exploiting semi-supervised and self-supervised learning paradigms, as well as advanced generative modeling. First, we addressed the limitations of temporal reasoning in Graph Convolutional Networks (GCNs) by proposing REGINA, a reasoning- augmented architecture. This method injects explicit temporal self-similarity cues into the network through a learnable temporal adjacency matrix, allowing the model to adaptively optimize its receptive fields to capture long-range dependencies that standard convolutions often miss. Addressing data scarcity, we proposed Kinetic-GAN, a generative adversarial network that scales action conditioning by an order of magnitude over prior works. By generating actions directly from a disentangled latent space using a mapping network and stochastic noise injection, it synthesizes diverse, high-fidelity global body movements across more than 100 action classes. We further advanced representation learning without labels through ATOM, a self-supervised strategy that leverages atomic motion representation learning. By decomposing actions into short, fine-grained primitives and training the backbone to recover their temporal order, ATOM learns robust features from the intrinsic structure of motion, transferring effectively to supervised tasks without the computational burden of heavy reconstruction heads. To bridge the gap between generation and recognition, we developed an intrinsic, kinematics-aware quality assessment framework. Recognizing that conventional distribution metrics fail to capture physical validity, this framework utilizes per-sample kinematic indicators within a weaklysupervised discriminator to iteratively filter synthetic samples, ensuring only physically plausible data is used to boost downstream performance. Finally, pushing the boundaries of controllable synthesis, we proposed GLDM, a Spatiotemporal Graph Latent Diffusion Model. GLDM projects skeleton sequences into a compact, graph-aligned latent space and performs diffusion with graph-aware updates. Crucially, by integrating cross-attention mechanisms, GLDM enables precise multi-modal conditioning, allowing generation to be guided not just by class labels but also by natural language prompts, achieving generalization beyond training data, unconstrained temporal flexibility and solving the mode collapse issues inherent to adversarial approaches. Results obtained by the proposed methods show that it is possible to improve HBU systems regarding label efficiency, generative controllability, and physical plausibility, while still obtaining state-of-the-art results. All proposed methods were evaluated on several large-scale benchmarks, demonstrating that robust behaviour understanding can be achieved with significantly reduced reliance on manual annotation.",
            "source_url": "https:\/\/openalex.org\/W7225277943",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)",
            "source_record_id": "W7225277943",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 583,
            "title": "Semi-supervised learning methods for unsupervised domain adaptation in medical imaging segmentation",
            "title_ar": "",
            "title_en": "Semi-supervised learning methods for unsupervised domain adaptation in medical imaging segmentation",
            "author": "Pedro L. Ballester",
            "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; computer-vision; medical-ai; transfer-learning; self-semi-supervised; predictive-analytics; image-segmentation; medical-imaging",
            "keywords": "",
            "abstract": "Machine learning applications make several assumptions regarding the scenario where they are employed. One common assumption is that data distribution in the test environment follows the same distribution of the training set. This assumption is systematically broken in most real-world scenarios; the difference between these distributions is commonly known as domain shift. Unsupervised domain adaptation aims at suppressing this problem by leveraging knowledge with unlabeled data from the test environment. One of the most sensitive fields for domain shift is medical imaging. Due to the heterogeneity in data distributions from scanners, models tend to vary in predictive performance when dealing with images from scanners with no examples in the training set. We propose two contributions in this work. First, we introduce the use of self-ensembling domain adaptation in the field of medical imaging segmentation in a spinal cord grey matter segmentation task. Next, based on the success of self-ensembling, we adapt two other recent work from the semi-supervised learning literature to the same task, namely, unsupervised data augmentation and MixMatch. We conduct ablation studies and other experiments in order to understand the behavior of each method and compare their best results. The results show improvements over training models in a supervised learning fashion and demonstrate that recent semi-supervised learning methods are promising for domain adaptation in medical imaging segmentation.",
            "source_url": "https:\/\/openalex.org\/W2992030155",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)",
            "source_record_id": "W2992030155",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 584,
            "title": "Semi-Supervised Learning with Unlabeled data: from Centralized to Distributed Systems",
            "title_ar": "",
            "title_en": "Semi-Supervised Learning with Unlabeled data: from Centralized to Distributed Systems",
            "author": "Nan Yang",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "The University of Sydney",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Australia",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "image-classification",
            "categories": "machine-learning; deep-learning; computer-vision; responsible-ai; self-semi-supervised; cnn; image-classification; federated-learning; fairness",
            "keywords": "",
            "abstract": "The rapid increase in data generated by edge devices and IoT technologies demands efficient management solutions, especially in terms of cost and infrastructure. Key challenges include expensive data labeling, requiring significant human resources, and ensuring data privacy and security, with the risk of information leakage during transmission. The limited availability of labeled data versus the exponential growth of new data presents challenges for maintaining accuracy and efficiency in data-driven models. High costs of data annotation, especially involving subject-matter experts, limit model training effectiveness. Privacy concerns are heightened due to edge devices' interaction with sensitive user data, making the affordability of data labeling and data privacy protection at the edge crucial issues. To tackle these challenges, we proposed Data Augmentation Random Padding to increase effective data for model training in CNNs, enhancing image classification accuracy. Despite limitations, we developed Semi-Supervised Learning (SSL) method \"AdaptMatch\" to utilize a large amount of unlabeled data and a small number of labeled data in centralized learning, improving learning speed and reducing label bias. To address the inadequacies of centralized data learning, we introduced a decentralized SSL method, Federated Incremental Learning (FedIL), for learning on edge devices while protecting privacy. However, FedIL's lower training efficiency and struggles with data imbalance led to the development of Federated Masked Autoencoder (FedMAE), which is also a decentralized semi-supervised learning method based on self-supervised learning. FedMAE enables asynchronous training of large-scale unlabeled images in federated learning, outperforming existing methods in handling highly imbalanced data.",
            "source_url": "https:\/\/openalex.org\/W7126832066",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "The Sydney eScholarship Repository (The University of Sydney)",
            "source_record_id": "W7126832066",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 590,
            "title": "Discriminator-driven diffusion generative adversarial network for synthetic medical image generation",
            "title_ar": "",
            "title_en": "Discriminator-driven diffusion generative adversarial network for synthetic medical image generation",
            "author": "Dennis Chia Yin Lim",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Australia",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "deep-learning; computer-vision; generative-ai; medical-ai; gan; medical-imaging",
            "keywords": "",
            "abstract": "This research project addresses the significant challenge of class imbalance in medical deep learning classification models, particularly when the abnormal class is underrepresented. Class imbalance can severely affect the classification performance of deep learning models, potentially leading to patient misdiagnosis and impeding clinician trust in AI adoption. In healthcare, class imbalance arises due to various factors, including the rarity of diseases or medical scenarios and data insufficiency for specific classes within large datasets. Existing solutions, such as traditional data augmentation and Generative Adversarial Networks (GANs) like DCGAN, as well as Conditional GANs like Pix2Pix and Stable Diffusion, have attempted to mitigate this issue, but with limitations.",
            "source_url": "https:\/\/openalex.org\/W7131907591",
            "pdf_url": "",
            "doi": "10.25916\/sut.31368169",
            "handle": "",
            "repository_name": "Swinburne figshare (Swinburne University of Technology)",
            "source_record_id": "W7131907591",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 592,
            "title": "Towards data efficient generative models",
            "title_ar": "",
            "title_en": "Towards data efficient generative models",
            "author": "Zhaoyu Zhang",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Queen's University Belfast",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "gan",
            "categories": "machine-learning; computer-vision; generative-ai; gan; diffusion",
            "keywords": "",
            "abstract": "The past decade has seen significant advancements in generative models. As one of the most fundamental machine learning and computer vision tasks, generative models aim to produce realistic-looking synthetic samples by learning from real samples. However, training generative models from scratch commonly requires large amounts of data, which can be costly, time-consuming, or even impractical to collect and clean for specific domains. To address this, data-efficient generative models, which are designed to train with limited data from scratch, have gained significant attention. In this thesis, we focus on the theory and algorithms for training data-efficient generative models from scratch using two widely used generative models, i.e., generative adversarial networks (GANs) and diffusion models (DMs). For GANs, we address the challenges in data-efficient training from three different theoretical perspectives: the unfair min-max game, the overfitting of discriminator ($D$) and the leaking of augmentations problem. For DMs, we address the data efficiency challenge by better minimizing the total denoising score matching error during training. Firstly, we apply information game theory to analyze the GANs' min-max game and unveil a novel perspective on GAN training: the min-max game in existing GANs training is unfair. Based on this, we present a novel GAN called Information Gap GAN (IGGAN) to enhance the min-max game in GANs training. Specifically, IGGAN comprises a generator ($G$) and two discriminators ($D_1$ and $D_2$), each applying distinct data augmentation (DA) techniques. The information gap caused by various DA methods between $D_1$ and $D_2$ can alter the information received by each player in the min-max game, leading to incomplete information for all three players—$G$, $D_1$, and $D_2$—in IGGAN. As a result, IGGAN outperforms other existing methods, achieving better Inception Scores and lower Fréchet Inception Distances. Secondly we introduce a straightforward yet effective approach named Dual Adaptive Noise Injection (DANI) to mitigate the overfitting of $D$ in DE-GANs training. Specifically, DANI incorporates two adaptive strategies: adaptive injection probability and adaptive noise strength. By dynamically adjusting these factors, DANI effectively alleviates the overfitting of $D$. The strong performance and generalization ability of DANI demonstrate its effectiveness in improving GAN training under limited data conditions. Thirdly, we first illustrate that applying Data augmentation (DA) in DE-GANs can introduce out-of-distribution samples, leading to the undesirable leaking of augmentation issue in DE-GANs training. To address this, we present a straightforward yet powerful technique named Adaptive Negative Data Augmentation (ANDA) for DE-GANs. Specifically, ANDA enhances the augmented distribution of generated data by incorporating the augmented distribution of negative real data, which is generated by applying Negative Data Augmentation (NDA) to real data. This approach allows potential leaking samples to be presented as ``fake” instances to the discriminator in an adaptive manner, preventing the generator ($G$) from learning these samples and improving overall performance. We demonstrate that ANDA is effective in mitigating the leaking of augmentation issue. Finally, we focus on training diffusion models with limited data. We present a novel theoretical insight for diffusion models that two factors, i.e., the denoiser function hypothesis space and the number of training samples, can affect the denoising score matching error of all training samples. Based on this theoretical insight, it is clearly evident that the total denoising score matching error is hard to be minimized within the denoiser function hypothesis space of existing methods when training diffusion models with limited data. To address this, we design a new diffusion model with limited data called Limited Data Diffusion (LD-Diffusion), which consists of two main components: a compressing model and a novel mixed augmentation with fixed probability (MAFP) strategy. Comprehensive experiments show that LD-Diffusion greatly enhances the training of diffusion models with limited data, achieving state-of-the-art performance compared to other diffusion models.",
            "source_url": "https:\/\/openalex.org\/W7215036991",
            "pdf_url": "",
            "doi": "10.17034\/32826059",
            "handle": "",
            "repository_name": "Research Portal (Queen's University Belfast)",
            "source_record_id": "W7215036991",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 605,
            "title": "Synthetic Ultrasound Video Generation with Generative Adversarial Networks",
            "title_ar": "",
            "title_en": "Synthetic Ultrasound Video Generation with Generative Adversarial Networks",
            "author": "Daniil Kulik",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Canada",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; generative-ai; medical-ai; cnn; video-analysis; gan; medical-imaging",
            "keywords": "",
            "abstract": "Ultrasound is a non-invasive, radiation-free portable imaging modality that offers real-time diagnostics in different clinical settings.Ultrasound video analysis can benefit from the rise of AI-powered applications in healthcare.However, access to ultrasound data remains the main challenge for the development of state-of-the-art machine learning models.Synthetic data generation can provide various benefits to ultrasound imaging analysis.Namely, generating ultrasound videos with specific characteristics allows for better training and testing of machine learning models.This work proposes a generative adversarial network for conditional ultrasound video generation.We conduct a thorough quantitative and qualitative evaluation of the network.Additionally, we show the added value of using the synthetic video for data augmentation in a downstream task.Extensive experiments on the EchoNet-Dynamic dataset demonstrate that the proposed model achieves an FID score of 126 and an FVD score of 233 and can be used in data augmentation tasks in small data scenarios.Contents 7 Conclusion and Future Work 70 vi List of Tables 3.1 Prior work in ultrasound image and video generation with GANs. .5.1 Configuration of the image discriminator. . . . . . . . . . . . . . . .5.2 Configuration of the video discriminator. . . . . . . . . . . . . . . .5.3 Configuration of the transposed convolutional generator. . . . . . .5.4 Configuration of the subpixel generator. . . . . . .",
            "source_url": "https:\/\/openalex.org\/W4389205759",
            "pdf_url": "https:\/\/repository.library.carleton.ca\/downloads\/w0892c38h",
            "doi": "10.22215\/etd\/2023-15790",
            "handle": "",
            "repository_name": "Carleton University's Institutional Repository (MacOdrum Library, Carleton University)",
            "source_record_id": "W4389205759",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 613,
            "title": "Dual-Attention Generative Adversarial Network and Flame and Smoke Analysis",
            "title_ar": "",
            "title_en": "Dual-Attention Generative Adversarial Network and Flame and Smoke Analysis",
            "author": "Yuchuan Li",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Ottawa",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Canada",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; computer-vision; generative-ai; expert-systems; predictive-analytics; transformers; image-segmentation; video-analysis; gan",
            "keywords": "",
            "abstract": "Flame and smoke image processing and analysis could improve performance to detect smoke or fire and identify many complicated fire hazards, eventually to help firefighters to fight fires safely. Deep Learning applied to image processing has been prevailing in recent years among image-related research fields. Fire safety researchers also brought it into their studies due to its leading performance in image-related tasks and statistical analysis. From the perspective of input data type, traditional fire research is based on simple mathematical regressions or empirical correlations relying on sensor data, such as temperature. However, data from advanced vision devices or sensors can be analyzed by applying deep learning beyond auxiliary methods in data processing and analysis. Deep Learning has a bigger capacity in non-linear problems, especially in high-dimensional spaces, such as flame and smoke image processing. We propose a video-based real-time smoke and flame analysis system with deep learning networks and fire safety knowledge. It takes videos of fire as input and produces analysis and prediction for flashover of fire. Our system consists of four modules. The Color2IR Conversion module is made by deep neural networks to convert RGB video frames into InfraRed (IR) frames, which could provide important thermal information of fire. Thermal information is critically important for fire hazard detection. For example, 600 °C marks the start of a flashover. As RGB cameras cannot capture thermal information, we propose an image conversion module from RGB to IR images. The core of this conversion is a new network that we innovatively proposed: Dual-Attention Generative Adversarial Network (DAGAN), and it is trained using a pair of RGB and IR images. Next, Video Semantic Segmentation Module helps extract flame and smoke areas from the scene in the RGB video frames. We innovated to use synthetic RGB video data generated and captured from 3D modeling software for data augmentation. After that, a Video Prediction Module takes the RGB video frames and IR frames as input and produces predictions of the subsequent frames of their scenes. Finally, a Fire Knowledge Analysis Module predicts if flashover is coming or not, based on fire knowledge criteria such as thermal information extracted from IR images, temperature increase rate, the flashover occurrence temperature, and increase rate of lowest temperature. For our contributions and innovations, we introduce a novel network, DAGAN, by applying foreground and background attention mechanisms in the image conversion module to help reduce the hardware device requirement for flashover prediction. Besides, we also make use of combination of thermal information from IR images and segmentation information from RGB images in our system for flame and smoke analysis. We also apply a hybrid design of deep neural networks and a knowledge-based system to achieve high accuracy. Moreover, data augmentation is also applied on the Video Semantic Segmentation Module by introducing synthetic video data for training. The test results of flashover prediction show that our system has leading places quantitative and qualitative in terms of various metrics compared with other existing approaches. It can give a flashover prediction as early as 51 seconds with 94.5% accuracy before it happens.",
            "source_url": "https:\/\/openalex.org\/W3204711149",
            "pdf_url": "",
            "doi": "10.20381\/ruor-26991",
            "handle": "",
            "repository_name": "uO Research (University of Ottawa)",
            "source_record_id": "W3204711149",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 667,
            "title": "Video-based similar gesture action recognition using deep learning and GAN-based approaches",
            "title_ar": "",
            "title_en": "Video-based similar gesture action recognition using deep learning and GAN-based approaches",
            "author": "Di Wu",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Technology Sydney",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Australia",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "video-analysis",
            "categories": "machine-learning; deep-learning; computer-vision; generative-ai; medical-ai; robotics; responsible-ai; predictive-analytics; cnn; rnn; video-analysis; gan; fairness",
            "keywords": "",
            "abstract": "Human action is not merely a matter of presenting patterns of motion of different parts of the body, in addition, it is also a description of intention, emotion and thoughts of the person. Hence, it has become a crucial component in human behavior analysis and understanding. Human action recognition has a wide variety of applications such as surveillance, robotics, health care, video searching and human-computer interaction. Analysing human actions manually is tedious and easily prone to errors. Therefore, computer scientists have been trying to bring the abilities of cognitive video understanding to human action recognition systems by using computer vision techniques. However, human action recognition is a complex task in computer vision because of the camera motion, occlusion, background cluttering, viewpoint variation, execution rate and similar gestures. These challenges significantly degrade the performance of the human action recognition system. The purpose of this research is to propose solutions based on traditional machine learning methods as well as the state-of-the-art deep learning methods to automatically process video-based human action recognition. This thesis investigates three research areas of video-based human action recognition: traditional human action recognition, similar gesture action recognition, and data augmentation for human action recognition. To start with, the feature-based methods using classic machine learning algorithms have been studied. Recently, deep convolutional neural networks (CNN) have taken their place in the computer vision and human action recognition research areas and have achieved tremendous success in comparison to traditional machine learning techniques. Current state-of-the-art deep convolutional neural networks were used for the human action recognition task. Furthermore, recurrent neural networks (RNN) and its variation of long-short term memory (LSTM) are used to process the time series features which are handcrafted features or extracted from the CNN. However, these methods suffer from similar gestures, which appear in the human action videos. Thus, a hierarchical classification framework is proposed for similar gesture action recognition, and the performance is improved by the multi-stage classification approach. Additionally, the framework has been modified into an end-to-end system, therefore, the similar gestures can be processed by the system automatically. In this study, a novel data augmentation framework for action recognition has been proposed, the objective is to generate well learnt video frames from action videos which can enlarge the dataset size as well as the feature bias. It is very important for a human action recognition system to recognize the actions with similar gestures as accurately as possible. For such a system, a generative adversarial net (GAN) is applied to learn the original video datasets and generate video frames by playing an adversarial game. Furthermore, a framework is developed for classifying the original dataset in the first place to obtain the confusion matrix using a CNN. The similar gesture actions will be paired based on the confusion matrix results. The final classification result will be applied on the fusion dataset which contains both original and generated video frames. This study will provide realtime and practical solutions for autonomous human action recognition system. The analysis of similar gesture actions will improve the performance of the existing CNN-based approaches. In addition, the GAN-based approaches from computer vision have been applied to the graph embedding area, because graph embedding is similar to image embedding but used for different purposes. Unlike the purpose of the GAN in computer vision for generating the images, the GAN in graph embedding can be used to regularize the embedding. So the proposed methods are able to reconstruct both structural characteristics and node features, which naturally possess the interaction between these two sources of information while learning the embedding.",
            "source_url": "https:\/\/openalex.org\/W3020614990",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "UTS ePRESS (University of Technology Sydney)",
            "source_record_id": "W3020614990",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 669,
            "title": "Data augmentation of visual rhythms using symmetric extension for deep learning video based human action recognition",
            "title_ar": "",
            "title_en": "",
            "author": "Hemerson Tacon",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2019,
            "language": "pt",
            "research_domain": "computer-vision",
            "research_subdomain": "video-analysis",
            "categories": "deep-learning; computer-vision; video-analysis",
            "keywords": "",
            "abstract": "Nos últimos anos, avanços significativos foram alcançados no problema de classificação de imagens devido ao aprimoramentos dos modelos de Aprendizagem Profunda. Entretanto, no que diz respeito ao Reconhecimento de Ações Humanas, ainda existe muito espaço para melhorias. Uma forma de melhorar o desempenho de tais modelos é através do aumento de dados. Dessa forma propomos, como aumento de dados, o uso de múltiplos recortes do Ritmo Visual, simetricamente estendidos no tempo e separados por uma distância fixa. Propomos ainda utilizar uma nova forma de extração do Ritmo Visual, o Ritmo Visual Ponderado. Este método propõe reforçar os padrões de movimento pesando os aspectos mais próximos de uma posição específica no vídeo na qual julgamos que a ação tenha maior probabilidade de ocorrer. O método final consiste na replicação do Ritmo Visual Ponderado concatenando quantas cópias forem necessárias ao longo da dimensão temporal, tendo as cópias pares invertidas horizontalmente. Esse método torna possível a extração de recortes que correspondam ao tamanho de entrada fixo da Rede Neural Convolucional utilizada, bem como a preservação da taxa de amostragem do vídeo, o que é crucial para não distorcer a velocidade das ações. Não obstante, os vários recortes garantem que toda extensão espacial e temporal do Ritmo Visual seja contemplada. Com o objetivo de avaliar nosso método, empregamos uma estratégia multi-fluxo. Essa estratégia consiste na combinação de informações extraídas a partir dos frames RGB dos vídeos, do Fluxo Ótico, e dos Ritmos Visuais Simetricamente Estendidos horizontal e vertical. Nosso método resultou em taxas de acurácia próximas ao estado da arte nos conjuntos de dados UCF101 e HMDB51.",
            "source_url": "https:\/\/openalex.org\/W3137056519",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Americanae (AECID Library)",
            "source_record_id": "W3137056519",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 690,
            "title": "Privacy-preserving federated learning framework",
            "title_ar": "",
            "title_en": "Privacy-preserving federated learning framework",
            "author": "Wenxuan Huang",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Southampton",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "responsible-ai",
            "research_subdomain": "federated-learning",
            "categories": "responsible-ai; ai-applications; federated-learning; fairness; ai-cybersecurity",
            "keywords": "",
            "abstract": "Federated Learning (FL) enables multiple parties to collaboratively train a shared model without exposing raw data. However, FL often suffers from degraded performance due to three core challenges: non-IID data distributions, residual privacy risks, and limited data volume per node. This work explores the privacy–performance trade-offs arising from these challenges and proposes a unified framework combining partial data sharing, anonymisation, and data augmentation. We first investigate how non-IID distributions impair standard FL convergence, and propose a Cluster-of-Trust (CoT) mechanism that groups mutually trusted clients for hierarchical aggregation. Experiments on the IoT-23 intrusion detection dataset show that CoT significantly improves model accuracy and convergence speed, closing most of the gap to centralised training. Next, we compare combinations of privacy-preserving techniques—including differential privacy, data anonymisation, and CoT-based grouping—highlighting how these impact model utility. Our results demonstrate that strong privacy guarantees can be achieved with only modest accuracy loss and reduced communication overhead. To address the limited data volume problem, we introduce data augmentation strategies and test their effectiveness in a privacy-sensitive Human Activity Recognition (HAR) task. We find that combining augmentation with trust-aware aggregation improves generalisation under strict privacy constraints. Across two domains—cybersecurity and HAR—we systematically evaluate this framework and demonstrate its effectiveness and generalisability. Our results show that strong privacy can be reconciled with competitive performance, offering practical insights for deploying FL in real-world, heterogeneous environments.",
            "source_url": "https:\/\/openalex.org\/W7140959527",
            "pdf_url": "https:\/\/eprints.soton.ac.uk\/510212\/1\/Privacy_Preserving_Federated_Learning_Framework_2_.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "ePrints Soton (University of Southampton)",
            "source_record_id": "W7140959527",
            "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": 721,
            "title": "Deep Learning For The Classification of Lung Diseases Using Chest X-Rays",
            "title_ar": "",
            "title_en": "Deep Learning For The Classification of Lung Diseases Using Chest X-Rays",
            "author": "Khamesi, Zahra",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Concordia University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Canada",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "deep-learning; computer-vision; medical-ai; medical-imaging",
            "keywords": "",
            "abstract": "The discovery of X-rays marked a significant milestone in the field of medicine. One of the most common types of X-rays, the chest X-ray (CXR), allows doctors to examine an individual’s internal structure without surgery. Over the years, deep learning methods and algorithms have been developed to automate lung disease detection and identification. This paper introduces RADIA, a project that combines multiple deep learning techniques to identify abnormal areas and abnormal- ities in chest X-rays. RADIA builds upon previous studies conducted by the Stanford ML group, such as ChexNet and ChexPert. Our team utilized the ConvNeXt-Large, a deep learning convo- lutional model, implemented with a pre-trained ConvNext algorithm on the ImageNet database to classify various pathologies from public datasets like ChestX-ray14, CheXpert, MIMIC-CXR, PadChest, and VinDr-CXR, as well as a private dataset obtained from the Picture Archiving Com- munication System (PACS) at Verdun and Notre Dame Hospitals in Montreal in the collaboration with CIUSSS (Centre Integre Universitaire de Sante et de Services Sociaux du Centre-Sud-de-l’Ile- de-Montreal) and valuable consultants from the radiology team at Notre Dame Hospital contributed to the project’s success. Our team employed image enhancement and augmentation techniques to create various image versions. We used different and novel approaches to address the challenges, and the results were evaluated using metrics such as AUC, F1, and G-Means to analyze performance with imbalanced input data. It is essential to note that the project’s development extends beyond the creation of a web tool based on deep learning techniques. Our future plans involve building a decision helper that combines inference models and web tools to assist healthcare professionals.",
            "source_url": "https:\/\/openalex.org\/W7112380474",
            "pdf_url": "https:\/\/spectrum.library.concordia.ca\/id\/eprint\/993141\/7\/Khamesi_MCompSc_S2024.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Spectrum Research Repository (Concordia University)",
            "source_record_id": "W7112380474",
            "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": 793,
            "title": "Addressing data heterogeneity, scarcity, and training efficiency in privacy-preserving federated learning",
            "title_ar": "",
            "title_en": "Addressing data heterogeneity, scarcity, and training efficiency in privacy-preserving federated learning",
            "author": "Chen, Haokun",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Ludwig-Maximilians-Universität München",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Germany",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; generative-ai; medical-ai; responsible-ai; ai-applications; transfer-learning; few-zero-shot; optimization; multimodal; llm; diffusion; federated-learning; fairness; ai-industry",
            "keywords": "",
            "abstract": "Over the past decade, deep learning has achieved significant breakthroughs in various domains, including computer vision and natural language processing, with applications spanning industries such as healthcare and manufacturing. However, the success of deep neural networks (DNNs) relies heavily on access to large-scale datasets, which can be difficult for individual organizations to acquire. The reasons behind are the complexities and costs for data collection and annotation at large scale. A straightforward solution is to centralize data from multiple organizations for training. However, this approach raises significant privacy concerns, as such data often contains sensitive or confidential information. Furthermore, regulations like the General Data Protection Regulation (GDPR) emphasize the importance of protecting user privacy in inter-organizational data exchanges. Moreover, transmitting large volumes of data introduces substantial computational overhead, further complicating the process. These challenges highlight the urgent need for methods that facilitate collaborative data use while ensuring privacy preservation. Federated learning (FL), which enables multiple parties to collaboratively train a DNN with the assistance of a central server, offers an effective solution to the aforementioned problem. Unlike traditional centralized learning, which requires collecting data from each party, FL eliminates the need to upload data for joint training. Instead, locally trained models are exchanged with a central server, which aggregates the knowledge from all of the uploaded models and then distributes a refined global model to each party. This approach allows each party to benefit from the collective contributions, ultimately enhancing the model performance. This thesis makes four key contributions to addressing challenges in federated learning, including data heterogeneity, data scarcity, and system convergence rate, while preserving client data privacy. For each contribution, we propose a novel method and empirically demonstrate its effectiveness within the relevant problem context. In this thesis, we address key challenges in federated learning (FL) related to data heterogeneity, foundation model adaptation, hyperparameter tuning, and communication efficiency. First, we tackle feature space heterogeneity by introducing a generative augmentation method that aligns diverse client distributions, validated on both public and real-world datasets. We then adapt parameter-efficient fine-tuning techniques for vision-language models in FL by designing a dual-stream adapter that captures both client-specific and client-agnostic knowledge. To optimize performance under limited resources and non-IID conditions, we propose an evolutionary hyperparameter tuning framework that enables efficient online optimization. Lastly, we address data scarcity and heterogeneity in One-Shot FL by personalizing pretrained latent diffusion models, enabling privacy-preserving synthetic data generation that improves performance across challenging domains such as medical and satellite imaging.",
            "source_url": "https:\/\/openalex.org\/W7108654185",
            "pdf_url": "",
            "doi": "10.5282\/edoc.36097",
            "handle": "",
            "repository_name": "Electronic Theses of LMU Munich (Ludwig-Maximilians-Universität München)",
            "source_record_id": "W7108654185",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 829,
            "title": "A Novel Hybrid Deep Learning Model using U-net and Vision Transformer for Polyp Segmentation in medical imaging",
            "title_ar": "",
            "title_en": "A Novel Hybrid Deep Learning Model using U-net and Vision Transformer for Polyp Segmentation in medical imaging",
            "author": "Prity Rani Das",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "deep-learning; computer-vision; medical-ai; cnn; transformers; image-segmentation; medical-imaging",
            "keywords": "",
            "abstract": "This research represents a hybrid model for polyp segmentation in medical images, which combines convolutional neural networks (CNN) and vision transformers (ViT). We propose a hybrid architecture that integrates UNet with a Vision Transformer, where UNet is used as an encoder to capture local features and ViT is used as a bottleneck module to extract global contextual information. To improve the robustness and generalization of the model, various data augmentation techniques are applied to the training data set, including horizontal flip, vertical flip, and rotation. The model is trained and evaluated on the multicenter PolypDB dataset, with all images preprocessed to a consistent resolution, and the corresponding masks are appropriately managed. A loss function, combining Dice Loss and Binary Cross-Entropy (BCE) Loss, is applied to optimize segmentation performance.",
            "source_url": "https:\/\/openalex.org\/W7128515784",
            "pdf_url": "",
            "doi": "10.5281\/zenodo.18591130",
            "handle": "",
            "repository_name": "Zenodo (CERN European Organization for Nuclear Research)",
            "source_record_id": "W7128515784",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 832,
            "title": "Weakly supervised learning for medical image segmentation",
            "title_ar": "",
            "title_en": "Weakly supervised learning for medical image segmentation",
            "author": "Hateef Alshewaier",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Cardiff University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "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; predictive-analytics; image-segmentation; medical-imaging; fairness",
            "keywords": "",
            "abstract": "Medical image segmentation plays a critical role in clinical diagnosis and treatment planning; however, the performance of deep learning models typically depends on large quantities of pixel-wise annotated data, which are costly and time-consuming to obtain. This thesis investigates annotation-efficient approaches for medical image segmentation by developing weakly supervised learning frameworks that reduce annotation requirements while maintaining high segmentation accuracy. The first contribution proposes an enhanced scribble-based segmentation framework that extends a modified U-Net architecture with increased feature learning capacity, mix-based data augmentation, and global and local consistency regularisation. These components improve learning from sparse scribble annotations and promote anatomically coherent segmentation masks. Experimental results demonstrate improved segmentation performance compared with existing scribble-supervised methods. The second contribution presents an ensemble learning framework for weakly supervised medical image segmentation based on single bounding-box annotations. The proposed framework integrates U-Net, ResUNet, and DeepLabV3 using bagging and boosting strategies to exploit complementary architectural characteristics. Despite relying solely on coarse single-bounding-box supervision, the ensemble models improve robustness, reduce model-specific bias, and yield more stable segmentation predictions. Experimental results demonstrate that the ensemble methods consistently outperform the individual models, with boosting achieving the highest segmentation performance. The third contribution introduces a novel dual bounding-box supervision strategy that utilises an inner bounding box to represent high-confidence object regions and an outer bounding box to provide contextual anatomical information. A region-aware weighted loss function encourages accurate object localisation while reducing ambiguity in boundary regions. The proposed framework significantly outperforms conventional single-box weakly supervised approaches and narrows the gap between weak and full supervision. Overall, the findings demonstrate that high-quality medical image segmentation can be achieved using sparse scribble annotations, ensemble learning techniques, and coarse bounding-box supervision without requiring exhaustive pixel-wise labels. The proposed methods reduce annotation effort while maintaining competitive segmentation accuracy, providing a practical and scalable pathway for deploying deep learning-based segmentation systems in clinical environments.",
            "source_url": "https:\/\/openalex.org\/W7219256121",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "ORCA Online Research @Cardiff (Cardiff University)",
            "source_record_id": "W7219256121",
            "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": 874,
            "title": "Psoriasis support system based on semantic segmentation AI models",
            "title_ar": "",
            "title_en": "Psoriasis support system based on semantic segmentation AI models",
            "author": "Lopes, Toni Marcos Silva",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Portugal",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "deep-learning; computer-vision; medical-ai; ai-applications; cnn; object-detection; image-segmentation; medical-imaging; ai-agriculture",
            "keywords": "",
            "abstract": "Psoriasis is a chronic inflammatory skin disease characterized by the presence of lesions that vary in shape, size, and color. Accurate segmentation of these lesions from clinical images is crucial for effective diagnosis and treatment monitoring. However, the variability in image dimensions, lighting conditions, and the presence of noise in real-world datasets complicates the segmentation task. Additionally, available datasets for psoriasis lesion segmentation are often small, making it challenging to train deep learning models effectively without overfitting. The project aims to enhance the segmentation accuracy of psoriasis lesions by employing a range of AI models and optimizing their performance through the application of advanced pre-processing techniques and data augmentation strategies. The AI models tested include Mask R-CNN, U-Net, YOLOv8n, FCN, DeepLabV3+, BiSeNet, HRNet, PSPNet, and SegNet. Pre-processing techniques, such as bilateral smooth filters and adaptive median filters, were applied to enhance image quality and reduce noise. Furthermore, data augmentations, including random adjustments in brightness, contrast, cropping, rotation, flipping, and scaling, were used to simulate real-world variations and increase the robustness of the models. These augmentations were carefully replicated from related works to mimic their experimental setups. The evaluation of multiple AI models for psoriasis lesion segmentation demonstrated that applying effective pre-processing and data augmentation techniques significantly improves model performance. Among the tested models, FCN achieved the highest F1 score of 0.889, using a bilateral smooth filter and translation augmentations. U-Net and SegNet followed closely, with U-Net reaching an F1 score of 0.885 and SegNet 0.880, both benefiting from similar pre-processing and augmentation strategies. Mask R-CNN and BiseNet also showed competitive results, underscoring the importance of carefully selected augmentations that mimic real-world variability. These findings highlight the value of pre-processing and augmentation in enhancing model generalization, particularly in small, diverse datasets. In addition to the AI-based segmentation work, the project also incorporates a mobile application designed to assist patients in tracking their psoriasis lesions over time. This application enables users to monitor whether lesions are improving or worsening, providing valuable insights for deciding when to consult a dermatologist. By helping patients recognize early signs of deterioration, the application plays a crucial role in supporting more proactive and informed healthcare decisions.",
            "source_url": "https:\/\/openalex.org\/W7113660975",
            "pdf_url": "https:\/\/bdigital.ufp.pt\/bitstreams\/d3e9f0b8-cf78-4d94-8dcd-0f04470834fa\/download",
            "doi": "",
            "handle": "",
            "repository_name": "Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)",
            "source_record_id": "W7113660975",
            "other_sources": "",
            "verification_status": "needs_review",
            "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": 943,
            "title": "Solving Graph Problems with Large Language Models",
            "title_ar": "",
            "title_en": "Solving Graph Problems with Large Language Models",
            "author": "Angelo Zangari",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Illinois Chicago",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "deep-learning; nlp; responsible-ai; gnn; llm; xai",
            "keywords": "",
            "abstract": "This thesis investigates how large language models (LLMs) can be used to solve classical computational problems on graphs. Graphs are a fundamental abstraction for representing real-world systems, such as social, transportation, and communication networks, but they pose unique challenges: their structure is not tied to any fixed ordering of nodes (graph isomorphism), and different tasks (such as reachability, shortest paths, flows, or substructure counting) require very different reasoning patterns. With the advent of large language models, there is growing interest in replacing or complementing traditional graph neural networks with text-based models. Recent work shows that LLMs can exhibit human-like behaviors in specific settings, which raises a key question: can we design graph representations that better align with how humans (and thus LLMs) naturally interpret structure? The first contribution of this thesis is the proposal of new techniques for augmenting node-level information with structural signals derived from the graph itself. These methods are orthogonal to the specific graph characteristics, thus are applicable to any graph dataset. The second contribution is the design of a systematic evaluation framework. I construct a synthetic benchmark covering multiple graph families and a diverse set of tasks, including computationally challenging ones, and develop an end-to-end pipeline to generate datasets, construct prompts, query LLMs, and analyze responses. The proposed representations are assessed through theoretical analysis and extensive experiments, giving additional insights on whether human-interpretable structural augmentation can improve LLM performance on non-trivial graph problems.",
            "source_url": "https:\/\/openalex.org\/W7168364382",
            "pdf_url": "",
            "doi": "10.25417\/uic.32991947",
            "handle": "",
            "repository_name": "University of Illinois Chicago",
            "source_record_id": "W7168364382",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 962,
            "title": "Unstructured data for large language models",
            "title_ar": "",
            "title_en": "Unstructured data for large language models",
            "author": "Aleksandra Piktus",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Sapienza University of Rome",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Italy",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; nlp; transfer-learning; predictive-analytics; llm",
            "keywords": "",
            "abstract": "In recent years, we have witnessed an impressive rise in the ubiquity of large language models (LLMs). Although their fundamental objective, predicting the most probable next word in a sequence, has remained unchanged, the models themselves have expanded dramatically in scale and capability, becoming the dominant paradigm in Natural Language Processing (NLP). Progress has been marked by the development of increasingly sophisticated evaluation benchmarks on one hand and by a growing demand for vast amounts of training data on the other. In this thesis, we examine how unstructured, primarily web-based data is utilized in LLM pre-training and fine-tuning. We investigate two principal roles that large textual corpora play within these models: first, as a source of world knowledge through retrieval augmentation, and second, as pre-training data. We begin by demonstrating how retrieval from large, unstructured web corpora can enhance performance on open-domain tasks, paving the way towards assistants capable of supporting humans in solving complex, knowledge-intensive problems. Next, we address the challenge of improving the robustness of pre-training data through the development of tools that enable qualitative analysis of massive text collections. Finally, we explore potential avenues for model scaling under data-constrained conditions, anticipating a future in which the entirety of publicly available web text may no longer suffice to meet the demands of ever-larger language models.",
            "source_url": "https:\/\/openalex.org\/W7134876569",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "IRIS Research product catalog (Sapienza University of Rome)",
            "source_record_id": "W7134876569",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:56",
            "updated_at": "2026-11-15 16:52:56"
        },
        {
            "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": 1016,
            "title": "Machine learning for healthcare with a focus on the early diagnosis of epilepsy and brain tumor detection",
            "title_ar": "",
            "title_en": "Machine learning for healthcare with a focus on the early diagnosis of epilepsy and brain tumor detection",
            "author": "Diyuan Lu",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Goethe University Frankfurt",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Germany",
            "governorate": "",
            "publication_year": 2022,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; predictive-analytics; rnn; medical-imaging",
            "keywords": "",
            "abstract": "Machine learning (ML) techniques have evolved rapidly in recent years and have shown impressive capabilities in feature extraction, pattern recognition, and causal inference. There has been an increasing attention to applying ML to medical applications, such as medical diagnosis, drug discovery, personalized medicine, and numerous other medical problems. ML-based methods have the advantage of processing vast amounts of data. With an ever increasing amount of medical data collection and large, inter-subject variability in the medical data, automated data processing pipelines are very much desirable since it is laborious, expensive, and error-prone to rely solely on human processing. ML methods have the potential to uncover interesting patterns, unravel correlations between complex features, learn patient-specific representations, and make accurate predictions. Motivated by these promising aspects, in this thesis, I present studies where I have implemented deep neural networks for the early diagnosis of epilepsy based on electroencephalography (EEG) data and brain tumor detection based on magnetic resonance spectroscopy (MRS) data. In the project for early diagnosis of epilepsy, we are dealing with one of the most common neurological disorders, epilepsy, which is characterized by recurrent unprovoked seizures. It can be triggered by a variety of initial brain injuries and manifests itself after a time window which is called the latent period. During this period, a cascade of structural and functional brain alterations takes place leading to an increased seizure susceptibility. The development and extension of brain tissue capable of generating spontaneous seizures is defined as epileptogenesis (EPG). Detecting the presence of EPG provides a precious opportunity for targeted early medical interventions and, thus, can slow down or even halt the disease progression. In order to study brain signals in this latent window, animal epilepsy models are used to provide valuable data as it is extremely difficult to obtain this data from human patients. The aim of this study is to discover biomarkers of EPG using animal models and then to find the equivalent and counterparts in human patients' data. However, the EEG features for EPG are not well-understood and there is not a sufficiently large amount of annotated data for ML-based algorithms. To approach this problem, firstly, I utilized the timestamp information of the recorded EEG from an animal epilepsy model where epilepsy is induced by an electrical stimulation. The timestamp serves as a form of weak supervision, i.e., before and after the stimulation. Secondly, I implemented a deep residual neural network and trained it with a binary classification task to distinguish the EEG signals from these two phases. After obtaining a high discriminative ability on the binary classification task, I proposed to divide further the time span after the stimulation for a three-class classification, aiming to detect possible stages of the progression of the latent EPG phase. I have shown that the model can distinguish EEG signals at different stages of EPG with high accuracy and generalization ability. I have also demonstrated that some of the learned features from the network are clinically relevant. In the task of detecting brain tumors based on MRS data, I first proposed to apply a deep neural network on the MRS data collected from over 400 patients for a binary classification task. To combat the challenge of noisy labeling, I developed a distillation step to filter out relatively ``cleanly'' labeled samples. A mixing-based data augmentation method was also implemented to expand the size of the training set. All the experiments were designed to be conducted with a leave-patient-out scheme to ensure the generalization ability of the model. Averaged across all leave-patient-out cross-validation sets, the proposed method performed on par with human neuroradiologists, while outperforming other baseline methods. I have demonstrated the distillation effect on the MNIST data set with manually-introduced label noise as well as providing visualization of the input influences on the final classification through a class activation map method. Moreover, I have proposed to aggregate information at the subject level, which could provide more information and insights. This is inspired by the concept of multiple instance learning, where instance-level labels are not required and which is more tolerant to noisy labeling. I have proposed to generate data bags consisting of instances from each patient and also proposed two modules to ensure permutation invariance, i.e., an attention module and a pooling module.",
            "source_url": "https:\/\/openalex.org\/W4229378113",
            "pdf_url": "http:\/\/publikationen.ub.uni-frankfurt.de\/files\/67966\/Diyuan_PhD_Thesis-pdfA.pdf",
            "doi": "10.21248\/gups.67966",
            "handle": "",
            "repository_name": "Publication Server of Goethe University Frankfurt am Main (Goethe University Frankfurt)",
            "source_record_id": "W4229378113",
            "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": 1055,
            "title": "Evolving Convolutional Neural Networks for Image and Text Classification Tasks",
            "title_ar": "",
            "title_en": "Evolving Convolutional Neural Networks for Image and Text Classification Tasks",
            "author": "Trevor Londt",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "New Zealand",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "cnn",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; generative-ai; predictive-analytics; optimization; cnn",
            "keywords": "",
            "abstract": "In the Machine Learning field, Convolutional Neural Networks (CNNs) have successfully been applied to image and text classification tasks. Innovative research in CNN design, such as the usage of deeper models and data augmentation, has resulted in significantly increased performance. However, the resultant growth in CNN complexity from these innovations has required a corresponding increase in expert skills to design them. Furthermore, CNN architectures and data augmentation techniques designed for a classification task in one domain may not generalise to other classification tasks in a different domain, meaning the difficult and costly design process must be repeated. Evolutionary Deep Learning Neural Architecture Search (EDLNAS) has been used to automatically evolve performant CNNs for various classification tasks, including image and text classification. However, the approach suffers from high computation costs, often resulting in algorithms needing to focus on a single task for a single domain, thereby missing the opportunity to achieve algorithm generalisability. This thesis aims to investigate and improve upon the efficiency, effectiveness, and generalisability of EDLNAS of CNNs for image and text classification tasks without using data augmentation. Achieving this goal can mitigate three significant problems: the high-computational cost of EDLNAS algorithms, the generalisability problem, and the problem of collecting additional training data or implementing bespoke data augmentation techniques that require costly expert domain knowledge. This thesis proposes a new, configurable, and extensible version of Cellular Encoding (CE), including supporting network structures designed to represent and construct novel CNN architectures. The encoding successfully represents various novel CNN architectures of varying width and depth, suitable for image or text classification tasks. This thesis proposes a data augmentation-free EDLNAS method to automatically evolve novel CNN architectures for image and text classification tasks, using the proposed CE representation and predesigned state-of-the-art micro-architectures. The results show that peer-competitive CNNs can be evolved in less than one GPU day across image or text domains. Next, this thesis proposes to evolve micro-architectures to boost the performance in evolving CNN architectures for image and text classification tasks without data augmentation. The results show that this is achieved without increasing the number of GPU days required. This thesis proposes the first data augmentation-free cooperative coevolution algorithm to decompose a CNN architecture into four constituent sub-architectures, each evolved separately but in cooperation, to synthesise performant CNN architectures. A new population structure and novelty injection mechanism are proposed to create a better balance between exploration and exploitation. Furthermore, a persistent offline database is created, storing tens of thousands of evolved CNN architectures and associated performance metrics. The results show that highly competitive CNN architectures can be evolved in less than one GPU day, with the algorithm achieving a good balance between exploration and exploitation during the evolution process. Finally, this thesis proposes the first EDLNAS method that models a database of stored CNN architectures and performance metrics to create a deep neural network prediction model to predict the potential classification accuracy of a candidate CNN architecture, thereby removing the need to conduct back-propagation training during the evolutionary process. The method is able to evolve a large population of CNN architectures for both image and text classification tasks in seconds, making the evolutionary process near real-time while still achieving state-of-the-art peer-competitive results.",
            "source_url": "https:\/\/openalex.org\/W4404658997",
            "pdf_url": "",
            "doi": "10.26686\/wgtn.27897288",
            "handle": "",
            "repository_name": "Open Access Victoria University of Wellington | Te Herenga Waka (Figshare)",
            "source_record_id": "W4404658997",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:57",
            "updated_at": "2026-11-15 16:52:57"
        },
        {
            "id": 1074,
            "title": "SPEECH EMOTION RECOGNITION USING DEEP NEURAL NETWORKS",
            "title_ar": "",
            "title_en": "SPEECH EMOTION RECOGNITION USING DEEP NEURAL NETWORKS",
            "author": "Raiymbek Mustazhapov",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Nazarbayev University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Kazakhstan",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "sentiment-analysis",
            "categories": "deep-learning; nlp; cnn; sentiment-analysis; speech-recognition",
            "keywords": "",
            "abstract": "There is an apparent evolving interest in speech emotion recognition (SER), one of the particular cases of a broader problem of multimedia pattern recognition. SER is considered to possess the capability to enhance the communication efficiency between human and artificial intelligence providing an emotional context to the machine. The field has been developing fast with the emergence and increase in accessibility of deep learning techniques recently. This potential critical benefit and novel techniques have drawn the attention of many specialists in the field and generated a great number of research papers that furnish diverse intricate methods. One of such methods involving various data augmentation techniques has demonstrated high performance in this field. This paper performs an analysis of various simple augmentation methods to attempt to improve existing models. Particularly, this research focuses on state of the art CNN models for RAVDESS, EMO-DB, and IEMOCAP datasets, and exploits temporal, spatial, and spectral transformations of sound as an underlying method for augmentation. As a result of exploiting simple augmentations, we achieved an increase in performance for IEMOCAP model and positive effects comparable to their complex counterparts for other datasets.",
            "source_url": "https:\/\/openalex.org\/W7197763834",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Nazarbayev University Repository (Nazarbayev University)",
            "source_record_id": "W7197763834",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "id": 1082,
            "title": "A Deep Neural Network Approach Integrating CNN and BiLSTM-Transformer Architectures for Emotion Recognition from Speech",
            "title_ar": "",
            "title_en": "A Deep Neural Network Approach Integrating CNN and BiLSTM-Transformer Architectures for Emotion Recognition from Speech",
            "author": "Divyansh Anand",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; nlp; medical-ai; ai-applications; predictive-analytics; cnn; transformers; sentiment-analysis; speech-recognition; ai-education; ai-industry; ai-smart-cities",
            "keywords": "",
            "abstract": "The goal of speech emotion recognition is to make human-computer interaction more efficient in several areas such as customer service, entertainment industry, human-computer interaction, healthcare, and education. Previous work in speech emotion analysis presented some issues like limited choice of features, model complexity, noise variability, and insufficient data samples, which negatively affected the prediction of emotions. This paper provides an in-depth study of speech emotion recognition using a hybrid deep neural network architecture that combines 1-D Convolutional Neural Network (CNN) and BiLSTM-Transformer models to analyze data from the Ravdess and Crema-D datasets. To make the datasets appropriate for emotion detection, all were preprocessed by means of librosa library to get rid of non-speech segments. Important sound characteristics such as Mel-Frequency Cepstral Coefficients(MFCC), Root Mean Square Energy (RMSE), and Zero Crossing Rate (ZCR) were extracted to get the spectral characteristics, intensity of feelings, and dynamic features present in the emotions. In order to improve model’s generalization and robustness noise injection, time stretching, time shifting as well as pitch shifting have been applied during data augmentation. The proposed model leverages the strengths of both CNN and BiLSTM-Transformer components. The proposed model’s 1-D CNN captures local patterns in sound whereas the BiLSTM-Transformer handles sequence data and complex hierarchical structures of audio. Various datasets such as Ravdess and Crema-D were used to train and test the performance of the model in the emotion classification task. To evaluate model’s performance, training-validation accuracy graph, confusion matrix and overall metrics which include precision, recall, and F1-score are used. Ravdess dataset achieved a high accuracy of 83.3%, surprise, angry, disgust and sad were among those emotions which this model identified with great accuracy. Crema-D dataset achieved 82.7% accuracy, and showed solid performance in detecting neutral, fear, and happy emotions. Accuracy plots between training and validation demonstrated good generalization for the unseen data and confusion matrices highlighted the emotion categories where improvement could be made.",
            "source_url": "https:\/\/openalex.org\/W7127233843",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "NORMA",
            "source_record_id": "W7127233843",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "id": 1123,
            "title": "Robust Neural Machine Translation",
            "title_ar": "",
            "title_en": "Robust Neural Machine Translation",
            "author": "Abdul Rafae Khan",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "City University of New York",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "machine-translation",
            "categories": "machine-learning; nlp; transfer-learning; data-mining; machine-translation",
            "keywords": "",
            "abstract": "This thesis aims for general robust Neural Machine Translation (NMT) that is agnostic to the test domain. NMT has achieved high quality on benchmarks with closed datasets such as WMT and NIST but can fail when the translation input contains noise due to, for example, mismatched domains or spelling errors. The standard solution is to apply domain adaptation or data augmentation to build a domain-dependent system. However, in real life, the input noise varies in a wide range of domains and types, which is unknown in the training phase. This thesis introduces five general approaches to improve NMT accuracy and robustness, where three of them are invariant to models, test domains, and noise types. First, we describe a novel unsupervised text normalization framework Lex-Var, to reduce the lexical variations for NMT. Then, we apply the phonetic encoding as auxiliary linguistic information and obtained very significant (5 BLEU point) improvement in translation quality and robustness. Furthermore, we introduce the random clustering encoding method based on our hypothesis of Semantic Diversity by Phonetics and generalizes to all languages. We also discussed two domain adaptation models for the known test domain. Finally, we provide a measurement of translation robustness based on the consistency of translation accuracy among samples and use it to evaluate our other methods. All these approaches are verified with extensive experiments across different languages and achieved significant and consistent improvements in translation quality and robustness over the state-of-the-art NMT.",
            "source_url": "https:\/\/openalex.org\/W2997654874",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "CUNY Academic Works (City University of New York)",
            "source_record_id": "W2997654874",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "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": 1163,
            "title": "The Relevance of Explainable Artificial Intelligence (xAI) in High-Risk Decisions",
            "title_ar": "",
            "title_en": "The Relevance of Explainable Artificial Intelligence (xAI) in High-Risk Decisions",
            "author": "Julie Gerlings",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Copenhagen Business School",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Germany",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "responsible-ai",
            "research_subdomain": "xai",
            "categories": "machine-learning; responsible-ai; xai",
            "keywords": "Artificial Intelligence (AI), Explainable artificial intelligence (xAI), machine learning (ML), stakeholder theory, human-AI collaboration, high-risk decision making, trust, organizational context, transaction monitoring (TM), anti-money laundering (AML)",
            "abstract": "The increasing adoption of machine learning (ML) and artificial intelligence (AI) in critical decision-making has intensified demands for explainability and transparency, particularly in high-risk domains such as finance. This dissertation investigates how explainable AI (xAI) can be designed and adapted to meet the diverse explainability needs of stakeholders in high-risk organizations through a longitudinal Action Design Research (ADR) study conducted in collaboration with a European financial institution implementing ML in transaction monitoring (TM) for anti-money laundering (AML). The ADR study addresses key gaps in the explainable AI literature by providing empirical evidence of how stakeholders interact with xAI in organizational contexts. The systematic literature review reveals four central debates in xAI research and identifies a critical need for empirical studies examining stakeholder needs. The empirical investigation demonstrates how implementation modes (automation versus augmentation) fundamentally alter stakeholder information requirements and liability structures, challenging assumptions about universal explainability needs. The research introduces a novel proximity-responsibility framework that systematically explains how stakeholders' proximity to AI systems influences both their trust in these systems and their utilization of xAI. High-proximity stakeholders (data scientists, investigators) develop trust through operational familiarity and use xAI for optimization and decision support, while low-proximity stakeholders (compliance managers, auditors) rely on xAI primarily for oversight, documentation, and regulatory compliance. Significantly, this dissertation challenges the prevailing explainability-trust hypothesis that dominates xAI literature by providing empirical evidence that trust influences explainable AI use rather than being produced by it. The research reconceptualizes trust and control as complementary coordination mechanisms and proposes a hierarchical conceptual framework positioning interpretability as methodology for developing xAI serving a specific purpose rather than generic trust generation. The findings contribute theoretical frameworks for understanding human-AI collaboration in high-stakes environments, practical design principles for stakeholder-specific xAI implementation, and methodological guidance for conducting rigorous xAI research in organizational contexts. The study demonstrates that effective xAI design requires moving beyond one-size-fits-all approaches toward nuanced, stakeholder-specific solutions that recognize the complex interplay between organizational context, implementation choices, and human factors in AI adoption. Keywords: Artificial Intelligence (AI), Explainable artificial intelligence (xAI), machine learning (ML), stakeholder theory, human-AI collaboration, high-risk decision making, trust, organizational context, transaction monitoring (TM), anti-money laundering (AML)",
            "source_url": "https:\/\/openalex.org\/W4414292580",
            "pdf_url": "",
            "doi": "10.22439\/phd.35.2025",
            "handle": "",
            "repository_name": "OpenArchive@CBS (Copenhagen Business School)",
            "source_record_id": "W4414292580",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:59",
            "updated_at": "2026-11-15 16:52:59"
        },
        {
            "id": 1286,
            "title": "Data Augmentation Methods for Deep Learning Neural Networks",
            "title_ar": "",
            "title_en": "Data Augmentation Methods for Deep Learning Neural Networks",
            "author": "Md. Sharif",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Eastern Finland",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Finland",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "",
            "categories": "deep-learning",
            "keywords": "",
            "abstract": "",
            "source_url": "https:\/\/openalex.org\/W7215584607",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "UEF eRepo (University of Eastern Finland)",
            "source_record_id": "W7215584607",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:53:00",
            "updated_at": "2026-11-15 16:53:00"
        },
        {
            "id": 1287,
            "title": "Image Data Augmentation Methods with Deep Learning Neural Networks",
            "title_ar": "",
            "title_en": "Image Data Augmentation Methods with Deep Learning Neural Networks",
            "author": "Mohammad Hossain",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Eastern Finland",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Finland",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "cnn",
            "categories": "deep-learning; computer-vision; ai-applications; cnn; ai-agriculture",
            "keywords": "",
            "abstract": "Image data enhancement is a vital method in the field of deep learning for enhancing model performance and generalization capabilities.This thesis explores various image data augmentation methods and their effectiveness in improving the performance of deep learning neural networks.The study begins with an overview of image data augmentation techniques, including rotation, flipping, scaling, cropping, translation, brightness adjustment, contrast adjustment, and Gaussian noise addition.Each augmentation method is examined in detail, discussing its impact on the variety and richness of the training collection.Following the theoretical overview, a series of experiments are conducted using widely used deep learning models such as Convolutional Neural Networks (CNNs), VGG, and MobileNet.These experiments aim to evaluate the performance of different augmentation methods in terms of model accuracy, robustness, and generalization on benchmark datasets.The results of the experiments demonstrate the effectiveness of certain augmentation techniques in improving model performance, while also highlighting potential trade-offs and considerations for real-world applications.Additionally, the study investigates the impact of augmentation parameters such as magnitude, probability, and combination strategies on model training dynamics and convergence.This thesis provides valuable insights into the role of image data augmentation in deep learning and offers practical guidance for selecting and implementing augmentation methods to enhance the effectiveness of neural networks across various computer vision assignments.",
            "source_url": "https:\/\/openalex.org\/W7215158281",
            "pdf_url": "https:\/\/erepo.uef.fi\/bitstreams\/13972c2f-f64d-4f28-8b7c-b18f3a88a358\/download",
            "doi": "",
            "handle": "",
            "repository_name": "UEF eRepo (University of Eastern Finland)",
            "source_record_id": "W7215158281",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:53:00",
            "updated_at": "2026-11-15 16:53:00"
        }
    ]
}