{
    "exported_at": "2026-11-17 23:08:13",
    "count": 59,
    "records": [
        {
            "id": 21,
            "title": "An improved method using fuzzy system based on hybrid boahs for phishing attack detection",
            "title_ar": "",
            "title_en": "An improved method using fuzzy system based on hybrid boahs for phishing attack detection",
            "author": "Noor Syahirah Nordin",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Universiti Malaysia Pahang",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Malaysia",
            "governorate": "",
            "publication_year": 2022,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "predictive-analytics",
            "categories": "machine-learning; expert-systems; ai-applications; predictive-analytics; optimization; ai-education; ai-cybersecurity",
            "keywords": "",
            "abstract": "A fuzzy system is a rule-based system that uses human expert's knowledge which holds the truth or false values to make a particular decision. However, it is difficult to generate fuzzy parameters manually to classify data when it comes to a very complex problem. Therefore, metaheuristic algorithm as the optimization method is needed to solve this issue. A small experiment was being performed to choose the best metaheuristic algorithm where seven metaheuristic algorithms were analyzed in terms of their performance measurement that including accuracy, recall, precision, and f-measure. The algorithms involved were Genetic Algorithm, Differential Evolution Algorithm, Particle Swarm Optimization, Butterfly Optimization Algorithm, Teaching-Learning-Based Optimization Algorithm, Harmony Search Algorithm and Gravitational Search Algorithm. The proposed method of this study is to cater the problems occur in fuzzy systems by using optimization method. Moreover, Butterfly Optimization Algorithm and Harmony Search Algorithm were combined as optimization method led to a new method named BOAHS. The proposed algorithm has utilized the advantages of both algorithms to balance the exploration and exploitation search process. The experiment was executed by using k-fold cross validation techniques for predicting the classification algorithm performance. Thereby, two datasets; Website Phishing Dataset and Phishing Websites Dataset were used to test the performance of the proposed method. As a result, the average accuracy value for both datasets are 98.69% and 98.80% respectively. The proposed method has proven to outperform the other methods including the standard BOA and HS algorithm.",
            "source_url": "https:\/\/openalex.org\/W7205250197",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "UMP Institutional Repository (Universiti Malaysia Pahang)",
            "source_record_id": "W7205250197",
            "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": 97,
            "title": "Explainable artificial intelligence for analysing mosquito flight behaviour",
            "title_ar": "",
            "title_en": "Explainable artificial intelligence for analysing mosquito flight behaviour",
            "author": "Yasser M. Qureshi",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Warwick",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "image-segmentation",
            "categories": "machine-learning; computer-vision; medical-ai; responsible-ai; predictive-analytics; optimization; image-segmentation; xai",
            "keywords": "",
            "abstract": "Mosquitoes are among the deadliest organisms on Earth, transmitting diseases that threaten global health. Malaria alone kills over half a million people annually, mostly young children. While insecticide-treated bed nets and indoor residual spraying have reduced transmission, these measures are increasingly compromised by insecticide-resistant mosquito populations and their behavioural adaptations. Despite well-documented genetic resistance, behavioural resistance remains poorly understood but critical to intervention efficacy. This thesis helps to address this gap by developing a machine learning and explainable AI (XAI) framework to analyse mosquito flight behaviours, focusing on identifying traits linked to resistance. The framework integrates preprocessing, trajectory segmentation, feature extraction, classification, and SHapley Additive exPlanations (SHAP) to provide interpretable insights. New techniques addressed tracking challenges like occlusions and spatial distortions, ensuring robustness. Three experimental conditions were analysed: (1) mating swarm data to classify males from non-males, (2) behavioural differences between insecticide-susceptible (IS) and insecticide-resistant (IR) mosquitoes near untreated nets, and (3) analogous trials involving permethrin-treated nets. The primary contributions of this thesis include the identification of behavioural signatures associated with insecticide resistance. IR mosquitoes exhibited reduced flight speeds, more direct paths, and lower fractal dimensions than IS mosquitoes, suggesting goal-directed flight. Exposure to permethrin-treated nets triggered erratic flight patterns in both IR and IS mosquitoes, with SHAP analysis identifying key features predictive of irritancy. Comparative analyses using this framework evaluated the performance of different tracking systems, confirming that 2D telecentric imaging matches 3D stereoscopic tracking performance, with singlecamera setups offering similar approximations at long ranges. Additionally, synthetic trajectories enhanced model interpretability by probing decision boundaries. The framework’s versatility and interpretability provide insights that could inform the design of interventions targeting mosquito vulnerabilities, with potential applications to other complex behavioural systems where understanding subtle patterns is essential.",
            "source_url": "https:\/\/openalex.org\/W7128281259",
            "pdf_url": "",
            "doi": "10.82444\/warw.33910837",
            "handle": "",
            "repository_name": "Warwick Research Archive Portal (University of Warwick)",
            "source_record_id": "W7128281259",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 174,
            "title": "Quantum machine learning",
            "title_ar": "",
            "title_en": "Quantum machine learning",
            "author": "Riu Vicente, Jordi",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Universitat Politècnica de Catalunya",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Spain",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "reinforcement-learning",
            "research_subdomain": "quantum-ml",
            "categories": "machine-learning; reinforcement-learning; quantum-ml; optimization",
            "keywords": "",
            "abstract": "We use reinforcement learning techniques to optimize the Quantum Approximate Optimization Algorithm when applied to the MaxCut problem. We explore Q-learning based techniques both for continuous and discrete action environments with regular and irregular graphs.",
            "source_url": "https:\/\/openalex.org\/W7113567326",
            "pdf_url": "https:\/\/upcommons.upc.edu\/bitstreams\/7e0aa1a9-6da4-4f83-8c44-076cb8797aa7\/download",
            "doi": "",
            "handle": "",
            "repository_name": "UPCommons institutional repository (Universitat Politècnica de Catalunya)",
            "source_record_id": "W7113567326",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:47",
            "updated_at": "2026-11-15 16:52:47"
        },
        {
            "id": 193,
            "title": "Graph Neural Networks",
            "title_ar": "",
            "title_en": "Graph Neural Networks",
            "author": "Fernando Gama",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Pennsylvania",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "gnn",
            "categories": "machine-learning; deep-learning; robotics; ai-applications; optimization; gnn; ai-smart-cities",
            "keywords": "",
            "abstract": "The theme of this dissertation is machine learning on graph data. Graphs are generic models of signal structure that play a crucial role in tackling problems in a diverse array of fields, including smart grids, sensor networks, and robot swarms. Thus, developing machine learning models that can successfully learn from graph data is a promising area of research with high potential impact. This dissertation focuses particularly on the topic of graph neural networks (GNNs) as the main machine learning model for successfully addressing problems involving graph data. GNNs are nonlinear representation maps that exploit the underlying graph structure to improve learning and achieve better performance. One of the key properties of GNNs is that they are local and distributed mathematical models, making them particularly relevant for problems involving physical networks. The overarching objective of this dissertation is to characterize the representation space of GNNs. This entails several research directions. First, we define a mathematical framework that provides the general tools and lays the groundwork for the analysis and design of concrete GNN models. Second, we derive fundamental properties and theoretical insights that serve as a foundation for understanding the success observed when employing GNNs in practical problems involving graph data. Third, we explore new application domains that are naturally suited for the use of GNNs based on the properties that these exhibit. We leverage graph signal processing (GSP) and its key concepts of graph filtering and graph frequency domain to provide a general mathematical framework for characterizing GNNs. We derive the properties of permutation equivariance and stability to perturbations of the graph support and use these to explain the improved performance of GNNs over linear graph filers. We also show how these two properties help explain the scalability and transferability of GNNs. We explore the use of GNNs in learning decentralized controllers and showcase their success in the problem of flocking.",
            "source_url": "https:\/\/openalex.org\/W3098598627",
            "pdf_url": "",
            "doi": "10.17023\/h7qz-6762",
            "handle": "",
            "repository_name": "ScholarlyCommons (University of Pennsylvania)",
            "source_record_id": "W3098598627",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:47",
            "updated_at": "2026-11-15 16:52:47"
        },
        {
            "id": 213,
            "title": "Trustworthy AI Under Distribution Shifts: Enhancing Generalization and Fairness in Deep Learning",
            "title_ar": "",
            "title_en": "Trustworthy AI Under Distribution Shifts: Enhancing Generalization and Fairness in Deep Learning",
            "author": "Gezheng Xu",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Western University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Canada",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "fairness",
            "categories": "machine-learning; deep-learning; computer-vision; generative-ai; medical-ai; responsible-ai; transfer-learning; predictive-analytics; optimization; fairness",
            "keywords": "",
            "abstract": "Recent advances in machine learning and deep learning have achieved remarkable success across a wide range of applications, yet they largely rely on data-driven paradigms that assume the training and test data share similar distributions. In real-world scenarios, however, this assumption often fails. Distribution shifts between training and deployment environments or among population subgroups can significantly compromise the performance and reliability of AI systems. Moreover, privacy constraints frequently prevent direct access to source data, and ethical concerns surrounding fairness raise additional challenges for the trustworthy use of AI in sensitive domains such as healthcare and finance. These factors together highlight the urgent need for a deeper and more principled understanding of trustworthy AI under distribution shifts. This thesis examines the influence of distribution shifts along two complementary dimensions of trustworthy AI: generalizability and fairness. On one hand, we focus on the noisy and unreliable signals caused by distribution shift, which place learning in a weak-supervision regime and thereby limit AI systems’ generalizability. On the other hand, we focus on the distribution shifts that arise from structural data imbalance or scarcity rooted in historical and societal factors, which give rise to socially unfavorable model behaviors and, in turn, exacerbate fairness issues in the decision-making process. From the generalizability perspective, the thesis studies the domain adaptation problem under data privacy constraints, formulated as the Source-Free Domain Adaptation (SFDA) problem. SFDA is examined in both classification and regression tasks, with a focus on pseudo-label noise mitigation and uncertainty modeling, respectively. For the classification problem, a noise-robust loss–based noise-and-variance control method (NVC-LLN) is proposed to mitigate the unbounded label noise inherent in SFDA. For the regression task, a histogram-based uncertainty reconstruction framework, MERCI, is proposed to refine continuous supervision signals and align feature presentations under distribution shift. For the fairness problem, this thesis focuses on the multiple-subgroup situation, ranging from a single sensitive attribute with multiple subgroups to multiple sensitive attributes with intersectional bias, covering both unfairness discovery and mitigation. For subgroup discovery, a Bias-Guided Generative Network (BGGN) is proposed to identify underrepresented subgroups instead of relying on traditional search methods. For mitigation, a generalization error bound is derived under the PAC-Bayes framework, motivating a probabilistic-predictor-based bilevel optimization algorithm, FAMS, which achieves both fairness and accuracy across multiple subgroups under limited-data conditions. Collectively, these studies advance the development of responsible, adaptive, and human-centric AI systems. These systems are capable of performing reliably across diverse and dynamic environments.",
            "source_url": "https:\/\/openalex.org\/W7205536362",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Scholarship@Western (Western University)",
            "source_record_id": "W7205536362",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:47",
            "updated_at": "2026-11-15 16:52:47"
        },
        {
            "id": 354,
            "title": "Machine learning for offensive cyber operations",
            "title_ar": "",
            "title_en": "Machine learning for offensive cyber operations",
            "author": "Sommervoll, Åvald Åslaugson",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Norway",
            "governorate": "",
            "publication_year": 2023,
            "language": "en",
            "research_domain": "reinforcement-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; reinforcement-learning; ai-applications; optimization; ai-education; ai-cybersecurity",
            "keywords": "",
            "abstract": "Cybersecurity with machine learning has received widespread attention in education, research, and innovation in both the private and public sectors. Unfortunately, while essential for strong cyber security, offensive cyber operations with machine learning have seen significantly less innovation, at least in open academic literature. This thesis's contribution to the field of offensive cyber operations with machine learning can naturally be divided into the following: 1. Algorithmic cryptanalysis with machine learning 2. SQL injection with machine learning The historical cipher Enigma's plugboard is shown to be susceptible to an attack powered by the machine learning technique Genetic Algorithms, being broken far faster than any earlier attack. Modern ciphers are naturally more robust than historical ciphers. The cryptographic algorithm ASCON is still secure, but the novel machine learning technique, The Phantom Gradient Attack, is shown to attack many of its subfunctions successfully. OWASP's top 10 had SQL injections as the number one web vulnerability in 2017; in 2021, it was number three. This thesis highlights the possibility of automated SQL injection exploitation and identification with reinforcement learning for accelerated penetration testing. The reinforcement learning agent can exploit all 5 SQL injection archetypes, distinguish between them, and determine whether or not the website is vulnerable.",
            "source_url": "https:\/\/openalex.org\/W3188417193",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "NORA - Norwegian Open Research Archives",
            "source_record_id": "W3188417193",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 358,
            "title": "Computational biology in plant tissue culture: Systematic evaluation of machine learning approaches for callus induction in Solanum L.: A thesis submitted in partial fulfilment of the requirements for the Degree of Doctor of Philosophy at Lincoln University",
            "title_ar": "",
            "title_en": "Computational biology in plant tissue culture: Systematic evaluation of machine learning approaches for callus induction in Solanum L.: A thesis submitted in partial fulfilment of the requirements for the Degree of Doctor of Philosophy at Lincoln University",
            "author": "Sadegh Mohajer",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "نص السجل: «Doctor of Philosophy»",
            "university": "Lincoln University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "New Zealand",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "xai",
            "categories": "machine-learning; deep-learning; medical-ai; responsible-ai; ai-applications; transfer-learning; predictive-analytics; optimization; xai; ai-agriculture",
            "keywords": "",
            "abstract": "Optimization of plant tissue culture systems remains a major biotechnological challenge; yet successful callus induction, the formation of unorganized, proliferating cell masses from differentiated tissues, enables transformative applications in agriculture, medicine, and fundamental research. Callus serves as a foundation for genetic transformation and genome editing, mass propagation of elite varieties, production of pharmaceutically valuable secondary metabolites, and breeding programs. However, achieving consistent callus induction is hindered by the multifactorial nature of the process, governed by intricate dependencies among environmental conditions, genetic background, hormonal composition, and explant source. Conventional trial-and-error methodologies are further constrained by the difficulty of systematically capturing and optimizing these complex interactions, resulting in protocols with poor transferability and requiring extensive empirical refinement for each new species or genotype. This study established comprehensive machine learning (ML) frameworks to model and predict callus induction rates in the Solanum genus, one of the most diverse angiosperm genera containing approximately 1,500–2,000 species. This genus includes economically significant crop species such as potato, tomato, and eggplant that sustain global food security, as well as wild relatives possessing valuable traits for disease resistance and abiotic stress tolerance. The genus also includes species of pharmaceutical interest, owing to their diverse alkaloids and secondary metabolites, which exhibit antimicrobial, antioxidant, and anticancer activities. Despite their agricultural, nutritional, and medicinal importance, many Solanum species remain recalcitrant in tissue culture, as standard protocols developed for model cultivars often perform poorly when applied to wild species and new genotypes. The ML methods developed here systematically evaluate modeling strategies ranging from global to local approaches, with the goal of addressing the protocol optimization bottleneck that constrains biotechnological applications across this economically and scientifically important genus. Five machine learning algorithms were evaluated: Random Forest and XGBoost as tree-based ensemble models, Support Vector Regression, and Gaussian Process Regression as kernel-based methods, and an artificial neural network (multilayer perceptron) with genetic algorithm optimization for hyperparameter tuning and protocol development. Model interpretability was achieved through SHAP analysis and permutation importance assessment. Genetic algorithm optimization of neural networks identified optimal protocols achieving remarkable callus induction rates, representing substantial improvements over conventional approaches. Feature optimization revealed specific strategies ranging from minimal hormone supplementation to comprehensive growth regulator networks. Sensitivity analysis confirmed that environmental precision provides primary control mechanisms, with hormonal supplementation serving as fine tuning parameters rather than primary drivers. The thesis advances both methodology and biological understanding. It establishes a rigorous methodological framework integrating systematic preprocessing, cross-validation with independent holdout data, and comprehensive interpretability analysis. The approach delivers predictive models with quantified uncertainty and clear performance boundaries. Biologically, the work demonstrates that machine learning can successfully capture complex tissue culture interactions. These findings represent a paradigm shift from empirical protocol development to data-driven optimization, with applications across plant biotechnology, crop improvement, pharmaceutical compound production, and conservation. The work may also motivate future steps that include transfer learning across species, imaging-based phenotyping with deep learning, classification of callus quality tiers, and time-resolved modeling of induction dynamics.",
            "source_url": "https:\/\/openalex.org\/W7131545409",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Lincoln University Research Archive (Lincoln University)",
            "source_record_id": "W7131545409",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "id": 367,
            "title": "Application of Machine Learning in Peptide Design",
            "title_ar": "",
            "title_en": "Application of Machine Learning in Peptide Design",
            "author": "Sabino Sepčić",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; optimization",
            "keywords": "",
            "abstract": "The main purpose of this thesis is to explore the use of computational techniques such as machine learning and genetic algorithms in peptide design. P",
            "source_url": "https:\/\/openalex.org\/W3093245414",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W3093245414",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:49",
            "updated_at": "2026-11-15 16:52:49"
        },
        {
            "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": 508,
            "title": "Meta Learning for Graph Neural Networks",
            "title_ar": "",
            "title_en": "Meta Learning for Graph Neural Networks",
            "author": "Rohan Dhamdhere",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Rochester Institute of Technology",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "image-segmentation",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; optimization; cnn; gnn; image-classification; image-segmentation; video-analysis",
            "keywords": "",
            "abstract": "Deep learning has enabled incredible advances in pattern recognition such as the fields of computer vision and natural language processing. One of the most successful areas of deep learning is Convolutional Neural Networks (CNNs). CNNs have helped improve performance on many difficult video and image understanding tasks but are restricted to dense gridded structures. Further, designing their architectures can be challenging, even for image classification problems. The recently introduced graph CNNs can work on both dense gridded structures as well as generic graphs. Graph CNNs have been performing at par with traditional CNNs on tasks such as point cloud classification and segmentation, protein classification and image classification, while reducing the complexity of the network. Graph CNNs provide an extra challenge in designing architectures due to more complex weight and filter visualization of generic graphs. Designing neural network architectures, yielding optimal performance, is a laborious and rigorous process. Hyperparameter tuning is essential for achieving state of the art results using specific architectures. Using a rich suite of predefined mutations, evolutionary algorithms have had success in delivering a high-quality population from a low-quality starter population. This thesis research formulates the graph CNN architecture design as an evolutionary search problem to generate a high-quality population of graph CNN model architectures for classification tasks on benchmark datasets.",
            "source_url": "https:\/\/openalex.org\/W2923863837",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "RIT Scholar Works (Rochester Institute of Technology)",
            "source_record_id": "W2923863837",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 527,
            "title": "Robots Need Some Education: On the complexity of learning in evolutionary robotics",
            "title_ar": "",
            "title_en": "Robots Need Some Education: On the complexity of learning in evolutionary robotics",
            "author": "Fuda van Diggelen",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "responsible-ai",
            "research_subdomain": "fairness",
            "categories": "machine-learning; robotics; responsible-ai; ai-applications; optimization; fairness; ai-education",
            "keywords": "",
            "abstract": "Evolutionary Robotics and Robot Learning are two fields in robotics that aim to automatically optimize robot designs. The key difference between them lies in what is being optimized and the time scale involved. Evolutionary Robotics is a field that applies evolutionary computation techniques to evolve the morphologies or controllers, or both. Robot Learning, on the other hand, involves any learning technique aimed at optimizing a robot's controller in a given morphology. In terms of time scales, evolution occurs across multiple generations, whereas learning takes place within the 'lifespan' of an individual robot. The long-term goal of Evolutionary Robotics is to create adaptive systems where a population of robots evolve autonomously, optimizing both their physical structure and control system through an evolutionary process. In the context of evolution, adaptability is a trait of the population. Conversely, when it comes to learning, it is the robots' controller that exhibits adaptability. In the end, both forms of adaptation aim to enhance the robots' task performance. Integrating Robot Learning with Evolutionary Robotics seems like a natural fit for improving robot design. Unfortunately, integration requires the careful design of suitable learning algorithms in the context of evolutionary robotics. The effects of introducing learning into the evolutionary process are not well-understood and can thus be tricky. This thesis investigates these intricacies and presents several learning algorithms developed for an Evolutionary Robotics context. My dissertation is structured into three parts: Part I - investigates the complex interaction between learning algorithms and evolutionary processes, provides statistical tools for evaluating different learning algorithms, and explores the dynamics of optimization and the reality gap. The interactions present a counterintuitive finding: learning can negatively affect the evolutionary process. Learning can bias evolution by converging to simple designs that learn quickly, overfitting simulators and exacerbating the reality gap. Part II - investigates model-agnostic learning methods for autonomous robots. Evolutionary algorithms can produce arbitrary robot designs for environments with minimal prior knowledge. This presents a challenging requirement for learning. Nevertheless, robots are expected to be able to autonomously perform tasks 'in the wild'. Here, I cover continuous self-modeling for adaptive feedback control and rapid skill acquisition for quickly learning locomotion. Part III - explores how learning can be extended beyond individual robot. In group settings, swarms of robots can obtain abilities beyond that of any individual robot inside. Here, I demonstrate how such emergent capabilities can be learned and used to solve complex tasks, both in homogeneous and heterogeneous populations of robots. Overall, this thesis offers a comprehensive analysis of Robot Learning within the context of Evolutionary Robotics presented as a collection of peer-reviewed works. Each part of the dissertation combines rigorous theoretical analysis with practical hardware implementations, demonstrating the validity of the ideas presented. As a result, my thesis provides unique insights into how an evolving population of robots can effectively integrate learning. From the 'birth' of a robot, learning about its environment, to its 'adulthood' as a functioning member of a robotic society.",
            "source_url": "https:\/\/openalex.org\/W4408010328",
            "pdf_url": "",
            "doi": "10.5463\/thesis.1004",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W4408010328",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 561,
            "title": "Evolutionary game theoretic models for natural language processing",
            "title_ar": "",
            "title_en": "Evolutionary game theoretic models for natural language processing",
            "author": "Rocco Tripodi",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Università Ca' Foscari Venezia",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Italy",
            "governorate": "",
            "publication_year": 2016,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "self-semi-supervised",
            "categories": "machine-learning; nlp; ai-applications; self-semi-supervised; data-mining; optimization; ai-education",
            "keywords": "",
            "abstract": "This thesis is aimed at discovering new learning algorithms inspired by principles of biological evolution, which are able to exploit relational and contextual information, viewing clustering and classification problems in a dynamical system perspective. In particular, we have investigated how game theoretic models can be used to solve different Natural Language Processing tasks. Traditional studies of language have used a game-theoretic perspective to study how language evolves over time and how it emerges in a community but to the best of our knowledge, this is the first attempt to use game-theory to solve specific problems in this area. These models are based on the concept of equilibrium, a state of a system, which emerges after a series of interactions among the elements, which are part of it. Starting from a situation in which there is uncertainty about a particular phenomenon, they describe how a disequilibrium state resolves in equilibrium. The games are situations in which a group of objects has to be classified or clustered and each of them has to choose its collocation in a predefined set of classes. The choice of each one is influenced by the choices of the other and the satisfaction that a player has, about the outcome of a game, is determined by a payoff function, which the players try to maximize. After a series of interactions the players learn to play their best strategies, leading to an equilibrium state and to the resolution of the problem. From a machine-learning perspective this approach is appealing, because it can be employed as an unsupervised, semi-supervised or supervised learning model. We have used it to resolve the word sense disambiguation problem. We casted this task as a constraint satisfaction problem, where each word to be disambiguated is con- strained to choose the most coherent sense among the available, according to the sense that the words around it are choosing. This formulation ensures the mainte- nance of textual coherence and has been tested against state-of-the-art algorithms with higher and more stable results. We have also used a game theoretic formulation, to improve the clustering results of dominant set clustering and non-negative matrix factorization technique. We evaluated our system on different document datasets through different approaches, achieving results, which outperform state-of-the-art algorithms. This work opened new perspectives in game theoretic models, demonstrating that these approaches are promising and that they can be employed also for the resolution of new problems.",
            "source_url": "https:\/\/openalex.org\/W2509969451",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "ARCA (Università Ca' Foscari Venezia)",
            "source_record_id": "W2509969451",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 576,
            "title": "Optimization Methods for Semi-Supervised Learning",
            "title_ar": "",
            "title_en": "Optimization Methods for Semi-Supervised Learning",
            "author": "Edward Cheung",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Waterloo",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Canada",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "self-semi-supervised",
            "categories": "machine-learning; medical-ai; self-semi-supervised; predictive-analytics; optimization",
            "keywords": "",
            "abstract": "The goal of this thesis is to provide efficient optimization algorithms for some semi-supervised learning (SSL) tasks in machine learning. For many machine learning tasks, training a classifier requires a large amount of labeled data; however, providing labels typically requires costly manual annotation. Fortunately, there is typically an abundance of unlabeled data that can be easily collected for many domains. In this thesis, we focus on problems where an underlying structure allows us to leverage the large amounts of unlabeled data, while only requiring small amounts of labeled data. In particular, we consider low-rank matrix completion problems with applications to recommender systems, and semi-supervised support vector machines (S3VM) to solve binary classification problems, such as digit recognition or disease classification. For the first class of problems, we study convex approximations to the low-rank matrix completion problem. Instead of restricting the solution space to low-rank matrices, we use the trace norm as a convex surrogate. Unfortunately, many trace norm minimization algorithms scale very poorly in practice since they require a full singular value decomposition (SVD) at each iteration. Recently, there has been renewed interest in the trace norm constrained problem utilizing the Frank-Wolfe algorithm, which only requires calculating the leading singular vector pair, providing an order of magnitude improvement on the iteration complexity. However, the Frank-Wolfe algorithm empirically has very slow convergence and in practice yields high-rank solutions, which greatly increases computational costs. To address this issue, we investigate a rank-drop step for Frank-Wolfe, which solves a subproblem specifically designed to decrease the rank of the iterate, ensuring that the Frank-Wolfe algorithm converges along a low-rank path. We show that this rank-drop subproblem can be decomposed into two cases, where each subproblem can be solved efficiently and we guarantee that the iterates remain feasible, preserving the projection-free property of Frank-Wolfe. Next we show that these ideas can be used to provide scalable algorithms for simultaneously sparse and low-rank matrix completion problems. We extend the Frank-Wolfe analysis to accommodate nonsmooth objectives, which can be used to solve the simultaneously sparse and low-rank problem. We replace the traditional linear approximation used in Frank-Wolfe by a uniform affine approximation to better address poor local approximations given by the first-order Taylor approximation. We show that this naturally leads to a sequence of smooth functions that uniformly converges to the original nonsmooth objective, allowing for a careful balance between approximation quality and convergence that is closely related to the step sizes of the Frank-Wolfe algorithm. We apply this algorithm to solve sparse covariance estimation problems, graph link prediction, and robust matrix completion problems. Finally, we propose a variant of self-training for the semi-supervised binary classification problem by leveraging ideas from S3VM. To address common issues associated with self-training, such as error propagation and label imbalances, we proposed an adaptive scheme using the functional margin of S3VM to construct a confidence measure. The confidence score is used to create rules to adapt the optimization problems to incorporate label uncertainty and class imbalances. Moreover, we show that the incremental training approach leverages warm-starts very well, leading to much faster training than standard S3VM methods alone, with much stronger empirical performance on imbalanced datasets.",
            "source_url": "https:\/\/openalex.org\/W2803599927",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "UWSpace (University of Waterloo)",
            "source_record_id": "W2803599927",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:50",
            "updated_at": "2026-11-15 16:52:50"
        },
        {
            "id": 601,
            "title": "Generative and geometric deep learning for 3D genome organization and biomolecular interaction modeling",
            "title_ar": "",
            "title_en": "Generative and geometric deep learning for 3D genome organization and biomolecular interaction modeling",
            "author": "Yanli Wang",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Missouri",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; nlp; generative-ai; medical-ai; predictive-analytics; optimization; gnn; llm; gan; diffusion",
            "keywords": "",
            "abstract": "The three-dimensional organization of the genome and the interactions between biomolecules are fundamental to understanding cellular function and disease. Recent advances in sequencing technologies and structural biology have generated unprecedented amounts of biological data, creating new opportunities to study these processes. However, these data are often sparse, noisy, and highly complex, making it difficult to accurately model biological systems using conventional computational methods. This dissertation explores how generative and geometric deep learning can address these challenges by learning meaningful biological representations from high-dimensional genomic and structural data. The first part of this dissertation focuses on modeling three-dimensional genome organization from single-cell Hi-C data. Because single-cell Hi-C experiments capture only a small fraction of chromatin interactions, computational methods are essential for recovering missing information and revealing genome architecture. I first developed a deep residual generative adversarial network to enhance sparse single-cell Hi-C contact maps by recovering biologically meaningful chromatin interactions. Building on this work, I proposed HiCDiff, a diffusion model that iteratively denoises chromatin contact maps and produces more accurate representations of genome organization. These improved contact maps provide a stronger foundation for downstream analyses and structural modeling. To further characterize genome architecture, I developed an SO(3)-equivariant graph neural network that reconstructs three-dimensional chromosome structures directly from single-cell Hi-C data. By incorporating geometric equivariance into the learning process, the model captures the spatial relationships among genomic loci and reconstructs chromosome conformations with improved accuracy and biological consistency. The second part of this dissertation extends geometric deep learning to biomolecular interaction modeling. I developed MPBind, a multitask framework for predicting protein binding sites by integrating protein language model embeddings with equivariant graph neural networks. This approach combines evolutionary information encoded in protein sequences with three-dimensional structural features, enabling accurate prediction of diverse protein interactions while achieving strong generalization across previously unseen proteins. Although these studies address different biological problems, they share a common theme: combining generative models with geometry-aware neural networks to learn from complex biological data. Generative deep learning improves the quality of sparse and noisy experimental measurements, while geometric deep learning enables models to capture the structural principles underlying biological systems. Together, the methods presented in this dissertation provide a unified framework for studying genome organization and biomolecular interactions, demonstrating how modern artificial intelligence can advance computational genomics and structural biology and support future discoveries in biology and precision medicine.",
            "source_url": "https:\/\/openalex.org\/W7224088771",
            "pdf_url": "",
            "doi": "10.32469\/10355\/113055",
            "handle": "",
            "repository_name": "MOspace Institutional Repository (University of Missouri)",
            "source_record_id": "W7224088771",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 623,
            "title": "Learning Tetris with reinforcement learning",
            "title_ar": "",
            "title_en": "Learning Tetris with reinforcement learning",
            "author": "Ioannis Tsirovasilis ; Ιωάννης Τσιροβασίλης",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Piraeus",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Greece",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "video-analysis",
            "categories": "machine-learning; computer-vision; reinforcement-learning; optimization; video-analysis",
            "keywords": "",
            "abstract": "The last decades, scientists have expressed an increasing interest for the game Tetris and more precisely for efficient algorithms that can score the most in-game points. A plethora of approaches have been tried out, including genetic algorithms, linear programming, cross-entropy and natural policy gradient, but none of them competes with experts players playing under no time pressure. In recent years, scientists have started applying reinforcement learning in Tetris as it displays effective results in adapting to video game environments, exploit mechanisms and deliver extreme performances. Current thesis aims to introduce Memory Based Learning, a reinforcement learning algorithm which uses a memory that helps in the training process by replaying past experiences.",
            "source_url": "https:\/\/openalex.org\/W3214945965",
            "pdf_url": "",
            "doi": "10.26267\/unipi_dione\/1314",
            "handle": "",
            "repository_name": "Dione (University of Piraeus)",
            "source_record_id": "W3214945965",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:51",
            "updated_at": "2026-11-15 16:52:51"
        },
        {
            "id": 787,
            "title": "Federated Learning of Fuzzy Rule-based Systems: Advances in Privacy, Security and Interpretability",
            "title_ar": "",
            "title_en": "Federated Learning of Fuzzy Rule-based Systems: Advances in Privacy, Security and Interpretability",
            "author": "Mattia Daole",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Pisa",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Italy",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "responsible-ai",
            "research_subdomain": "federated-learning",
            "categories": "machine-learning; responsible-ai; expert-systems; ai-applications; predictive-analytics; optimization; xai; federated-learning; fairness; ai-cybersecurity",
            "keywords": "",
            "abstract": "This thesis addresses the growing need for Trustworthy AI, focusing on the transparency and privacy requirements. Transparency is commonly addressed through eXplainable AI (XAI), while privacy-preserving paradigms such as Federated Learning (FL) enable collaborative model training without sharing sensitive data. The work extends traditional Fuzzy Rule-Based Classifiers (FRBCs) to federated settings, systematically analyzing their learning behavior and performance under heterogeneous and non-IID data distributions. To further improve the trade-off between predictive accuracy and interpretability, a multi-objective federated framework based on Evolutionary Fuzzy Systems is introduced, using synthetic data generation techniques to support privacy-preserving server-side optimization. In addition to model design, the thesis investigates security aspects by analyzing classical adversarial threats in FL, such as data and model poisoning, and by proposing a taxonomy of attacks specifically targeting federated FRBCs. Finally, an edge-oriented application framework compliant with Multi-Access Edge Computing architectures is presented, demonstrating the practical feasibility and effectiveness of deploying trustworthy, transparent, and privacy-aware AI systems in real-world distributed environments.",
            "source_url": "https:\/\/openalex.org\/W7140251669",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Electronic Theses and Dissertations Repository (University of Pisa)",
            "source_record_id": "W7140251669",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "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": 803,
            "title": "Hyperparameter Optimization of Convolutional Neural Networks (CNN) using an Adaptive Particle Swarm Optimization (PSO) and Genetic Algorithm (GA)",
            "title_ar": "",
            "title_en": "Hyperparameter Optimization of Convolutional Neural Networks (CNN) using an Adaptive Particle Swarm Optimization (PSO) and Genetic Algorithm (GA)",
            "author": "charles usigbe",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "London South Bank University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "cnn",
            "categories": "machine-learning; deep-learning; optimization; cnn",
            "keywords": "",
            "abstract": "",
            "source_url": "https:\/\/openalex.org\/W7170046797",
            "pdf_url": "",
            "doi": "10.18744\/77554c5f-2daa-4485-9ace-1723f37b3638",
            "handle": "",
            "repository_name": "Research Open (London South Bank University)",
            "source_record_id": "W7170046797",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 804,
            "title": "Optimization of neural network hyperparameters using metaheuristic algorithms",
            "title_ar": "",
            "title_en": "Optimization of neural network hyperparameters using metaheuristic algorithms",
            "author": "Riihimäki, Mikko",
            "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": "cnn",
            "categories": "machine-learning; deep-learning; optimization; cnn",
            "keywords": "",
            "abstract": "This thesis compares four hyperparameter search methods for tuning a compact convolutional neural network on CIFAR-10 under a uniform setup. The methods are grid search and three population-based metaheuristics, particle swarm optimization, genetic algorithms, and grey wolf optimization. The search space is limited to learning rate and dropout to isolate the effect of the search strategy. Each run has a budget of 50 model evaluations. All evaluations use the same protocol with 5 epochs, batch size 64 and a fixed stratified split. The study assesses three aspects of performance. First, the best validation accuracy reached within budget. Second, evaluation efficiency measured by the index of the first occurrence of the best score. Third, runtime reported as time to best and time to 95 percent of best. The configuration that yields the best validation score is retained on the full training set and then evaluated once on the test set. The methods achieve very similar best validation accuracies. The metaheuristics typically reach near best scores early, which appears as a shorter time to 95 percent of best. Grid search progresses in discrete steps and on average reaches the eventual best earlier and with lower variability. Test accuracy mirrors validation without large gaps. Metaheuristics are a practical choice when fast good solutions are needed, while a compact grid remains a strong baseline when the full budget is used. The study is limited by a narrow search space, short training, and CPU-only execution.",
            "source_url": "https:\/\/openalex.org\/W7112920518",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Aaltodoc (Aalto University)",
            "source_record_id": "W7112920518",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 805,
            "title": "An optimized internet of vehicles network for safety-based messages transmission using particle swarm optimization",
            "title_ar": "",
            "title_en": "An optimized internet of vehicles network for safety-based messages transmission using particle swarm optimization",
            "author": "Shahirah Mohamed Hatim",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Universiti Teknologi MARA",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Malaysia",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; ai-applications; optimization; ai-smart-cities",
            "keywords": "",
            "abstract": "This thesis addresses the problem of traffic congestion, which arises from increased vehicular queuing when the packet transmission load in the network exceeds the available buffer capacity. This condition leads to slower travel speed and also delays in travel time. Many urban cities worldwide have experienced severe congestion challenges. However, with the aid of the Internet of Things (IoT), the traffic congestion problem in the event can be managed effectively as vehicles are now equipped with sensors, actuators, data acquisition and communication systems that enable inter-vehicle communication. The Internet of Vehicles (IoV) has emerged as a key mechanism in in managing traffic congestion within modern Intelligent Transportation Systems (ITS), providing extensive opportunities for safety and mobility applications. This networking technology, provides vehicles with endless possibilities of applications including safety-related applications. Due to the high speed, dynamic mobility and unstable connectivity of vehicular nodes, maintaining stable IoV network performance remains a challenge. Previous research has explored various congestion control optimization techniques such Genetic Algorithm, Ant Colony and Ant Bee Colony for vehicular networks. While these methods improved performance to some extent, they often suffer from high computational complexity or slow convergence, limiting their suitability for real-time IoV environments. The recent proliferation of IoV network has emphasized the need for high Quality of Service (QoS) requirements in all networking scenarios. This study provides a comprehensive evaluation of the impact of vehicular mobility on IoV network performance. The analysis focuses on key QoS metrics, namely throughput, packet delivery ratio (PDR) and delay, while examining the relationship between mobility factors and medium access behaviour under varying network conditions. In achieving better performance in the QoS of the IoV network, a bio-inspired optimization approach based on the Particle Swarm Optimization (PSO) algorithm is proposed to mitigate network performance degradation caused by high node mobility. Vehicle mobility data is obtained from traffic flow simulation in SUMO and the network simulation phase is conducted in OMNeT++. Safety messages are disseminated among vehicles within the network. The experiment for the IoV network is concluded by optimizing the transmission rate to minimize the delay as the objective function in PSO algorithm. To ensure stable performance evaluation under dynamic vehicular conditions, simulations were conducted using varying simulation times and numbers of vehicles to capture both temporal network behaviour and traffic density variations. Under these settings, the throughput of the IoV network recorded average improvements of up to 23% and 14% after optimization. Packet delivery ratio (PDR) was also enhanced, with average gains of up to 37% and 15%, while network delay was reduced by up to 12% and 15% across different simulation times and vehicle densities. These results highlight the effectiveness of the optimization in improving IoV network performance under diverse conditions. The proposed PSO-based approach introduces a dynamic transmission rate control mechanism that adapts to vehicular density, effectively reducing congestion on the control channel. Overall, the findings highlight the potential for future research and practical applications in vehicular communication systems.",
            "source_url": "https:\/\/openalex.org\/W7170115999",
            "pdf_url": "https:\/\/ir.uitm.edu.my\/id\/eprint\/142641\/1\/142641_fulltext.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "UiTM Institutional Repositories (Universiti Teknologi MARA)",
            "source_record_id": "W7170115999",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 806,
            "title": "OPTIMIZING CONVOLUTIONAL NEURAL NETWORKS VIA GENETIC ALGORITHM-BASED PRUNING",
            "title_ar": "",
            "title_en": "",
            "author": "João Silva",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Portugal",
            "governorate": "",
            "publication_year": 2025,
            "language": "pt",
            "research_domain": "computer-vision",
            "research_subdomain": "cnn",
            "categories": "machine-learning; deep-learning; computer-vision; transfer-learning; optimization; cnn",
            "keywords": "",
            "abstract": "As redes neurais têm experienciado um crescimento significativo no seu tamanho e complexidade nos últimos anos, levando a avanços notáveis em diversas áreas da inteligência artificial. No entanto, este aumento exponencial no seu número de parâmetros e das necessidades computacionais tem trazido desafios consideráveis, especialmente quando se trata de implementar estes modelos em ambientes com recursos limitados. Além disso, esta exigência computacional dos modelos de Deep Learning tem contribuído para um maior consumo de energia, gerando preocupações económicas e ambientais. Como consequência, reduzir o tamanho e a carga computacional das redes neurais tornou-se um objetivo essencial para alcançar soluções de Deep Learning mais eficientes, escaláveis e sustentáveis. Este trabalho propõe uma abordagem de pruning estruturado para lidar com este desafio, tratando o pruning comouma tarefa de optimização multiobjetivo e recorrendo a um Algoritmo Genético(AG)paraidentificar subredes optimizadas na arquitetura VGG-16 aplicada à tarefa de classificação de imagem com o dataset CIFAR10. Os filtros da rede são representados como um genoma que evolui iterativamente através de processos de seleção natural para encontrar o equilíbrio ideal entre desempenho e eficiência computacional. Devido ao elevado custo computacional das avaliações, utilizou-se uma estratégia de mitigação onde o AG foi treinado e avaliado em apenas 25% do dataset CIFAR-10. A aptidão de cada indivíduo é avaliada com base numa função que pondera a preservação da precisão (40%) e a redução do custo computacional total (NumOps, 60%). Resultados quantitativos demonstram que, em cenários de fine-tuning, o AG superou o método tradicional de pruning por norma L1 em todos os níveis de esparsidade testados, alcançando 88,31% de precisão com 50% de esparsidade, o que representa uma redução de 51,42% no custo computacional (7,14 milhões de operações) face ao modelo base. No entanto, em cenários de reinicialização, embora o AG tenha atingido 92,02% de precisão com 25% de esparsidade (superando o modelo base de 91,05% e reduzindo as operações em 20,46%), não igualou a precisão superior obtida pelo método L1-norm(94,70%). Aumnívelextremode75esparsidade, oalgoritmofalhouemevoluirsoluções viáveis devido à estagnação do espaço de busca. As principais observações revelam que o AG desenvolveu uma estratégia adaptativa inteligente por camada, aprendendo a preservar as camadas iniciais cruciais para a extração de características enquanto aplicava um pruning mais agressivo nas camadas finais. O principal contributo deste trabalho é o desenvolvimento de um framework de pruning evolutivo que descobre configurações arquiteturais eficientes, revelando-se particularmente valioso para a optimização de modelos pré-treinados em contextos reais onde o re-treino total do modelo a partir do zero é impraticável.",
            "source_url": "https:\/\/openalex.org\/W7217945665",
            "pdf_url": "https:\/\/ciencipca.ipca.pt\/bitstreams\/9a8cd140-4f78-482f-b126-23e9d295b2ea\/download",
            "doi": "",
            "handle": "",
            "repository_name": "CiencIPCA",
            "source_record_id": "W7217945665",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 807,
            "title": "Simultaneous Shape, Size, and Topology Optimization of Truss Structures Using Graph Neural Networks and Metaheuristic Algorithms",
            "title_ar": "",
            "title_en": "Simultaneous Shape, Size, and Topology Optimization of Truss Structures Using Graph Neural Networks and Metaheuristic Algorithms",
            "author": "Ali Mosalli",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "gnn",
            "categories": "machine-learning; deep-learning; predictive-analytics; optimization; gnn",
            "keywords": "",
            "abstract": "This study presents a unified framework for the analysis and optimization of truss structures through the integration of Graph Neural Networks (GNNs) and metaheuristic algorithms. The proposed approach performs simultaneous size, shape, and topology optimization with the objective of minimizing structural weight while satisfying code-based constraints on strength, serviceability, and stability. Conventional optimization methods can become computationally expensive for complex truss systems, particularly when geometric nonlinear behavior is considered. To address this challenge, a physics-informed, dataset-free GNN framework is developed for structural analysis under both linear and geometric nonlinear conditions. The GNN model predicts nodal displacements, from which member forces and stresses are computed, based on structural characteristics such as geometry, connectivity, and loading conditions. The model is validated against finite element analysis results obtained from the commercial finite element software package SAP2000, demonstrating strong agreement and reliable predictive performance. Within the optimization framework, finite element analysis, implemented using a developed Python based direct stiffness method, is used for linear cases due to its efficiency, while the GNN model is directly integrated into the optimization loop for geometric nonlinear analysis, enabling efficient evaluation of candidate designs. Metaheuristic algorithms, including Particle Swarm Optimization, Genetic Algorithm, and Harmony Search, are used to explore the design space. The framework is evaluated through multiple benchmark truss examples, including a pedestrian bridge structure. A comparative evaluation of the optimization algorithms highlights differences in convergence behavior and solution stability. For the pedestrian bridge example, the strength-to-weight ratio is also assessed to provide a more comprehensive measure of structural efficiency. Overall, this research demonstrates the potential of GNN-based approaches as scalable, data-efficient, and code-compliant tools for structural analysis and optimization.",
            "source_url": "https:\/\/openalex.org\/W7160382209",
            "pdf_url": "",
            "doi": "10.11575\/prism\/51368",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W7160382209",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 808,
            "title": "Multi-objective optimization of composite sandwich structures by using artificial neural network and genetic algorithm",
            "title_ar": "",
            "title_en": "Multi-objective optimization of composite sandwich structures by using artificial neural network and genetic algorithm",
            "author": "Al-Hamzawi, Mortda Mohammed Sahib",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "اسم المستودع يخص أطاريح الدكتوراه: REAL-PhD (Hungarian Academy of Sciences)",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Hungary",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; deep-learning; optimization",
            "keywords": "",
            "abstract": "",
            "source_url": "https:\/\/openalex.org\/W7106694290",
            "pdf_url": "https:\/\/real-phd.mtak.hu\/2441\/1\/Mortda_Mohammed_Sahib_Al-Hamzawi_ert_doi.pdf",
            "doi": "10.14750\/me.2025.049",
            "handle": "",
            "repository_name": "REAL-PhD (Hungarian Academy of Sciences)",
            "source_record_id": "W7106694290",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 809,
            "title": "Multi-layer artificial neural network optimization using genetic algorithms and particle swarm",
            "title_ar": "",
            "title_en": "",
            "author": "Leonardo de Queiroz Dantas",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2017,
            "language": "pt",
            "research_domain": "deep-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; deep-learning; optimization",
            "keywords": "",
            "abstract": "As pesquisas na área de Redes Neurais Artificiais são caracterizadas pelo desenvolvimento de algoritmos inspirados no funcionamento do sistema nervoso que apresentam diversas aplicações, como classificação de dados. Porém, seu funcionamento depende de um processo de treinamento que, em alguns casos, pode consumir tempo e ter um custo elevado. Este trabalho apresenta uma proposta de técnica de otimização para Redes do tipo MultiLayer Perceptron (MLP), integrando os benefícios de duas categorias de algoritmos de otimização: Algoritmos Genéticos (AG) e Otimização por Enxame de Partículas (PSO – Particle Swarm Optimization). Tal técnica será utilizada para realizar a otimização simultânea da arquitetura e de seus pesos sinápticos, com o objetivo de buscar redes com boas arquiteturas, isto é, com o mínimo de neurônios e com um bom desempenho para cada problema, tudo de forma automática. E, assim, diminuir custos e tempo para a utilização das MLPs. Os resultados mostram que as redes otimizadas segundo o modelo proposto foram eficientes, pois geraram redes MLPs com boas acurácias e, simultaneamente, com boas arquiteturas.",
            "source_url": "https:\/\/openalex.org\/W7120352733",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)",
            "source_record_id": "W7120352733",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 810,
            "title": "Short-Term Load Forecasting Using A Hybrid Of Genetic Algorithm (Ga) And Particle Swarm Optimization (Pso) For An Optimized Neural Network",
            "title_ar": "",
            "title_en": "Short-Term Load Forecasting Using A Hybrid Of Genetic Algorithm (Ga) And Particle Swarm Optimization (Pso) For An Optimized Neural Network",
            "author": "Stephen T Siri",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Nairobi",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Kenya",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "predictive-analytics",
            "categories": "machine-learning; deep-learning; predictive-analytics; optimization",
            "keywords": "",
            "abstract": "Short-term load forecasting (STLF) has emerged as one of the most important fields of study for power system operation for system efficiency and reliability. It plays a significant role in load flow analysis, contingency analysis, planning, scheduling and maintenance of power systems facilities; therefore, the system cost-effectiveness is determined by accurate load forecast. Numerous researchers have been done to improve the accuracy of the conventional methods such as time series, regression analysis or autoregressive moving average (ARMA) and the use of Artificial Neural Networks (ANNs) in load forecasting. ANN has shown more accurate results than the others. But the training of ANNs, with a back-propagation algorithm or gradient algorithms, requires long processing time has the difficulty in selecting the optimal order of the components and trapping in local minima. This research aimed at solving this problem by proposing a hybrid method based on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for training and optimizing the weights of ANN. The proposed hybrid method enables a reduction in the search space and the iteration time. The proposed algorithm was tested in MATLAB 2016® software using 24 hourly load data of different days (i.e. weekdays and weekends) from Juba Power Plant (JPP), South Sudan. PSO, GA and a hybrid of genetic algorithm with particle swarm optimization (HGAPSO) and ANN were studied and the resulting mean absolute percentage error (MAPE) found to be range from 1.9% to 3.40%, 2.23% to 3.65% and 1.47% to 1.98% respectively. The results obtained were compared and it was observed that HGAPSO-ANN method has a better performance in reducing and improving forecast error compared to PSO-ANN and GA-ANN methods. Therefore, a hybridized HGAPSO algorithm with ANN improves forecast accuracy.",
            "source_url": "https:\/\/openalex.org\/W2936546245",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "University of Nairobi Research Archive (University of Nairobi)",
            "source_record_id": "W2936546245",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 811,
            "title": "Many-objective optimization with particle swarm optimization algorithm",
            "title_ar": "",
            "title_en": "",
            "author": "Freire, Hélio Alves",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "نص السجل: «tese de doutoramento»",
            "university": "Universidad De Tras-os Montes e Alto Douro",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Portugal",
            "governorate": "",
            "publication_year": 2017,
            "language": "pt",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; optimization",
            "keywords": "",
            "abstract": "Muitos dos problemas de optimização envolvem diversos objectivos sujeitos a algumas restrições e que devem ser considerados simultaneamente. Ao contrário dos problemas uni-objectivo em que se procura a solução óptima global, a resolução dos problemas com múltiplos objectivos dão origem a um conjunto de soluções, chamado frente de Pareto. Nas últimas duas décadas os algoritmos evolutivos conjuntamente com o princípio da dominância de Pareto têm demonstrado uma grande capacidade para obter um conjunto de soluções próximas da frente óptima de Pareto. Esta situação tem-se verificado principalmente para problemas com dois ou três objectivos. Nos últimos anos tem-se levado os algoritmos evolutivos a resolver problemas com mais de três objectivos, denominados many-objective. Os algoritmos evolutivos e métodos baseados no princípio da dominância de Pareto desenvolvidos para resolver problemas com dois ou três objectivos, têm-se mostrado desadequados para problemas many-objective. Uma das questões centrais com os problemas de optimização many-objective usando a dominância de Pareto é que praticamente toda a população se torna não-dominada numa etapa em que a população ainda se encontra muito longe da frente óptima de Pareto. A selecção das “boas\" soluções para recombinação com a restante população torna-se praticamente aleatória, tornando difícil a convergência da população para a frente óptima de Pareto. O princípio básico desenvolvido nesta tese de doutoramento é colocar algumas soluções próximas da frente óptima de Pareto na população, denominadas corner solutions, dos algoritmos evolutivos multi-objectivo. Para encontrar as corner solutions foi desenvolvido o algoritmo Corner MOPSO que aproveita os bons resultados demonstrados pelos algoritmos evolutivos e pelo princípio da dominância de Pareto para problemas com dois objectivos. Neste algoritmo faz-se uma transformação de um problema many-objective em diversos problemas bi-objective. Foram usados três algoritmos evolutivos, de paradigmas diferentes, um algoritmo genético, o NSGA-II, um particle swarm, o SMPSO e um algoritmo differential evolution, o GDE3, onde são introduzidos as corner solutions. O algoritmo é testado para a família de problemas benchmark DTLZ, mais propriamente os problemas DTLZ1, DTLZ2, DTLZ3, DTLZ4 e DTLZ5, com o número de objectivos, para cada um dos problemas, variando entre 4 e 10. Os métodos desenvolvidos são aplicados para projectar estruturas de controlo com controlador PID, considerando uma perspectiva many-objective. O objectivo é ajustar os parâmetros do controlador PID para diferentes sistemas.",
            "source_url": "https:\/\/openalex.org\/W2619656652",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Repository of UTAD (Universidad De Tras-os Montes e Alto Douro)",
            "source_record_id": "W2619656652",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 812,
            "title": "Analysis of the Niching Particle Swarm Optimization Algorithm",
            "title_ar": "",
            "title_en": "Analysis of the Niching Particle Swarm Optimization Algorithm",
            "author": "Tyler Crane",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Brock University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Canada",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; deep-learning; optimization; multimodal",
            "keywords": "",
            "abstract": "Multimodal optimization (MMO) techniques have been researched and developed over the years to track multiple global optima concurrently. MMO algorithms extend traditional unimodal optimization algorithms by using search strategies built around forming niches for multiple possible solutions. NichePSO was one of the first approaches to utilize particle swarm optimization (PSO) for MMO problems, using several small subswarms of agents working concurrently to form niches within the search space. Despite its promising performance NichePSO does suffer from some problems, and very little research has been done to study and improve upon the algorithm over the years. A main goal of this thesis is to analyze the NichePSO algorithm, gaining insight into the strengths and weaknesses of the algorithm. Empirical analyses were performed to study the NichePSO’s ability to maintain niches within complex problem domains, as well as methods for improving the overall performance and effectiveness of the algorithm. Two variants of the NichePSO algorithm are proposed, and experimental results show that they both significantly improve the performance of the NichePSO algorithm across several benchmark functions.",
            "source_url": "https:\/\/openalex.org\/W3175652444",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Brock University Digital Repository (Brock University)",
            "source_record_id": "W3175652444",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 813,
            "title": "Hardware\/software co-design for Neural Network trained by improved Particle Swarm Optimization",
            "title_ar": "",
            "title_en": "Hardware\/software co-design for Neural Network trained by improved Particle Swarm Optimization",
            "author": "Tuan Linh Dang",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "نص السجل: «Ph.D»",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Japan",
            "governorate": "",
            "publication_year": 2017,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; deep-learning; optimization",
            "keywords": "",
            "abstract": "Nowadays, using the particle swarm optimization (PSO) algorithms to train neural networks (NN) has become an attractive research.A famous method used to train the NNs is the back-propagation (BP) algorithm.Recently, previous studies have shown that the NN trained by PSO algorithms (NN-PSO) obtained higher recognition rates and lower learning errors when compared to the NN trained by the conventional BP algorithm.However, the standard PSO (SPSO) algorithm may stick to a local minimum in the training process.In this situation, the SPSO algorithm is stopped, leading to a high learning error rate or a low recognition rate of the trained NN.So far few studies have tried to overcome this problem by adding improving the standard PSO algorithms.Normally in previous studies, the improved versions of the PSO required to add more compute-intensive tasks that often increase computational burden the SPSO algorithm.Typically, previous researchers have implemented the NN trained by PSO algorithms only in hardware or only in software.Normally, the hardware implementation of the NN-PSO in these studies has been tested in a simulation using ModelSim program with the SPSO algorithm but it has not been tested in the real classification tasks.The FPGA-based NN was commonly investigated with a function-approximation, and the researchers just focused on reducing learning errors in the training phase.To deal with the issues described above, this research has three objectives.The first First of all, I would like to thank Professor Yukinobu Hoshino for his willingness to coach me, his promptness, the eye-opening discussions we had and his valuable comments on the progress of my research.In the same light, I thank my co-Supervisors, Professor Masayoshi Tachibana and Professor Yukio Mitsuyama for their excellent observations, ideas, and creativity that inspired my dissertation.I would like to thank all the professors at the Kochi University of Technology who were responsible for the Ph.D. courses that I have attended during these years.I have acquired considerable knowledge through their presentations and interactive scientific discussions.I would like to present all my gratitude to Dr. Cao Thang at the University of Tokyo for his constructive advice and interesting ideas",
            "source_url": "https:\/\/openalex.org\/W2775346207",
            "pdf_url": "https:\/\/kutarr.kochi-tech.ac.jp\/record\/615\/files\/118800131566.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Institutional Repositories DataBase (IRDB)",
            "source_record_id": "W2775346207",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 814,
            "title": "Hybrid algorithms of microbial genetic algorithm and particle swarm optimization for automatic learning groups composition",
            "title_ar": "",
            "title_en": "Hybrid algorithms of microbial genetic algorithm and particle swarm optimization for automatic learning groups composition",
            "author": "Nicholas Simeon Dienagha",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Brunel University London",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; ai-applications; optimization; ai-education",
            "keywords": "",
            "abstract": "Collaboration learning within diverse groups of varying knowledge levels and varying interest levels have been noted to improve learning outcomes.However, composing balanced learning groups with diversity in knowledge level and interest level within the groups while maintaining similarity among the groups is NP-hard and time consuming.The primary aim of this research is to develop an algorithm for automatic composition of balanced learning groups in (MOOCs) with minimal human intervention.The algorithm will assist facilitators in forming balanced learning groups with ease for learners in online classes to benefit from effective collaboration.The research design was experimental research.This design help established comparative experiments of the new algorithm with the particle swarm algorithm as the bench mark algorithm.The findings in the first experiment showed that, the hybrid MGAPSO (Microbial Genetic Algorithm and Particle Swarm Optimization) algorithm outperformed the PSO (Particle Swarm Optimization), an ANOVA (one-way test) showed high significant difference in the mean fitness of the two algorithms (hybrid Microbial Genetic Algorithm and Particle Swarm Optimization and Particle Swarm Optimization).A possible explanation for this might be that the microbial genetic algorithm component tends to re-introduce new particles at every iteration after every genetic operation, thus, introducing diversity in the swarm.In the second experiment, the new adaptive hybrid AMGAPSO (Adaptive hybrid Microbial Genetic Algorithm and Particle Swarm Optimization ) outperformed both the PSO (Particle Swarm Optimization) and the hybrid MGAPSO (Microbial Genetic Algorithm and Particle Swarm Optimization) with high significant difference in the mean fitness of the new adaptive hybrid AMGAPSO (Adaptive hybrid Microbial Genetic Algorithm and Particle Swarm Optimization ) and the mean fitness of the hybrid MGAPSO (Microbial Genetic Algorithm and Particle Swarm Optimization) and that of the Particle Swarm Optimization.A possible explanation of this finding is that particles stuck in the location in the PSO with their re-initialised new velocity may have searched the solution space in different directions and may have jumped out from their respective locations using the microbial genetic algorithm component, which suggest that the method of hybridisation could have resulted in the improved performance of the adaptive hybrid AMGAPSO algorithm relative to the hybrid MGAPSO.In the third Nicholas Simeon Dienagha experiment 500 learners profile data was used in a comparative experiment of the adaptive AMGAPSO (Adaptive Microbial Genetic Algorithm and Particle Swarm Optimization), MGAPSO (Microbial Genetic Algorithm and Particle Swarm Optimization) and PSO (Particle Swarm Optimization), groups formed by the new adaptive AMGAPSO algorithm were analysed; The ANOVA (one way) test resultsshowed no significant difference in the means of all groups for all six learners attributes among all groups formed by the algorithm.The understanding at this point is that, the adaptive hybridization method may have provided a means of avoiding the problem of parameter adjustment and the fitness function derived have contributed to the formation of groups with diversity within the groups while maintaining similarity among the groups formed by the algorithm.The findings answered the aim of the research as the new algorithm outperformed the existing algorithm used in the literature and the groups formed with the new algorithm were balanced in all profile features used in all the groups.The findings show that the new algorithm can be used to form balanced learning group with minimal human intervention.Limitations of the research are that only 500 learners' data was used for the validation of the experiment; this was because data for more students who belong to the same class could not be obtained; ANOVA (One Way Test) was the only statistical tool used in the analysis.In addition, the algorithm developed was evaluated only in terms of the groups form however the effectiveness of the groups and the overall learning improvement achieved by the groups formed by the algorithm was not evaluated.",
            "source_url": "https:\/\/openalex.org\/W2997009542",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Brunel University Research Archive (BURA) (Brunel University London)",
            "source_record_id": "W2997009542",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 815,
            "title": "Novel particle swarm optimization algorithms with applications in power systems",
            "title_ar": "",
            "title_en": "Novel particle swarm optimization algorithms with applications in power systems",
            "author": "Izaz Ur Rahman",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Brunel University London",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2016,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; optimization",
            "keywords": "",
            "abstract": "Optimization problems are vital in physical sciences, commercial and finance matters. In a nutshell, almost everyone is the stake-holder in certain optimization problems aiming at minimizing the cost of production and losses of system, and also maximizing the profit. In control systems, the optimal configuration problems are essential that have been solved by various newly developed methods. The literature is exhaustively explored for an appropriate optimization method to solve such kind of problems. Particle Swarm Optimization is found to be one of the best among several optimization methods by analysing the experimental results. Two novel PSO variants are introduced in this thesis. The first one is named as N State Markov Jumping Particle Swarm Optimization, which is based on the stochastic technique and Markov chain in updating the particle velocity. We have named the second variant as N State Switching Particle Swarm Optimization, which is based on the evolutionary factor information for updating the velocity. The proposed algorithms are then applied to some widely used mathematical benchmark functions. The statistical results of 30 independent trails illustrate the robustness and accuracy of the proposed algorithms for most of the benchmark functions. The better results in terms of mean minimum evaluation errors and the shortest computation time are illustrated. In order to verify the satisfactory performance and robustness of the proposed algorithms, we have further formulated some basic applications in power system operations. The first application is about the static Economic Load Dispatch and the second application is on the Dynamic Economic Load Dispatch. These are highly complex and non-linear problems of power system operations consisting of various systems and generator constraints. Basically, in the static Economic Load Dispatch, a single load is considered for calculating the cost function. In contrast, the Dynamic Economic Load Dispatch changes the load demand for the cost function dynamically with time. In such a challenging and complex environment the proposed algorithms can be applied. The empirical results obtained by applying both of the proposed methods have substantiated their adaptability and robustness into the real-world environment. It is shown in the numerical results that the proposed algorithms are robust and accurate as compared to the other algorithms. The proposed algorithms have produced consistent best values for their objectives, where satisfying all constraints with",
            "source_url": "https:\/\/openalex.org\/W2289879240",
            "pdf_url": "http:\/\/bura.brunel.ac.uk\/bitstream\/2438\/12219\/1\/FulltextThesis.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Brunel University Research Archive (BURA) (Brunel University London)",
            "source_record_id": "W2289879240",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 816,
            "title": "Items Arrangement in Container using Particle Swarm Optimization Algorithm",
            "title_ar": "",
            "title_en": "Items Arrangement in Container using Particle Swarm Optimization Algorithm",
            "author": "Putro, Angger Priyardhan",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2016,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; optimization",
            "keywords": "",
            "abstract": "Abstract — For the shipping companies, items arrangement in containers is an important issue. To earn profits as much as possible the preparation of the goods in the container must be as efficient as possible so it can minimize the transportation costs. That is why it needs an algorithm that can help to resolve this problem. One algorithm that can solve this problem is the Particle Swarm Optimization algorithm. This project was made using the Java programming language and the algorithm using Particle Swarm Optimization algorithm. How it works is at first the Particle Swarm Optimization is begin to formed a random solution, after that every solution will counting its fitness, after fitness value is obtained, a solution with a best value will be used as a reference to create a new solution in the next iteration by updating its speed and position. In this project every particle has several attributes I.e. the code, size and position of the goods in the container. The fitness value is determined from how much free space is available in that solution, the more free space available and the more items available in the container, the more fitness value is.",
            "source_url": "https:\/\/openalex.org\/W2909824468",
            "pdf_url": "http:\/\/repository.unika.ac.id\/9712\/8\/11.02.0065%20Angger%20Priyardhan%20Putro%20DAFTAR%20PUSTAKA.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Unika Repositor (Unika)",
            "source_record_id": "W2909824468",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 817,
            "title": "An Analysis of Parameter Control Mechanisms for the Particle Swarm Optimization Algorithm",
            "title_ar": "",
            "title_en": "An Analysis of Parameter Control Mechanisms for the Particle Swarm Optimization Algorithm",
            "author": "Kyle Robert Harrison",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Pretoria",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "South Africa",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; optimization",
            "keywords": "",
            "abstract": "The particle swarm optimization (PSO) algorithm is a stochastic, population-based optimization technique influenced by social dynamics. It has been shown that the performance of the PSO algorithm can be greatly improved if the control parameters are appropriately tuned. However, the tuning of control parameter values has traditionally been a time-consuming, empirical process followed by statistical analysis. Furthermore, ideal values for the control parameters may be time-dependent; parameter values that lead to good performance in an exploratory phase may not be ideal for an exploitative phase. Self-adaptive algorithms eliminate the need to tune parameters in advance, while also providing real-time behaviour adaptation based on the current problem. \\t This thesis first provides an in-depth review of existing self-adaptive particle swarm optimization (SAPSO) techniques. Their ability to attain order-2 stability is examined and it is shown that a majority of the existing SAPSO algorithms are guaranteed to exhibit either premature convergence or rapid divergence. A further investigation focusing on inertia weight control strategies demonstrates that none of the examined techniques outperform a static value. This thesis then investigates the performance of a wide variety of PSO parameter configurations, thereby discovering regions in parameter space that lead to good performance. This investigation provides strong empirical evidence that the best values to employ for the PSO control parameters change over time. Finally, this thesis proposes novel PSO variants inspired by results of the aforementioned studies.",
            "source_url": "https:\/\/openalex.org\/W2901362492",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "UpSpace Institutional Repository (University of Pretoria)",
            "source_record_id": "W2901362492",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 818,
            "title": "Genetic learning particle swarm optimization for task matching in grid environment",
            "title_ar": "",
            "title_en": "Genetic learning particle swarm optimization for task matching in grid environment",
            "author": "Eid Mohammad Albalawi",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Manitoba",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Canada",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; optimization",
            "keywords": "",
            "abstract": "Many scientific disciplines require processing computational-intensive applications with vast quantities of data. Large scale systems, such as Grid, provide shared resources on geographically distributed heterogeneous computing systems to meet the computational demands of the applications. One of the fundamental problem computing with the Grid system is assigning tasks of various users to the resources efficiently such that the execution time of the application is minimized while Grid resources are utilized optimally. This is called the task matching problem, an NP-hard problem, the focus of this thesis. While there are many heuristics for the task matching problem, particle swarm optimization (PSO) has been one of the latest heuristics in the literature adopted as a solution to this problem. However, PSO has few drawbacks, such as premature convergence to local optima. To circumvent these problems, we incorporate a learning approach inspired by the genetic algorithm to guide the PSO algorithm. We propose three novel genetic learning PSO algorithms: modified genetic learning PSO (MGLPSO), hybrid genetic learning PSO (HGLPSO), and modified genetic learning PSO with adaptive mutation (μ-MGLPSO). The proposed algorithms have been designed for both single and multi-objective task matching problem for tasks with and without dependencies. The proposed techniques are evaluated on standard benchmarks with large data sets and compared against state-of-the-art algorithms.",
            "source_url": "https:\/\/openalex.org\/W3083480189",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Mspace (University of Manitoba)",
            "source_record_id": "W3083480189",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 819,
            "title": "Multi self-adapting particle swarm optimization algorithm (MSAPSO).",
            "title_ar": "",
            "title_en": "Multi self-adapting particle swarm optimization algorithm (MSAPSO).",
            "author": "Gerhard Koch",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Louisville",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; optimization",
            "keywords": "",
            "abstract": "The performance and stability of the Particle Swarm Optimization algorithm depends on parameters that are typically tuned manually or adapted based on knowledge from empirical parameter studies. Such parameter selection is ineffectual when faced with a broad range of problem types, which often hinders the adoption of PSO to real world problems. This dissertation develops a dynamic self-optimization approach for the respective parameters (inertia weight, social and cognition). The effects of self-adaption for the optimal balance between superior performance (convergence) and the robustness (divergence) of the algorithm with regard to both simple and complex benchmark functions is investigated. This work creates a swarm variant which is parameter-less, which means that it is virtually independent of the underlying examined problem type. As PSO variants always have the issue, that they can be stuck-in-local-optima, as second main topic the MSAPSO algorithm do have a highly flexible escape-lmin-strategy embedded, which works dimension-less. The MSAPSO algorithm outperforms other PSO variants and also other swarm inspired approaches such as Memetic Firefly algorithm with these two major algorithmic elements (parameter-less approach, dimension-less escape-lmin-strategy). The average performance increase in two dimensions is at least fifteen percent with regard to the compared swarm variants. In higher dimensions (≥ 250) the performance gain accumulates to about fifty percent in average. At the same time the error-proneness of MSAPSO is in average similar or even significant better when converging to the respective global optima’s.",
            "source_url": "https:\/\/openalex.org\/W2887728610",
            "pdf_url": "https:\/\/ir.library.louisville.edu\/cgi\/viewcontent.cgi?article=4019&context=etd",
            "doi": "10.18297\/etd\/3000",
            "handle": "",
            "repository_name": "ThinkIR: The University of Louisville's Institutional Repository (University of Louisville)",
            "source_record_id": "W2887728610",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 820,
            "title": "Optimasi Parameter Premise Pada Adaptive-Network-Based Fuzzy Inference System Dengan Modifikasi Kombinasi Particle Swarm Optimization Dan Genetic Algorithm",
            "title_ar": "",
            "title_en": "",
            "author": "Muchamad Kurniawan",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2017,
            "language": "id",
            "research_domain": "deep-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; deep-learning; expert-systems; optimization",
            "keywords": "",
            "abstract": "ANFIS adalah kombinasi fuzzy inference system (FIS) dan neural network (NN). Terdapat dua parameter training pada ANFIS, parameter premise dan parameter consequent. Pada ANFIS tradisional menggunakan algoritma least square estimator (LSE) dan Gradient Decent (GD) sebagai algoritma pembelajaran parameter training. Kelemahan dari perpaduan dua algortima ini adalah mendapatkan solusi yang lokal optimal. Perubahan individu pada PSO cepat konvergen tapi memungkinkan mendapatkan hasil local optimal. hal ini dikarenakan pada PSO tidak mampu untuk menemukan ruang solusi baru. Kelebihan Algoritma GA adalah dalam menemukan ruang solusi yang lebih luas. Kontribusi yang diusulkan adalah modifikasi dari kombinasi PSOGA. Modifikasi yang dilakukan adalah dengan menambahkan pemilihan individu. Pada penelitian ini akan dilakukan pelatihan parameter premise dengan kombinasi perpaduan PSOGA dan pelatihan parameter consequent dengan algortima LSE pada ANFIS. Hasil Uji Coba ANFIS-PSOGA dibandingkan dengan metode ANFIS, ANFIS-GA,dan, ANFIS-PSO pada dataset Iris Flowers, Haberman, Vertebral dan Banana. ANFIS-PSOGA memperoleh nilai paling bagus dari metode-metode yang lain pada dataset Iris Flowers dengan akurasi 99.85%, dataset Haberman dengan akurasi 84.52% dan dataset Vertebral dengan akurasi 91.83%. ============================================================================================= ANFIS is a combination of namely fuzzy Inference System (FIS) and Neural Network (NN). There are two training parameters in ANFIS, premise parameter and consequent parameter. In traditional ANFIS using hybrid Least Square Estimator (LSE) and Gradient Decent (GD) as learning algorithm for training parameters. Disadvantages of combining those two algorithms getting local optimal solution. Individual changes to the PSO converge quickly but allow for optimal local results. This is because PSO is unable to find a new solution space. The advantage of GA's algorithm are finding a wider solution space. With the hybrid of these two algoritm will give better results. Proposed contribution in this study is a modification of the hybrid PSOGA. Modifications were done by adding the individual election. In this study, premise parameter will be trained with a modification of hybrid PSOGA and consequent parameter will be trained with the LSE algorithm in the ANFIS method or called ANFIS-PSOGA. ANFIS-PSOGA test results are compared with ANFIS, ANFIS-GA and ANFIS-PSO on Iris Flowers, Haberman, Vertebral and Banana datasets. ANFIS-PSOGA obtained the best accuracy results compared to other methods in the Iris Flowers dataset with 99.85% accuracy, Haberman dataset with 84.52% accuracy, and Vertebral dataset with 91.83% accuracy.",
            "source_url": "https:\/\/openalex.org\/W2789953228",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W2789953228",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 821,
            "title": "Using Particle Swarm Optimization for Market Timing Strategies",
            "title_ar": "",
            "title_en": "Using Particle Swarm Optimization for Market Timing Strategies",
            "author": "Ismail Mohamed",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Kent",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; optimization",
            "keywords": "",
            "abstract": "Market timing is the issue of deciding when to buy or sell a given asset on the market. As one of the core issues of algorithmic trading systems, designers of such system have turned to computational intelligence methods to aid them in this task. In this thesis, we explore the use of Particle Swarm Optimization (PSO) within the domain of market timing.nPSO is a search metaheuristic that was first introduced in 1995 [28] and is based on the behavior of birds in flight. Since its inception, the PSO metaheuristic has seen extensions to adapt it to a variety of problems including single objective optimization, multiobjective optimization, niching and dynamic optimization problems. Although popular in other domains, PSO has seen limited application to the issue of market timing. The current incumbent algorithm within the market timing domain is Genetic Algorithms (GA), based on the volume of publications as noted in [40] and [84]. In this thesis, we use PSO to compose market timing strategies using technical analysis indicators. Our first contribution is to use a formulation that considers both the selection of components and the tuning of their parameters in a simultaneous manner, and approach market timing as a single objective optimization problem. Current approaches only considers one of those aspects at a time: either selecting from a set of components with fixed values for their parameters or tuning the parameters of a preset selection of components. Our second contribution is proposing a novel training and testing methodology that explicitly exposes candidate market timing strategies to numerous price trends to reduce the likelihood of overfitting to a particular trend and give a better approximation of performance under various market conditions. Our final contribution is to consider market timing as a multiobjective optimization problem, optimizing five financial metrics and comparing the performance of our PSO variants against a well established multiobjective optimization algorithm. These algorithms address unexplored research areas in the context of PSO algorithms to the best of our knowledge, and are therefore original contributions. The computational results over a range of datasets shows that the proposed PSO algorithms are competitive to GAs using the same formulation. Additionally, the multiobjective variant of our PSO algorithm achieve statistically significant improvements over NSGA-II.",
            "source_url": "https:\/\/openalex.org\/W3136655786",
            "pdf_url": "",
            "doi": "10.22024\/unikent\/01.02.87076",
            "handle": "",
            "repository_name": "Kent Academic Repository (University of Kent)",
            "source_record_id": "W3136655786",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 822,
            "title": "Novel particle swarm optimization algorithms with applications to healthcare data analysis",
            "title_ar": "",
            "title_en": "Novel particle swarm optimization algorithms with applications to healthcare data analysis",
            "author": "Weibo Liu",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Brunel University London",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "optimization",
            "categories": "machine-learning; medical-ai; optimization",
            "keywords": "",
            "abstract": "",
            "source_url": "https:\/\/openalex.org\/W3013797946",
            "pdf_url": "https:\/\/bura.brunel.ac.uk\/bitstream\/2438\/20575\/1\/FulltextThesis.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Brunel University Research Archive (BURA) (Brunel University London)",
            "source_record_id": "W3013797946",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 823,
            "title": "An improved data classification framework based on fractional particle swarm optimization",
            "title_ar": "",
            "title_en": "An improved data classification framework based on fractional particle swarm optimization",
            "author": "Fahad Sherwani",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Universiti Tun Hussein Onn Malaysia",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Malaysia",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "rnn",
            "categories": "machine-learning; deep-learning; medical-ai; optimization; rnn",
            "keywords": "",
            "abstract": "Particle Swarm Optimization (PSO) is a population based stochastic optimization technique which consist of particles that move collectively in iterations to search for the most optimum solutions. However, conventional PSO is prone to lack of convergence and even stagnation in complex high dimensional-search problems with multiple local optima. Therefore, this research proposed an improved Mutually-Optimized Fractional PSO (MOFPSO) algorithm based on fractional derivatives and small step lengths to ensure convergence to global optima by supplying a fine balance between exploration and exploitation. The proposed algorithm is tested and verified for optimization performance comparison on ten benchmark functions against six existing established algorithms in terms of Mean of Error and Standard Deviation values. The proposed MOFPSO algorithm demonstrated lowest Mean of Error values during the optimization on all benchmark functions through all 30 runs (Ackley = 0.2, Rosenbrock = 0.2, Bohachevsky = 9.36E-06, Easom = -0.95, Griewank = 0.01, Rastrigin = 2.5E-03, Schaffer = 1.31E-06, Schwefel 1.2 = 3.2E-05, Sphere = 8.36E-03, Step = 0). Furthermore, the proposed MOFPSO algorithm is hybridized with Back-Propagation (BP), Elman Recurrent Neural Networks (RNN) and Levenberg-Marquardt (LM) Artificial Neural Networks (ANNs) to propose an enhanced data classification framework, especially for data classification applications. The proposed classification framework is then evaluated for classification accuracy, computational time and Mean Squared Error on five benchmark datasets against seven existing techniques. It can be concluded from the simulation results that the proposed MOFPSO-ERNN classification algorithm demonstrated good classification performance in terms of classification accuracy (Breast Cancer = 99.01%, EEG = 99.99%, PIMA Indian Diabetes = 99.37%, Iris = 99.6%, Thyroid = 99.88%) as compared to the existing hybrid classification techniques. Hence, the proposed technique can be employed to improve the overall classification accuracy and reduce the computational time in data classification applications.",
            "source_url": "https:\/\/openalex.org\/W3113818546",
            "pdf_url": "http:\/\/eprints.uthm.edu.my\/61\/1\/24p%20FAHAD%20SHERWANI.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "UTHM Institutional Repository (Universiti Tun Hussein Onn Malaysia)",
            "source_record_id": "W3113818546",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 824,
            "title": "Implementation of a surrogate model for structural optimization based on artificial neural network and genetic algorithm",
            "title_ar": "",
            "title_en": "Implementation of a surrogate model for structural optimization based on artificial neural network and genetic algorithm",
            "author": "Iuri Hermes Müller",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "predictive-analytics",
            "categories": "machine-learning; deep-learning; robotics; ai-applications; predictive-analytics; optimization; ai-industry",
            "keywords": "",
            "abstract": "The use of computational optimization methods in structural design, employing surrogate models based on artificial neural networks (ANNs), is a promising approach for achieving efficient and cost-effective solutions compared to traditional optimization relying solely on the finite element method (FEM). These methods are particularly effective for composite material structures, which can be tailored to meet varying mechanical requirements and are fabricated via fused deposition modeling (FDM), such as 3D printing, due to their flexibility and capability to efficiently produce complex geometries. This study aims to implement a numerical optimization algorithm combined with an ANN trained and tested using a database to optimize the support arm of an unmanned aerial vehicle (UAV), manufactured using FDM. The methodology was divided into two main stages. In the first stage, an algorithm was developed in Python to generate a database from FEM simulations conducted in ABAQUS software. These simulations considered the arm, fabricated using polylactic acid (PLA) as the constituent material, with one fixed end and the other subjected to thrust and torsional loads, replicating the UAV's operational conditions. Four geometric parameters of the arm (structure height and width, thickness, and the number of diagonal reinforcement cells) were modified to obtain the masses and stiffness values for each configuration. In the second stage, the algorithm was enhanced by incorporating three additional geometric variables (thickness of the edges and bottom reinforcement, and width of the top reinforcement), resulting in a more extensive database. This expanded dataset was used to train the ANN, which predicted masses and stiffness values based on the geometric variables. The multi-objective optimization problem was then defined using the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to minimize mass and maximize stiffness, constrained by the geometric variables, with the ANN employed to evaluate the multi-objective function as a surrogate for FEM. From the solutions obtained on the Pareto front, one was selected for experimental validation. The optimized and standard models were designed in computer-aided design (CAD) software, fabricated using FDM with PLA, and subjected to bending tests to replicate the conditions implemented in the FEM analyses. The results demonstrated that the ANN exhibited high accuracy, with correlation coefficients of 0.99 for stiffness and 0.99 for mass, reducing analysis time by 99.65% compared to FEM. The optimized model showed an average specific stiffness increase of 51.14% and a mass reduction of 42.13% compared to the standard model. Finally, the results indicated that the proposed methodology is efficient in determining optimized solutions. While the database generation required substantial computational time, analyses conducted using the trained neural network demonstrated a significant reduction in processing time. Moreover, the proposed method is adaptable for application in various engineering projects involving composite materials",
            "source_url": "https:\/\/openalex.org\/W7120726491",
            "pdf_url": "http:\/\/repositorio.ufsm.br\/bitstream\/1\/33781\/1\/DIS_PPGEM_2024_MULLER_IURI.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)",
            "source_record_id": "W7120726491",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 825,
            "title": "Stability and Scalability of Feature Subset Selection using Particle Swarm Optimization in Bioinformatics",
            "title_ar": "",
            "title_en": "Stability and Scalability of Feature Subset Selection using Particle Swarm Optimization in Bioinformatics",
            "author": "Hassen Dhrif",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "xai",
            "categories": "machine-learning; deep-learning; computer-vision; robotics; responsible-ai; predictive-analytics; optimization; multimodal; xai",
            "keywords": "",
            "abstract": "Feature Subset Selection (FSS) is a non-convex, non-linear, multi-modal, high-dimensional, Multi-Objective Optimization problem, where finding the optimum solution is a fairly difficult task due to its ultra-large search space and its very large number of local minima. Existing FSS methods suffer from problems like stagnation in local optima and high computational cost. Evolutionary Computation (EC) techniques are well known global search algorithms. Particle Swarm Optimization (PSO) is an EC technique that is simple to implement and that converges faster than other methods such as Genetic Algorithms (GA), Differential Evolution (DE) or Ant Colony Optimization (ACO). PSO has been successfully applied to areas such as engineering, biology, image processing, job scheduling, robotics and neural networks, but its potential for FSS has not been fully investigated. The overall goal of this thesis is to investigate and improve the capability of PSO for FSS aiming to select the smallest, most compact subset of features with the best classification performance in the least amount of time. This thesis investigates the use of PSO for wrapper, filter, embedded and hybrid approaches and it implements PSO on both single and multi-objective FSS. FSS problems are characterized by an increasing number of features and instances, massively challenging classical methods. Representing efficient global search methods, Swarm Intelligence (SI) based Evolutionary Computation (EC) techniques have increasingly been applied to solve such FSS problems. Despite their popularity, PSO and other swarm-based algorithms still suffer from a variety of problems and short comings as a consequence of high-dimensional data. We start this dissertation with a comprehensive survey, we formulate the challenges of SI algorithms that tackle FSS problems, discuss algorithmic solutions and present an overview of metrics that allow the systematic and comparable assessment of algorithms performance. Then, in bioinformatics, PSO methods can select subsets of predictive genes for sample classification. However; the obtained gene subsets lack interpretability and are usually too large to be used as biomarkers. Such characteristics may be rooted in the observation that PSO algorithms usually lose the diversity of the swarm, leading to premature convergence and leaving many areas of the search space unexplored. Furthermore, high-dimensional FSS problems like those encountered in gene expression data pose an additional challenge to EC techniques since their ability to pick out the important features must remain unchanged despite the increasing dimensionality of the feature space. Our goal is to develop an algorithm capable of scaling up to high-dimensional gene expression data while still selecting the smallest subsets that capture the information to carry the desired prediction tasks. To address these drawbacks, we introduce a new PSO variant called Combinatorial PSO (COMB-PSO). The proposed method develops a new encoding mechanism, an enhanced Pareto nondominated set…",
            "source_url": "https:\/\/openalex.org\/W2969952035",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "",
            "source_record_id": "W2969952035",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 826,
            "title": "Optimizing convolutional neural network parameters using genetic algorithm for breast cancer classification",
            "title_ar": "",
            "title_en": "Optimizing convolutional neural network parameters using genetic algorithm for breast cancer classification",
            "author": "Khatereh Davoudi",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Manitoba",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Canada",
            "governorate": "",
            "publication_year": 2020,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; medical-ai; optimization; cnn; medical-imaging",
            "keywords": "",
            "abstract": "Breast cancer, as the most-regularly diagnosed cancer in women, can be controlled effectively by early-stage tumour diagnosis. Clinical specialists use Computer-Aided Diagnosis (CAD) systems to help aid in their diagnosis, as accurate as possible. Deep learning techniques, such as Convolutional Neural Network (CNN), due to their classification capabilities, have been widely adopted in CAD systems. The parameters of the network, including the weights of the convolution filters, and the weights of the fully connected layers play a crucial role in classification accuracy. Back-propagation technique is the most frequently used approach for training CNN. However, this technique has some disadvantages, such as getting stuck in local minima. In this thesis, we propose to optimize the weights of the CNN using Genetic Algorithm (GA). The work consists of: designing a CNN model to facilitate the classification process, training the model using three different optimizer (mini-batch gradient descent, Adam, and GA), and evaluating the model through various experiments on BreakHis dataset. We show that the CNN model trained through GA performs as well as the Adam optimizer with a classification accuracy of 85%.",
            "source_url": "https:\/\/openalex.org\/W3048136822",
            "pdf_url": "https:\/\/mspace.lib.umanitoba.ca\/bitstreams\/050cf8f8-9e09-4432-8764-8ad5bbcae9e1\/download",
            "doi": "",
            "handle": "",
            "repository_name": "Mspace (University of Manitoba)",
            "source_record_id": "W3048136822",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 827,
            "title": "A fast learning network with improved particle swarm optimization for intrusion detection system",
            "title_ar": "",
            "title_en": "A fast learning network with improved particle swarm optimization for intrusion detection system",
            "author": "Mohammed Hasan Ali",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Universiti Malaysia Pahang",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Malaysia",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; ai-applications; optimization; ai-cybersecurity",
            "keywords": "",
            "abstract": "In current days the intrusion detection systems (IDS) have several shortcomings such as high rates of false positive alerts, low detection rates of rare but dangerous attacks, and the need for a constant human intervention and tuning. Daily, there are reports of incidents such as major ex-filtration of data for the purposes of stealing identities, credit card numbers, and intellectual properties, as well as to take control of network resources. Machine learning approaches have been widely used to increase the effectiveness of intrusion detection platforms. While some machine learning techniques are effective at detecting certain types of attacks, there are no known methods that can be applied universally and achieve consistent results for multiple attack types. This situation makes the detection of cyber-based attacks on computer networks a relevant and challenging area of research. The Fast Learning Network (FLN) is one of the new machine learning algorithms that are easy to implement, computationally efficient, and with excellent learning performance characteristics. However, the internal power parameters (weight and basis) of FLN are initialized at random, causing the algorithm to be unstable. In this work, a new cooperative multi-swarm scheme called multi-swarmoptimization (MRPSO) which is inspired by the human social behavior was proposed for the interaction of several PSO groups while searching for the best parameters values of PSO. The focus of this research is on the development of a model that can optimize the initial parameters of FLN based on MRPSO to obtain an optimal set of initial parameters for FLN, thus, creating an optimal FLN classifier named as MRPSO-FLN which can improve the efficacy of network intrusion on data sets that contain instances of multiple classes of attacks. These methods were tested on NSL-KDD intrusiondetection datasets and the results indicate that the proposed approaches used in the system performed well in large dataset processing. In these experiments, it was demonstrated that the FLN optimization method achieved 0.9964 which is a higher accuracy than most of the existing paradigms for classifying network intrusion detection data.",
            "source_url": "https:\/\/openalex.org\/W3202035355",
            "pdf_url": "https:\/\/umpir.ump.edu.my\/id\/eprint\/29922\/2\/mohammedhasanaliphd_2019.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "UMP Institutional Repository (Universiti Malaysia Pahang)",
            "source_record_id": "W3202035355",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 853,
            "title": "A hybrid Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for detecting Keratoconus in patients using genetic algorithm",
            "title_ar": "",
            "title_en": "A hybrid Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for detecting Keratoconus in patients using genetic algorithm",
            "author": "Somayeh Ghasedi Katak Lahijani",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Laurentian University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Canada",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "cnn",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; predictive-analytics; optimization; cnn",
            "keywords": "",
            "abstract": "Nowadays, there are still significant challenges encountered in the accurate diagnosis of various eye diseases, such as Keratoconus (KCN) and cataracts. Early detection of Keratoconus is crucial in preventing its progression and ensuring the best treatment outcomes. Artificial intelligence (AI) is being widely applied in ophthalmology through the training of deep learning networks for the early detection of eye diseases. This research presents a novel, integrated machine learning approach for diagnosing Keratoconus disease by combining feature extraction through Convolutional Neural Networks (CNN) with a Support Vector Machine (SVM) and Artificial Neural Network (ANN) for classification. Employing a multi-objective genetic algorithm, the method optimizes feature selection, aiming to minimize both diagnostic error and the number of features. The study utilizes a dataset of 5,152 ophthalmic images (1288 samples) categorized into Normal (476), Suspect (453), and Keratoconus (359) cases, sourced from an eye clinic in Egypt. Combining a Convolutional Neural Network (CNN) for feature selection with a Genetic Algorithm (GA) significantly improved diagnostic accuracy. Consequently, by focusing on the most relevant features of Keratoconus (KC), the model achieved an impressive 98.63% accuracy for ANN classification with a genetic algorithm, and 98.13% for SVM classification with a genetic algorithm. The accuracy of the algorithm exceeded that of when SVM and ANN were used without the genetic algorithm alone, which were 97.53% and 96.9% respectively, underscoring the benefit of combining Artificial Neural Networks (ANNs) with Genetic Algorithms (GAs) in KC diagnosis. Implementing this model can assist physicians in more accurate Keratoconus detection, providing better predictions regarding patients' eye conditions, and offering timely treatment recommendations.",
            "source_url": "https:\/\/openalex.org\/W7205487330",
            "pdf_url": "https:\/\/laurentian.scholaris.ca\/bitstreams\/ebade523-4710-440b-a199-72030adbc718\/download",
            "doi": "",
            "handle": "",
            "repository_name": "Lu Zone Ul (Laurentian University)",
            "source_record_id": "W7205487330",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 863,
            "title": "IoT System engineering approach using AI for managing safety products in healthcare and workplaces",
            "title_ar": "",
            "title_en": "IoT System engineering approach using AI for managing safety products in healthcare and workplaces",
            "author": "Jabbar Abed Eleiwy",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Brunel University London",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2021,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "predictive-analytics",
            "categories": "machine-learning; deep-learning; computer-vision; medical-ai; predictive-analytics; optimization",
            "keywords": "",
            "abstract": "The Internet of things (IoT) has been widely used in life support facilities, especially in the healthcare sector.The management of health and safety (H&S) devices is an indispensable factor in guaranteeing human life.Thus, many companies and organisations have ensured the safety of their workplace from any overwhelming risks, such as fire, damage and accidents.The problem is that companies that have thousands of employees also have hundreds of health and safety systems in continuous use and Building Service Managers do not know which devices need maintenance or replenishment and require a significant amount of time to continuously check that their health and safety systems are maintained according to legislation requirements.The consequences of companies not meeting their health and safety obligations are serious and expensive if any of their employees are seriously injured as a consequence of the health and safety products not being in their original, immaculate order for use.Furthermore, insurance companies will refuse to pay compensation for injury to employees if it has been shown that the health and safety products are not in their original, immaculate order for use.Therefore, it makes economic sense to design and use an Internet of Things based monitoring system to record the state of health and safety products within companies.This thesis presents the design and prototype of an IoT-based health and safety (H&S) products monitoring system using artificial intelligence (AI) and image processing.The thesis aims to present a real-time control and monitoring system to determine the status of consumable hospital devices, such as first aid boxes, earplug dispensers, life jackets and fire extinguishers by using Zigbee sensors to read the measurement of the weight, and image-processing (sensor in a micro digital camera with affixed laser light) to determine the level.The proposed design is a dynamic (real-time) system that can monitor and predict the status of any equipment in hospitals or workplaces and notify the building service managers when any facilities need to be updated.Therefore, the proposed system can reduce hospitals' and companies' time, money and workforce requirements compared with previous manual maintenance approaches that are time-consuming and require more efforts and higher costs.Artificial intelligence infrastructure based on Ant Colony, Traveling Salesman Problem TSP and Genetic Algorithm GA is proposed to be implemented in optimisation algorithm to support salesmen in selecting the shortest path and latest time in maintaining and replenishing critically low devices at different locations in an appropriate time.Artificial neural networks are used to predict the optimal performance and the correlation between effective input factors and ii performance output.The achieved AI accuracy results is 96% of the proposed system which are proven to be reliable and can be used to manage many consumable H&S products in different district hospitals and companies as compared with the other approaches i.e. (Genetic, Ant-colony and TSP) that have been used at the same application whilst meeting regulatory requirements.The efficiency of the proposed system is validated because it reduces time, costs, efforts and workforce resources compared with previous manual maintenance approaches.",
            "source_url": "https:\/\/openalex.org\/W3171521908",
            "pdf_url": "https:\/\/bura.brunel.ac.uk\/bitstream\/2438\/22075\/1\/FulltextThesis.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "Brunel University Research Archive (BURA) (Brunel University London)",
            "source_record_id": "W3171521908",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:53",
            "updated_at": "2026-11-15 16:52:53"
        },
        {
            "id": 915,
            "title": "Data-efficient domain adaptation for pretrained language models",
            "title_ar": "",
            "title_en": "Data-efficient domain adaptation for pretrained language models",
            "author": "Xu Guo",
            "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; nlp; responsible-ai; transfer-learning; self-semi-supervised; predictive-analytics; optimization; rnn; transformers; llm; federated-learning",
            "keywords": "",
            "abstract": "Recent advances in Natural Language Processing (NLP) are built on a range of large-scale pretrained language models (PLMs), which are based on deep transformer neural networks. These PLMs simultaneously learn contextualized word representations and language modeling by training the entire model on massive unlabeled corpora using self-supervised learning techniques, bringing about a paradigm shift that moves our focus from customizing different models for different tasks to adapting one PLM to all tasks. Studying how to adapt a general-purpose PLM to a specific domain of interest is of great significance to the deployment of PLMs. The mainstream practice is to finetune a PLM with a task-specific head on a labeled dataset from the target domain. However, for most target applications, labeled data is limited and even scarce in many low-resource scenarios. The huge number of parameters in a PLM often leaves those small datasets struggling to harness the power of the language priors. As a result, even under the same task, when a PLM finetuned on one dataset is applied to another dataset with some domain gap, it sometimes encounters performance degradation due to overfitting the previous training set. This phenomenon hinders the wide adoption of PLMs in practice, particularly in the face of new domains, calling for approaches to enhance the generalization performance of PLMs during adaptation without requesting more labeled data. Early domain adaptation methods, which leverage similar source domains to boost model performance on the target domains, are developed based on customized models using traditional neural networks such as LSTMs. These models are shallow, require longer training time to converge, and have no prior knowledge compared to PLMs. Studies show that some popular domain adaptation methods can even harm the generalization performance of PLMs on the target domains. The unique characteristics of PLMs such as unprecedented scales, rich language priors, and many hitherto underexplored skills could be uncontrollable factors that make them exhibit different learning behaviors compared to traditional models. To this end, there is a need to develop algorithms for PLMs to enhance their domain adaptation performance, thereby accelerating their wide adoption in real-world scenarios. This thesis aims to explore techniques that can efficiently make use of the target domain labeled data and better adapt a given PLM to the target domains of interest by effectively transferring knowledge from similar source domains to the target domains. To achieve this goal, I conduct research from three perspectives throughout a machine learning pipeline, each assuming only specified locations can be updated with available computing resources. That is, we keep all other conditions fixed and only make updates to the input data, model representations, and output predictions respectively. We show how to achieve better generalization performance with limited labeled data from the target domains under each scenario. To sum up, we propose a new algorithm to generate adversarial perturbations using the domain adaptation objective to enhance the transferability of soft prompt tuning in low-resource scenarios, a new model optimization algorithm that takes into account the next-step gradients of adversarial domain discriminator when optimizing the task classifiers to accommodate competing losses and a new federated learning framework that calibrates the conditional probability distribution to adapt the same PLM to multiple domains under different label distributions. We present the specific problems, related works, detailed methods, extensive experiments, and thorough discussions in the following chapters, and shed light on how to base on traditional machine learning methods while catering to newly emerging learning paradigms.",
            "source_url": "https:\/\/openalex.org\/W4378983312",
            "pdf_url": "https:\/\/dr.ntu.edu.sg\/bitstream\/10356\/167965\/2\/PhD_Thesis_GuoXu.pdf",
            "doi": "10.32657\/10356\/167965",
            "handle": "",
            "repository_name": "DR-NTU (Nanyang Technological University)",
            "source_record_id": "W4378983312",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 940,
            "title": "Documenting and Improving Prompts for Large Language Models",
            "title_ar": "",
            "title_en": "Documenting and Improving Prompts for Large Language Models",
            "author": "Amandine M. Caut",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Dalarna University Library",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Sweden",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; nlp; generative-ai; responsible-ai; optimization; llm; fairness",
            "keywords": "",
            "abstract": "Generative Artificial Intelligence has fundamentally reshaped the landscape of technology, transitioning from academic research into a revolutionary force across virtually every sector of society. Today, generative AI drives innovation across numerous domains, reflecting its expanding societal impact. At the forefront of this revolution are large language models (LLMs): sophisticated systems that have redefined human-AI interaction and democratized access to intelligent analysis. As LLMs become increasingly accessible, the critical challenge is no longer whether to use them, but how to deploy them effectively and responsibly within specialized domains. This thesis investigates how Large Language Models can deepen our understanding of the world and enhance our capacity for insight and discovery. Specifically, it examines the practical integration of LLMs into data science workflows, exploring how they can enhance data exploration, strengthen analytical reasoning, and support informed decision-making. Equally important, it addresses a fundamental challenge often overlooked: establishing rigorous documentation and structural practices that ensure reproducibility, transparency, and methodological integrity when working with these powerful tools. By synthesizing theoretical foundations with practical application, this research provides both technical insights and actionable guidance for LLMs into data science practice: not as a shortcut, but as a disciplined, transparent, and accountable approach to modern analytical work.",
            "source_url": "https:\/\/openalex.org\/W7161225329",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Diva portal (Dalarna University Library)",
            "source_record_id": "W7161225329",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:54",
            "updated_at": "2026-11-15 16:52:54"
        },
        {
            "id": 1008,
            "title": "Machine learning applications in medical imaging for early diagnosis of cardiovascular diseases",
            "title_ar": "",
            "title_en": "Machine learning applications in medical imaging for early diagnosis of cardiovascular diseases",
            "author": "Marena Soliman",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Boston University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2025,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "medical-imaging",
            "categories": "machine-learning; deep-learning; medical-ai; responsible-ai; optimization; cnn; medical-imaging; fairness",
            "keywords": "",
            "abstract": "Since cardiovascular diseases (CVDs) continue to be the primary cause of morbidity and death worldwide, better patient outcomes depend on early and precise diagnosis. Although they are essential for clinical decision-making, traditional cardiovascular imaging methods such as computed tomography (CT), cardiac magnetic resonance (CMR), and echocardiography sometimes rely on subjective evaluations that are prone to inter-observer variability. A revolutionary method for improving diagnostic automation, efficiency, and accuracy is the incorporation of machine learning (ML) into medical imaging. Large amounts of imaging data can be analyzed using ML algorithms, such as supervised and unsupervised learning models, which can also extract complex patterns and accurately detect small cardiovascular abnormalities. Accurate measurement of cardiac structures and functions is made possible by deep learning models and convolutional neural networks (CNNs), which further enhance feature extraction and classification. By enabling early identification, lowering diagnostic errors, and improving patient prognosis, ML-driven diagnostic technologies have the potential to completely transform cardiovascular healthcare, notwithstanding obstacles relating to data privacy, ethical issues, and regulatory compliance. With a focus on its contribution to the advancement of automated diagnostics and precision medicine, this paper examines the present uses, difficulties, and potential of machine learning in cardiovascular imaging.",
            "source_url": "https:\/\/openalex.org\/W7132960968",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "OpenBU (Boston University)",
            "source_record_id": "W7132960968",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:57",
            "updated_at": "2026-11-15 16:52:57"
        },
        {
            "id": 1048,
            "title": "Image Classification with Evolved Convolutional Neural Networks",
            "title_ar": "",
            "title_en": "Image Classification with Evolved Convolutional Neural Networks",
            "author": "Darnowsky, Philip",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Harvard University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United States",
            "governorate": "",
            "publication_year": 2022,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "image-classification",
            "categories": "machine-learning; deep-learning; computer-vision; optimization; cnn; image-classification",
            "keywords": "",
            "abstract": "Convolutional neural networks (CNNs) are a well-established technique for image classification problems. While the topology of a CNN strongly affects the performance of that CNN, designing a CNN’s topology remains a difficult task, often with nothing better than some empirical rules-of-thumb for guidance. Evolutionary algorithms are a family of metaheuristics that can be applied to optimization problems where good solutions are hard to create from first principles, but the quality of a given solution is easy to measure. In this research, we develop and evaluate several variations on an algorithm, SDAG, which applies evolutionary methods to finding performant topologies for CNN-based image classifiers.",
            "source_url": "https:\/\/openalex.org\/W7112923353",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Digital Access to Scholarship at Harvard (DASH) (Harvard University)",
            "source_record_id": "W7112923353",
            "other_sources": "",
            "verification_status": "needs_review",
            "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": 1070,
            "title": "Optimisation Methods For Training Deep Neural Networks in Speech Recognition",
            "title_ar": "",
            "title_en": "Optimisation Methods For Training Deep Neural Networks in Speech Recognition",
            "author": "Haider, Mustafa Adnan",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Cambridge",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "speech-recognition",
            "categories": "machine-learning; deep-learning; nlp; optimization; speech-recognition",
            "keywords": "",
            "abstract": "Automatic Speech Recognition (ASR) is an example of a sequence to sequence level classification task where, given an acoustic waveform, the goal is to produce the correct word level hypotheses. In machine learning, a classification problem such as ASR is solved in two stages: an inference stage that models the uncertainty associated with the choice of hypothesis given the acoustic waveform using a mathematical model, and a decision stage which employs the inference model in conjunction with decision theory to make optimal class assignments. With the advent of careful network initialisation and GPU computing, hybrid Hidden Markov Models (HMMs) augmented with Deep Neural Networks (DNNs) have shown to outperform traditional HMMs using Gaussian Mixture Models (GMMs) in solving the inference problem for ASR. In comparison to GMMs, DNNs possess a better capability to model the underlying non-linear data manifold due to their deep and complex structure. While the structure of such models gives rich modelling capability, it also creates complex dependencies between the parameters which can make learning difficult via first order stochastic gradient descent (SGD). The task of finding the best procedure to train DNNs continues to be an active area of research and has been made even more challenging by the availability of ever more training data. This thesis focuses on designing better optimisation approaches to train hybrid HMM-DNN models using sequence level discriminative criterion which is a natural loss function that preserves the sequential ordering of frames within a spoken utterance. The thesis presents an implementation of the second order Hessian Free (HF) optimisation method, and shows how the method can made efficient through appropriate modifications to the Conjugate Gradient algorithm. To achieve better convergence than SGD, this work explores the Natural Gradient method to train DNNs with discriminative sequence training. In the DNN literature, the method has been applied to train models for the Maximum Likelihood objective criterion. A novel contribution of this thesis is to extend this approach to the domain of Minimum Bayes Risk objective functions for discriminative sequence training. With sigmoid models trained on a 50hr and 200hr training set from the Multi-Genre Broadcast 1 (MGB1) transcription task, the NG method applied in a HF styled optimisation framework is shown to achieve better Word Error Rate (WER) reductions on the MGB1 development set than SGD from sequence training. This thesis also addresses the particular issue of overfitting between the training criterion and WER, that primarily arises during sequence training of DNN models that use Rectified Linear Units (ReLUs) as activation functions. It is shown how by scaling with the Gauss Newton matrix, the HF method unlike other approaches can overcome this issue. Seeing that different optimisers work best with different models, it is attractive to have a consistent optimisation framework that is agnostic to the choice of activation function. To address the issue, this thesis develops the geometry of the underlying function space captured by different realisations of DNN model parameters, and presents the design considerations for an optimisation algorithm to be well defined on this space. Building on this analysis, a novel optimisation technique called NGHF is presented that uses both the direction of steepest descent on a probabilistic manifold and local curvature information to effectively probe the error surface. The basis of the method relies on an alternative derivation of Taylor’s theorem using the concepts of manifolds, tangent vectors and directional derivatives from the perspective of Information Geometry. Apart from being well defined on the function space, when framed within a HF style optimisation framework, the method of NGHF is shown to achieve the greatest WER reductions from sequence training on the MGB1 development set with both sigmoid and ReLU based models trained on the 200hr MGB1 training set. The evaluation of the above optimisation methods in training different DNN model architectures is also presented.",
            "source_url": "https:\/\/openalex.org\/W2922432155",
            "pdf_url": "",
            "doi": "10.17863\/cam.37773",
            "handle": "",
            "repository_name": "Apollo (University of Cambridge)",
            "source_record_id": "W2922432155",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "id": 1120,
            "title": "Multimodal neural machine translation",
            "title_ar": "",
            "title_en": "Multimodal neural machine translation",
            "author": "Malek Mgaidi",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Spain",
            "governorate": "",
            "publication_year": 2016,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "machine-translation",
            "categories": "machine-learning; deep-learning; computer-vision; nlp; optimization; multimodal; video-analysis; machine-translation; speech-recognition",
            "keywords": "",
            "abstract": "Neural Machine Translation is a newly emerging approach to machine translation which attempts to build and train a large neural network that reads a sentence and outputs a notable translation. Nowadays the performance of such machines is in- creasingly in demand and Multilingual Neutral Machine Translation has emerged. There is an abundant bibliography on Multimodal Neutral Machine Translation as there is a consistent number of models which differ by the final aspects of trans- lation (adequacy, fidelity and fluency) and the multitude of inputs they can use (images, videos, text, speech or a combination of them). The GroundedTranslation was chosen in this work. As we know, by far, the state- of-the art provides some techniques such as using Long Short Term Memory and an encoder-decoder architecture for example to solve some training problems and they already have been implemented by Elliot Desmond for this retained solution. However, no investigation has been oriented toward the optimizer. This work aims to study multimodal neural machine translation architectures and its behavior un- der different optimization algorithms.",
            "source_url": "https:\/\/openalex.org\/W2520119691",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "RECERCAT (Consorci de Serveis Universitaris de Catalunya)",
            "source_record_id": "W2520119691",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "id": 1139,
            "title": "Intelligent data mining using artificial neural networks and genetic algorithms : techniques and applications",
            "title_ar": "",
            "title_en": "Intelligent data mining using artificial neural networks and genetic algorithms : techniques and applications",
            "author": "Jianhua Yang",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Warwick",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "xai",
            "categories": "machine-learning; deep-learning; medical-ai; responsible-ai; expert-systems; data-mining; predictive-analytics; optimization; xai",
            "keywords": "",
            "abstract": "Data Mining (DM) refers to the analysis of observational datasets to find relationships and to summarize the data in ways that are both understandable and useful. Many DM techniques exist. Compared with other DM techniques, Intelligent Systems (ISs) based approaches, which include Artificial Neural Networks (ANNs), fuzzy set theory, approximate reasoning, and derivative-free optimization methods such as Genetic Algorithms (GAs), are tolerant of imprecision, uncertainty, partial truth, and approximation. They provide flexible information processing capability for handling real-life situations. This thesis is concerned with the ideas behind design, implementation, testing and application of a novel ISs based DM technique. The unique contribution of this thesis is in the implementation of a hybrid IS DM technique (Genetic Neural Mathematical Method, GNMM) for solving novel practical problems, the detailed description of this technique, and the illustrations of several applications solved by this novel technique. GNMM consists of three steps: (1) GA-based input variable selection, (2) Multi- Layer Perceptron (MLP) modelling, and (3) mathematical programming based rule extraction. In the first step, GAs are used to evolve an optimal set of MLP inputs. An adaptive method based on the average fitness of successive generations is used to adjust the mutation rate, and hence the exploration\/exploitation balance. In addition, GNMM uses the elite group and appearance percentage to minimize the randomness associated with GAs. In the second step, MLP modelling serves as the core DM engine in performing classification\/prediction tasks. An Independent Component Analysis (ICA) based weight initialization algorithm is used to determine optimal weights before the commencement of training algorithms. The Levenberg-Marquardt (LM) algorithm is used to achieve a second-order speedup compared to conventional Back-Propagation (BP) training. In the third step, mathematical programming based rule extraction is not only used to identify the premises of multivariate polynomial rules, but also to explore features from the extracted rules based on data samples associated with each rule. Therefore, the methodology can provide regression rules and features not only in the polyhedrons with data instances, but also in the polyhedrons without data instances. A total of six datasets from environmental and medical disciplines were used as case study applications. These datasets involve the prediction of longitudinal dispersion coefficient, classification of electrocorticography (ECoG)\/Electroencephalogram (EEG) data, eye bacteria Multisensor Data Fusion (MDF), and diabetes classification (denoted by Data I through to Data VI). GNMM was applied to all these six datasets to explore its effectiveness, but the emphasis is different for different datasets. For example, the emphasis of Data I and II was to give a detailed illustration of how GNMM works; Data III and IV aimed to show how to deal with difficult classification problems; the aim of Data V was to illustrate the averaging effect of GNMM; and finally Data VI was concerned with the GA parameter selection and benchmarking GNMM with other IS DM techniques such as Adaptive Neuro-Fuzzy Inference System (ANFIS), Evolving Fuzzy Neural Network (EFuNN), Fuzzy ARTMAP, and Cartesian Genetic Programming (CGP). In addition, datasets obtained from published works (i.e. Data II & III) or public domains (i.e. Data VI) where previous results were present in the literature were also used to benchmark GNMM’s effectiveness. As a closely integrated system GNMM has the merit that it needs little human interaction. With some predefined parameters, such as GA’s crossover probability and the shape of ANNs’ activation functions, GNMM is able to process raw data until some human-interpretable rules being extracted. This is an important feature in terms of practice as quite often users of a DM system have little or no need to fully understand the internal components of such a system. Through case study applications, it has been shown that the GA-based variable selection stage is capable of: filtering out irrelevant and noisy variables, improving the accuracy of the model; making the ANN structure less complex and easier to understand; and reducing the computational complexity and memory requirements. Furthermore, rule extraction ensures that the MLP training results are easily understandable and transferrable.",
            "source_url": "https:\/\/openalex.org\/W2111157768",
            "pdf_url": "http:\/\/wrap.warwick.ac.uk\/3831\/1\/WRAP_THESIS_Yang_2010.pdf",
            "doi": "10.82444\/warw.33491953",
            "handle": "",
            "repository_name": "Warwick Research Archive Portal (University of Warwick)",
            "source_record_id": "W2111157768",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "id": 1140,
            "title": "The development of new artificial intelligence based hybrid techniques combining bees algorithm, data mining and genetic algorithm for detection, classification and prediction of faults in induction motors",
            "title_ar": "",
            "title_en": "The development of new artificial intelligence based hybrid techniques combining bees algorithm, data mining and genetic algorithm for detection, classification and prediction of faults in induction motors",
            "author": "Ammar K. Al-Musawi",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Cardiff University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2019,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "data-mining",
            "categories": "machine-learning; computer-vision; ai-applications; data-mining; predictive-analytics; optimization; ai-industry",
            "keywords": "",
            "abstract": "This thesis focuses on applying Artificial Intelligence (AI) methods for detecting, classifying and predicting the faults in induction motors in order to prevent any failures happening during their operation due to loading conditions. It is very important to monitor and detect any faults in the motor during its operation in order to alert the operators so that potential problems could be avoided. In this study, a new AI algorithm has been developed and applied to detect, classify and predict the induction motor faults at an early stage. This is based on a hybrid approach using the Bees Algorithm (BA) and Data Mining called Bee for Mining (B4M), which overcomes the drawbacks of current AI methods in achieving higher classification accuracy with reduced rule set generated from the training data. The proposed B4M algorithm has been implemented, tested and validated using the University of California at Irvine (UCI) dataset, and was compared with other well-known classifiers. Later, the proposed B4M algorithm was applied in dealing with two most common faults, firstly, that of rotor (one rotor bar, four rotor bars and eight rotor bars), and secondly, bearing defects (inner race, outer race and ball bearing defects). In this research, three condition monitoring techniques involving thermal imaging, current and vibration signal processing have been used to monitor these faults. Further, features such as image metrics and Discrete Wavelet Transform (DWT) coefficients were extracted from the thermal images, and DWT coefficients from the current and vibration signals. Later, five-feature selection methods were applied in order to select the best features for defect classification. Finally, an improvement to the proposed B4M was made by producing a new hybrid classification algorithm by combining The Development of New Artificial Intelligence based Hybrid Techniques Combining Bees Algorithm, Data Mining and Genetic Algorithm for Detection, Classification and Prediction of Faults in Induction Motors Page | v Genetic Algorithm (GA) with B4M referred to as GA-B4M where the GA was used for feature selection. The new algorithms were successfully implemented on MATLAB and its performance was tested on real data and compared with other algorithms using the WEKA software. The results obtained for the thermal image monitoring data showed 98.97% classification accuracy with a reduced rule set containing 10 rules for B4M while a 100% accuracy with a larger rule set of 63 and 72 rules were achieved by Decision Table and OneR classifiers respectively. For the current monitoring data, the classification accuracy fell to 79.62% with only 8 rules for B4M, while 79.20% with 837 rules was achieved by Random Tree. Similarly, for the vibration monitoring data the B4M achieved 80.05% with 7 rules in comparison with Naïve Bayes tree at 79.25% with 31 rules. Furthermore, the results achieved by the proposed hybrid approach GAB4M on thermal imaging dataset also showed an overall improvement on the classification accuracy reaching 99.85% with 7 rules. Similarly, on the current and vibration dataset the GA-B4M obtained 79.98% with 16 rules and 98.74% with 7 rules respectively. This study has shown that the new proposed classification algorithms B4M and GA-B4M are able to detect, classify and predict the induction motor faults more reliably.",
            "source_url": "https:\/\/openalex.org\/W2982461209",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "ORCA Online Research @Cardiff (Cardiff University)",
            "source_record_id": "W2982461209",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "id": 1153,
            "title": "Data mining in computational finance",
            "title_ar": "",
            "title_en": "Data mining in computational finance",
            "author": "Swati Jadhav",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Cranfield University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2017,
            "language": "en",
            "research_domain": "machine-learning",
            "research_subdomain": "data-mining",
            "categories": "machine-learning; data-mining; predictive-analytics; optimization",
            "keywords": "",
            "abstract": "Computational finance is a relatively new discipline whose birth can be traced back to early 1950s. Its major objective is to develop and study practical models focusing on techniques that apply directly to financial analyses. The large number of decisions and computationally intensive problems involved in this discipline make data mining and machine learning models an integral part to improve, automate, and expand the current processes. One of the objectives of this research is to present a state-of-the-art of the data mining and machine learning techniques applied in the core areas of computational finance. Next, detailed analysis of public and private finance datasets is performed in an attempt to find interesting facts from data and draw conclusions regarding the usefulness of features within the datasets. Credit risk evaluation is one of the crucial modern concerns in this field. Credit scoring is essentially a classification problem where models are built using the information about past applicants to categorise new applicants as ‘creditworthy’ or ‘non-creditworthy’. We appraise the performance of a few classical machine learning algorithms for the problem of credit scoring. Typically, credit scoring databases are large and characterised by redundant and irrelevant features, making the classification task more computationally-demanding. Feature selection is the process of selecting an optimal subset of relevant features. We propose an improved information-gain directed wrapper feature selection method using genetic algorithms and successfully evaluate its effectiveness against baseline and generic wrapper methods using three benchmark datasets. One of the tasks of financial analysts is to estimate a company’s worth. In the last piece of work, this study predicts the growth rate for earnings of companies using three machine learning techniques. We employed the technique of lagged features, which allowed varying amounts of recent history to be brought into the prediction task, and transformed the time series forecasting problem into a supervised learning problem. This work was applied on a private time series dataset.",
            "source_url": "https:\/\/openalex.org\/W3142208920",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "CERES (Cranfield University)",
            "source_record_id": "W3142208920",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        },
        {
            "id": 1156,
            "title": "A data mining approach for automated classification of Alzheimer's disease",
            "title_ar": "",
            "title_en": "A data mining approach for automated classification of Alzheimer's disease",
            "author": "Alexander Luke Spedding",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Reading",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "United Kingdom",
            "governorate": "",
            "publication_year": 2018,
            "language": "en",
            "research_domain": "medical-ai",
            "research_subdomain": "data-mining",
            "categories": "machine-learning; computer-vision; medical-ai; data-mining; predictive-analytics; optimization",
            "keywords": "",
            "abstract": "This work presents the creation of classifiers able to automatically diagnose Alzheimer’s disease from structural magnetic resonance images. Measurements of regions inside the human brain and how they relate to a diagnosis of Alzheimer’s disease are investigated. A genetic algorithm is used to extract a subset of brain measurements which have some of the highest predictive power when compared to the rest of the measurements. A descriptive classifier is created which uses the size of each of the hippocampal volumes of a subject and compares it to the distribution of other subjects. Based on how the individual subject’s measurements compares to the distribution, we can determine whether it is an Alzheimer’s disease predictive volume. This classifier achieves an accuracy equivalent to state-of-the-art approaches. A second descriptive classifier is created using a regression model to predict a healthy subject’s age and applying this to Alzheimer’s disease positive subjects to generate an apparent brain age. The classification accuracy of when the apparent brain age is compared to the subject’s real age is comparable to the state-of-the-art methods in the literature.",
            "source_url": "https:\/\/openalex.org\/W2981015562",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "CentAUR (University of Reading)",
            "source_record_id": "W2981015562",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:59",
            "updated_at": "2026-11-15 16:52:59"
        },
        {
            "id": 1223,
            "title": "Implementasi Particle Swarm Optimization pada NPC Hunter untuk pencarian NPC Hewan Hunter of Forest",
            "title_ar": "Implementasi Particle Swarm Optimization pada NPC Hunter untuk pencarian NPC Hewan Hunter of Forest",
            "title_en": "",
            "author": "Achmad Ihwany",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Maulana Malik Ibrahim State Islamic University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Indonesia",
            "governorate": "",
            "publication_year": 2018,
            "language": "ar",
            "research_domain": "machine-learning",
            "research_subdomain": "optimization",
            "categories": "machine-learning; optimization",
            "keywords": "",
            "abstract": "مستخلص البحث تحسين سرب الجسيمات (PSO) ، والذي يحاكي شخصية مجموعة من الطيور أو الأسماك. تحاكي خوارزمية PSO السلوك الاجتماعي لهذا الكائن الحي. يتكون السلوك الاجتماعي من العمل الفردي وتأثير الأفراد الآخرين في المجموعة. كلمة الجسيمات تثبت ، على سبيل المثال ، طائرًا في قطيع من الطيور. في كل شخصية فردية أو جسيمية باستخدام ذكائه الخاص وأيضاً بسبب سلوكه الجماعي المشترك. لذلك ، إذا كان أحد الجسيمات أو طائر واحد يحصل على أفضل مسار أو أسرع مسار إلى مصدر الغذاء ، فسيجد الطائر الآخر أو المجموعة الأخرى أيضًا المسار الأسرع أو الأسرع ، على الرغم من أن موقعه بعيد جدًا في المجموعة قبل ، أحرف غير المشغِّل (NPC) أو تسمى أيضًا بالكيانات هي كيان في اللعبة لا يتحكم فيه المشغل مباشرة. يتم التحكم في NPC تلقائيًا بواسطة الكمبيوتر. لتكون قادرة على الحصول على سلوك ذكي من المجلس الوطني للمرأة استخدام الذكاء الاصطناعي أو الذكاء الاصطناعي (منظمة العفو الدولية). يتم استخدام. AIS في NPC من خلال توفير خوارزميات محددة وفقًا للسلوك الذكي المتوقع تتناول هذه الدراسة تطبيق خوارزمية تحسين سرع الجسيمات لتحديد سلوك صائد NPC في لعبة \" صياد الغابة. \" حتى تتمكن من تحديد سلوك الصياد في لعبة FPS صياد الغابة المعتمدة على سطح المكتب نتيجة هذا البحث ، هذا البحث ينجح أقصر طريق إلى لعبة الصيد المطبق على NPC Hunter بشكل حيوي باستخدام خوارزمية سرب تحسين الجسيمات ABSTRACT Particle swarm optimization (PSO), which mimics the character of a group of birds or fish. The PSO algorithm mimics the social behavior of this organism. Social behavior consists of individual action and the influence of other individuals in a group. The word particle proves, for example, a bird in a flock of birds. In each individual or particle character using his own intelligence and also due to his collective joint behavior. Therefore, if one of the particles or one bird gets the best path or the fastest path to the food source, the other bird or other group will also find the fastest or fastest route, although their location is far in the group before . Non-Player Characters (NPC) or also called agents are an in-game entity that is not directly controlled by the player. NPC is automatically controlled by computer. To be able to obtain intelligent behavior from NPC used artificial intelligence or Artificial Intelligence (AI). The use of AI in NPC is done by providing specific algorithms according to the expected intelligent behavior. This study discusses the Implementation of Particle Swarm Optimization Algorithm for Determining the Behavior of NPC Hunter in \"Hunter Of Forest\" Game In order to be able to determine the hunter behavior in the desktop-based FPS Hunter Of Forest game. The result of this research is, This research succeed the shortest path to game hunting applied to NPC Hunter dynamically using Particle Swarm Optimization Algorithm ABSTRAK Particle swarm optimization (PSO), yang meniru karakter sekelompok burung atau ikan. Algoritma PSO meniru perilaku sosial organisme ini. Perilaku sosial terdiri dari aksi individu dan pengaruh dari individu-individu lain dalam suatu kelompok. Kata partikel membuktikan, misalnya, seekor burung dalam kawanan burung. Pada masing-masing individu atau partikel berkarakter memakai kecerdasannya (intelligence) sendiri dan juga diakibatkan tingkah laku gabungan kolektifnya. Maka dari itu, apabila salah satu dari partikel atau satu burung mendapatkan jalan yang terbaik atau jalan yang tercepat untuk menuju ke sumber makanan, maka burung yang lain atau kelompok yang lain juga akan menemukan jalur tebaik atau tercepat tadi, meskipun lokasinya mereka jauh di kelompok tadi. Non-Player Characters (NPC) atau disebut juga agen adalah suatu entitas dalam game yang tidak dikendalikan secara langsung oleh pemain. NPC dikendalikan secara otomatis oleh komputer. Untuk dapat memperoleh perilaku cerdas dari NPC digunakan kecerdasan buatan atau Artificial Intelligence (AI). Penggunaan AI pada NPC dilakukan dengan pemberian algoritma khusus sesuai dengan perilaku cerdas yang diharapkan. Penelitian ini membahas mengenai Implementasi Algoritma Particle Swarm Optimization Untuk Menentukan Perilaku NPC Hunter Pada Game “Hunter Of Forest” Dengan tujuan agar dapat menentukan prilaku hunter pada game FPS Hunter Of Forest yang berbasis dekstop. Hasil dari penelitian ini adalah, Penelitian ini berhasil jalur terpendek menuju hewan buruan yang diterapkan pada NPC Hunter secara dinamis menggunakan Algoritma Particle Swarm Optimization.",
            "source_url": "https:\/\/openalex.org\/W2907762393",
            "pdf_url": "http:\/\/etheses.uin-malang.ac.id\/12535\/1\/11650087.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "eTheses of Maulana Malik Ibrahim State Islamic University (Maulana Malik Ibrahim State Islamic University)",
            "source_record_id": "W2907762393",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:59",
            "updated_at": "2026-11-15 16:52:59"
        },
        {
            "id": 1228,
            "title": "Diversity in Reinforcement Learning",
            "title_ar": "",
            "title_en": "Diversity in Reinforcement Learning",
            "author": "Arno Feiden",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "University of Bonn",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Germany",
            "governorate": "",
            "publication_year": 2026,
            "language": "en",
            "research_domain": "computer-vision",
            "research_subdomain": "predictive-analytics",
            "categories": "machine-learning; computer-vision; reinforcement-learning; predictive-analytics; optimization",
            "keywords": "",
            "abstract": "Reinforcement learning is a machine learning paradigm that aims to develop optimal policies for discrete-time control problems based on quantitative feedback on the learner’s behaviour. Reinforcement learning is formulated as a gradient-based optimisation procedure, but reinforcement learning problems with unique optimal solutions are rare. This work focuses on ways to distinguish policies that solve the same reinforcement learning problem differently. A pointed analysis of reinforcement learning literature, specifically of policy gradient methods, shows that policies are best understood through their behaviour: The actions that the policy selects based on the encountered state. There are two equivalent main approaches to understanding this behaviour empirically: Episodic behavioural characterisation, which interprets a policy as a random element in the space of state-action time series and behavioural characterisation through the occupancy measure, which interprets a policy as a random element representing the visitation frequency in the space of state-action pairs. Both characterisations can be used to deduce general, problem-agnostic distance measures either by comparing time series or by comparing sampled distributions. Their utility is first explored by visualising small populations of policies. The relationships between policies that emerge in the visualisation also reflect other, hidden relationships, thereby validating the approach. This idea is then integrated with an evolutionary algorithm. Evolutionary computation is a branch of optimisation techniques that improve populations of candidate solutions. In quality-diversity methods specifically, the members of the population are encouraged to differ from one another to improve the evolutionary process. When these methods are used to solve reinforcement learning problems, a measure of distance between candidate solutions is required. The developed techniques to distinguish policies are successfully connected with MAP-Elites, a quality-diversity heuristic that is often used for reinforcement learning problems and typically distinguishes policies based on selective, problem-specific criteria. The applications validate the established general distances measure, but they also show that a diverse population of solutions is, for example, more explorative and more robust against environmental changes even if the diversity is not directed towards the specific goal such as exploration or robustness. This reveals the intrinsic value of diversity.",
            "source_url": "https:\/\/openalex.org\/W7172577797",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "bonndoc (University of Bonn)",
            "source_record_id": "W7172577797",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:59",
            "updated_at": "2026-11-15 16:52:59"
        },
        {
            "id": 1320,
            "title": "An effective sentiment analysis using machine learning and swarm intelligence schemes",
            "title_ar": "",
            "title_en": "An effective sentiment analysis using machine learning and swarm intelligence schemes",
            "author": "T. Saravanan",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "India",
            "governorate": "",
            "publication_year": 2017,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "sentiment-analysis",
            "categories": "machine-learning; nlp; optimization; sentiment-analysis",
            "keywords": "",
            "abstract": "",
            "source_url": "https:\/\/openalex.org\/W3159760934",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Shodhganga",
            "source_record_id": "W3159760934",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:53:01",
            "updated_at": "2026-11-15 16:53:01"
        }
    ]
}