http://dspace.univ-setif.dz:8888/jspui/handle/123456789/12 2026-05-04T15:14:53Z http://dspace.univ-setif.dz:8888/jspui/handle/123456789/6642 Titre: Ethics and Trustworthiness of Algorithmic Decision-Making Systems Auteur(s): Touameur, OUissem Résumé: The rapid adoption of artificial intelligence (AI) in high-stakes domains such as rec- ommender systems, healthcare, and disaster management has amplified the need for trustworthy systems. However, many AI models remain limited by opaque decision- making, biased or noisy data, and the lack of explicit mechanisms to model and quantify trust. This thesis addresses these limitations by integrating trust at three complementary levels—data, model, and prediction—through the combined use of knowledge graphs (KGs) and graph neural networks (GNNs). At the data and model levels, the thesis introduces a taxonomy of trust dimensions, including accuracy, reliability, provenance, fairness, robustness, and explainability, and demonstrates how structured knowledge and graph-based learning enhance transparency and relational reasoning. Building on this foundation, the first major contribution is GUITARES, a trust-aware recommender system based on graph attention networks. GUITARES integrates item confidence derived from external knowledge graphs, inferred user–user trust relationships, and structural learning over user–item graphs. Experimental evaluation shows that GUITARES achieves an RMSE of 0.80, outperforming state-of-the- art baselines while maintaining scalability and robustness. The second major contribution focuses on trust in predictions. The core framework, GraphSkinUQ, is proposed for skin cancer classification, combining CNN feature embed- dings, graph-based relational modeling, and uncertainty quantification to assess predictive confidence. GraphSkinUQ achieves 91% accuracy, with predictive uncertainty between 10% and 11%, a Brier score of 13%, an Expected Calibration Error (ECE) of 6%, and a ROC-AUC of 94%, demonstrating strong performance and well-calibrated confidence esti- mates. This predictive-trust framework is then extended to disaster management through the TDC-GCN model, which adapts the same principles—CNN features, graph convolu- tional learning, and Monte Carlo dropout—to disaster image classification. TDC-GCN achieves 97% accuracy with an entropy-based uncertainty measure of 30%, confirming its effectiveness in high-stakes scenarios. Overall, results across recommendation, medical imaging, and disaster analysis demon- strate that embedding trust mechanisms—from structured data modeling to uncertainty- aware predictions—significantly improves both performance and reliability. This thesis contributes to the development of AI systems that are not only accurate, but also transpar- ent, robust, and trustworthy. 2026-01-01T00:00:00Z http://dspace.univ-setif.dz:8888/jspui/handle/123456789/6636 Titre: Numerical Methods and Programming Auteur(s): Ziadi, Raouf Résumé: Numerous problems cannot be solved using traditional analyt- ical methods; this is why numerical methods have emerged. In many cases, approximating a solution depends on the number of operations to be performed, which presents a challenge to the application of these numerical methods. The emergence of computers and the expansion of computing have greatly facilitated the use of numerical methods, thanks to the development of algorithms implemented on machines with powerful processors. Today, technology continues to advance, constantly bringing new developments across various fields. Scientific research has progressed significantly, enabling the understanding and mod- eling of physical phenomena that were unclear just a few years ago. This progress has been made possible through numerical analysis. In this booklet, we present the numerical methods essential for second-year bachelor’s (LMD) students (Physics/Chemistry) to address many of the challenges they encounter throughout their academic studies. It is worth noting that our approach is based on two essential points: 1. The course content must be simplified. 2. The acquired knowledge is reinforced through simple ex- amples. Finally, I hope that readers will find at least something useful in this booklet. 2026-03-15T00:00:00Z http://dspace.univ-setif.dz:8888/jspui/handle/123456789/6635 Titre: Advanced Probabilities Auteur(s): ZIADI, Raouf Résumé: This booklet has been designed for first-year Master’s students in Computer Science, option: Quantum Computing. By blending theoretical foundations with illustrative examples, it aims to strengthen both intuition and analytical rigor. The material not only introduces students to key probabilistic tools but also prepares them to apply these concepts directly within the framework of quantum information theory, quantum algorithms, and related computational paradigms. 2026-03-15T00:00:00Z http://dspace.univ-setif.dz:8888/jspui/handle/123456789/6626 Titre: Knowledge Discovery in Big Data application to arabic handwriting characters recognition and genomic Auteur(s): Nasri, Khaled Résumé: The exponential growth of Big Data necessitates scalable knowledge discovery methodologies capable of handling massive, heterogeneous datasets. This dissertation explores distributed and parallel deep learning architectures across two critical application domains: genomics and Arabic handwriting recognition. In genomics, a novel distributed pipeline for variant calling integrates multimodal sequencing data through a hybrid Transformer-CNN architecture with attention-based fusion. The system simultaneously processes DNA sequence context via transformer encoders and read alignment evidence through three-dimensional convolutional networks, enabling accurate genomic variant classification while achieving computational efficiency through Distributed Data Parallel (DDP) training across multiple GPUs. Multi-task learning addresses variant type classification, genotype prediction, quality score estimation, and artifact detection, while class-weighted loss functions handle severe data imbalance inherent in genomic datasets. In Arabic handwriting recognition, a hybrid architecture embedding Capsule Networks within Residual Networks (Caps-ResNet) captures hierarchical features and spatial relationships essential for cursive script analysis. This specialized architecture overcomes unique challenges including ligature complexity, diacritical mark sensitivity, and significant stylistic variability across writing styles. This multidisciplinary research demonstrates how hybrid architectures, multimodal fusion mechanisms, and distributed computing strategies enable robust, accurate, and computationally efficient knowledge extraction systems applicable to diverse scientific domains. The results contribute to the development of scalable deep learning solutions that bridge theoretical innovations with real-world applications in genomics and natural language processing. 2026-01-01T00:00:00Z