Master Informatique
Permanent URI for this collectionhdl:123456789/1389
Browse
322 results
Search Results
Item Une solution IA pour médias et institutions face aux fake news SUR LES RÉSEAUX SOCIAUX(University of Mohamed El Bachir El Ibrahimi - Bordj Bou Arréridj, 2026) Sebaihi riadhThis work aims to develop an intelligent system for the automatic detection of fake news amid the widespread circulation of digital content. The system relies on natural language processing techniques and the analysis of textual content in news articles. Machine learning and deep learning algorithms were employed to classify news as true or false. Experiments were conducted on real datasets, and performance was evaluated using metrics such as accuracy and F1-score. The results demonstrate the effectiveness of intelligent models in reducing the spread of misinformationItem Fingerprint Classification for AFIS Search-Space Reduction Using Deep Learning(University of Mohamed El Bachir El Ibrahimi - Bordj Bou Arréridj, 2026) Mechri abdelhafid; Tebbi mohammed amineFingerprint-based Automatic Fingerprint Identification Systems (AFIS) perform 1:N matching by comparing each query against every enrolled template in the gallery, a procedure whose computational cost scales linearly with gallery size and becomes prohibitive at operational scale. This thesis addresses that bottleneck by developing a deep learning-based Henry-class pre-classification stage that partitions the enrolled gallery into five class-labelled bins before matching, restricting each identification query to the relevant subset and reducing the active comparison set without discarding correct candidates. The classification system was developed and evaluated on NIST Special Database 4 (NIST SD4), a 2 000-image benchmark comprising matched F/S impression pairs across all five Henry classes. Three fingerprint input representations were investigated — raw CLAHE-enhanced images, Orientation Field Enhancement Maps (OFEM), and HSV-encoded orientation fields — and five ImageNet-pretrained convolutional backbone architectures were evaluated: EfficientNet-B3, ResNet50, MobileNetV3-Small, VGG16-BN, and ConvNeXt-Tiny. Orientation-field encoding consistently outperformed raw and OFEM representations across all architectures, establishing input representation quality as the dominant performance factor. ConvNeXt-Tiny, trained on a dual raw-and-orientation-field input, achieved 92.50% standalone accuracy. A binary VGG16-BN specialist, trained with Focal Loss and controlled oversampling to address the chronic underperformance on the Tented Arch minority class, raised the Tented Arch F1-score from 0.606 to 0.808. Integration of the specialist through a confidence-gated veto mechanism produced the final dual-architecture system, reaching 93.25% overall classification accuracy. The operational contribution of the classification system was validated by integrating it with the SourceAFIS 3.18.1 minutiae-based matching engine within a complete 1:N identification pipeline. Three search-space scenarios were evaluated: full-gallery baseline (Scenario A, 2 000 comparisons), single-bin classification-guided search (Scenario B, ≈400 comparisons), and dual-bin search (Scenario B+, ≈800 comparisons). The B+ strategy preserved near-complete identification accuracy — 87.50% Rank-1 — while reducing active comparisons by 2.61× relative to the full-gallery baseline. A Gabor score-fusion stage, applying Gabor-enhanced template matching in parallel with raw matching and combining scores via a conservative max-fusion rule, lowered the Equal Error Rate from 13.36% to 8.58% by recovering 153 identification failures attributable to poor-quality probe impressions, while breaking only 14 previously passing matches. The principal finding of this thesis is the empirical demonstration that a deep learning classification front-end, integrated with a traditional minutiae matcher, delivers measurable and reproducible search-space reduction without sacrificing identification accuracy. The dual-architecture design, the Gabor fusion strategy, and the honest characterisation of the conditions under which the approach succeeds and fails together constitute a reproducible and extensible foundation for future work in adaptive AFIS search-space reduction.Item Détection de la somnolence du conducteur à l’aide de techniques d’intelligence artificielle(University of Mohamed El Bachir El Ibrahimi - Bordj Bou Arréridj, 2026) SALI Oussama; Benameur ZahraThis thesis focuses on the design and implementation of a driver drowsiness detection system based on the analysis of eye closure from video images. The objective is to automatically identify signs of drowsiness in real time by monitoring the driver's eyelid state. When the system detects that both eyes remain closed for a critical period, an audible alarm is immediately triggered to alert the driver and help prevent potential accidents. The proposed system relies on image processing and artificial intelligence techniques. The video is first analyzed to detect the driver's face using a face detector based on the Single Shot Detector (SSD) architecture, implemented through OpenCV's Deep Neural Network (DNN) module. The eyes are then localized using Haar Cascade classifiers. The extracted eye regions are analyzed by a Convolutional Neural Network (CNN) specifically trained to distinguish between open and closed eyes. The driver's level of alertness is continuously monitored using a scoring system that differentiates normal blinking from actual drowsiness episodes. When the score exceeds a predefined threshold, an audible alarm is activated to warn the driver.Item E-Health Digital Records Platform(University of Mohamed El Bachir El Ibrahimi - Bordj Bou Arréridj, 2026) Zouaoui Abdelghafour; Bouhali Abdelghafour; Salhi Amine; Haddad AbdelouadoudThis thesis presents the design and implementation of a multimodal biometric recognition system integrated into a full-stack E-Health web and mobile platform. Three physiological biometric modalities (iris, face, and fingerprint) are individually trained using ResNet-50 deep neural networks with ArcFace angular margin loss, then fused at score level using several strategies, including a Verification-Based Learned Fusion approach. The resulting system achieves a Rank-1 accuracy of 98.98% and an Equal Error Rate (EER) of 0.84% on a 64- subject test cohort of 3,444 probe samples. The biometric engine is deployed as a Python FastAPI microservice consumed by a Next.js 16 web application with role-based access control, while a Flutter mobile application extends access to Android patients. The platform follows Privacy-by-Design principles by storing only 512- dimensional embedding vectorsItem Étude des Techniques d’Interprétabilité Appliquées aux Modèles CNN pour la Détection Précoce de la Maladie d’Alzheimer à Partir d’Images IRM.(university of bordj bou arreridj, 2026) Chihab Imane Khadidja; Zouache HananeThis thesis aimed to develop an intelligent and innovative system to facilitate the early diagnosis of Alzheimer’s disease, using magnetic resonance imaging (MRI) and deep learning techniques. To achieve this, several convolutional neural network (CNN) models, such as Xception, MobileNet, and EfficientNet, were used to extract rich and subtle features from the images. This data was then integrated with classical machine learning algorithms, such as SVM, KNN, and Random Forest, to classify the stages of disease progression. The experimental results demonstrated that combining convolutional neural networks and machine learning algorithms provides optimal accuracy in disease classification. The hybrid model (Xception +SVM) achieved the greatest generalizability and the best diagnostic accuracy. To ensure the reliability of medical results and foster trust with clinicians, "Explainable AI methods, such as Grad-CAMandSHAP, have been integrated to provide a visual and systematic analysis that clarifies the model’s decision-making process. Furthermore, the research has led to the design of an integrated medical platform using the Flask framework. This platform allows users to intelligently manage patient data, upload MRI images, run prediction algorithms, view classification results, and interact with the model’s visual interpretations.Item Design and Implementation of a SIEM Platform for Enhanced Cybersecurity Monitoring and Incident Management(university of bordj bou arreridj, 2026) SANA Ishak Elmouatassem Billah; AOURAGH Omar Mehdi; OULD AMER Nassim; ROUABAH AdemThis project presents the design and implementation of a Security Information and Event Management platform aimed at improving cybersecurity monitoring and incident management within organizations. The proposed solution addresses the limitations of existing SIEM systems, particularly in terms of cost, complexity, and lack of adaptation to local operational environments. The platform is designed using a modular architecture that enables the collection, normalization, and analysis of security events from multiple sources. It incorporates a rule-based detection engine to identify suspicious activities and generate alerts in near real-time. The system also provides an intuitive interface for Security Operations Center analysts to monitor alerts, investigate incidents, and manage detection rules efficiently. The solution targets different SOC roles, including Level 1, Level 2, and Level 3 analysts, detection engineers, and system administrators, ensuring a structured and role-based approach to security operationsItem Système intelligent de gestion de présence des étudiants basé sur la reconnaissance faciale(university of bordj bou arreridj, 2026) Khedara Issam Eddine; Souahlia Yacine; Zemrak Anis; Madoui AthmaneFacial recognition is a technology based on artificial intelligence and computer vision that enables the identification or verification of a person’s identity from their face. It is widely used in security systems and biometric applications and plays an important role today in the automation of digital services.This thesis presents the design and implementation of an intelligent student attendance management system based on facial recognition. The system aims to improve and automate academic management within university institutions. The system is organized around three main roles: the administrator, the teacher, and the student. The administrator has user management functionalities, including adding, modifying, and deleting students and teachers, as well as managing subjects and groups. The administrator can also access statistics related to student attendance and absence.The teacher uses the system to track student attendance through facial recognition, as well as to manage grades for tutorials (TD) and practical work (TP). The teacher can also view attendance statistics. The student can access a personal space to view their information, subjects, teachers, and grades assigned by instructors. They can also monitor their attendance status.The system relies on computer vision and machine learning techniques to ensure fast and reliable face recognition, thereby improving the efficiency and quality of university management.Item Conception et réalisation d’une solution numérique pour faciliter l’accès aux médicaments en Algérie(university of bordj bou arreridj, 2026) Lidia SEHILI; Ahlem BELAGGOUNE; Maroua GAOUET; Sabrina ADROUCHEThe healthcare sector is undergoing rapid digital transformation ; however, patients in Algeria still face difficulties in quickly finding medicines available in pharmacies due to the lack of centralized solutions and the fragmentation of data. To address this issue, we designed and developed WinDawa, a digital platform aimed at facilitating access to medicines and strengthening communication between citizens and pharmacies. This solution is based on a mobile application developed with Flutter, intended for citizens, as well as a web application developed with React, providing a dedicated space for pharmacists to manage their medicine stock visible on the platform, and another space dedicated to administrators for data management, monitoring, and overall platform supervision. The system relies on a backend developed with Laravel. Communication with the mobile application is ensured through a REST API architecture, guaranteeing smooth, secure, and efficient data exchange. For web applications, interaction with the backend is handled via Inertia.js, enabling seamless integration between the server and web interfaces.WinDawa enables, among other features, real-time medicine search and the location of nearby pharmacies that have them in stock, as well as online reservation assisted by OCR (Optical Character Recognition) for automatic recognition of medicines in prescriptions. The platform also offers pharmaceutical stock management and notification services regarding medicine availability. Developed using an Agile approach based on Scrum, this project is part of the digital transformation of the pharmaceutical sector and contributes to improving access to information, optimizing medicine availability, and enhancing the quality of healthcare services provided to citizensItem An Explainable AI System for Parkinson’s Disease Diagnosis from MRI Images(university of bordj bou arreridj, 2026) Abderraouf CHAAParkinson’s disease, one of the most common neurodegenerative disorders worldwide, is still difficult to identify in its early stages with traditional clinical techniques. A deep learningbased method for automatically identifying Parkinson’s disease from brain MRI pictures is presented in this thesis. The NTUA Parkinson dataset, which consists of over 43,000 brain MRI pictures categorized into PD and Non-PD classes, was used to refine the Xception convolutional neural network, which had previously been trained on ImageNet. The model was tested as a feature extractor in conjunction with two machine learning classifiers, Random Forest (81.40%) and XGBoost (79.13%), as well as as a stand-alone deep learning classifier with an accuracy of 84.19%.To ensure interpretability, three Explainable AI (XAI) techniques were applied: Grad-CAM for visual explanation, SHAP for quantifying feature importance, and a Grad-CAM-based segmentation approach to localize the brain regions most associated with the disease, particularly the Substantia Nigra and Basal Ganglia. Finally, a fully functional desktop application, ParkinsonAI, was developed using CustomTkinter to integrate detection, patient management, XAI visualization, and medical report generation, complemented by a commercial web platform built with PHP and JavaScript for distribution to researchers and healthcare institutions.Item Plateforme intelligente de soutien psychologique et de thérapie en ligne basée sur l’intelligence artificielle(University of Mohamed El Bachir El Ibrahimi - Bordj Bou Arréridj, 2026) Maroua OUCHENE; Yamina DAHMOUNI; Nour Elhouda TAKOUKMental health constitutes a major public health challenge today, particularly in Algeria, where the shortage of specialists, high consultation costs, and social stigma limit access to care. Developed within the framework of a start-up project affiliated with the incubator of the University of Bordj Bou Arréridj, this thesis presents the design and implementation of INSAT, an intelligent hybrid clinical decision support platform dedicated to mental health. The existing systems review revealed that current solutions are limited to teleconsultation, lacking decision-support-oriented artificial intelligence or integration with physical clinics. In response, INSAT combines accessible digital support, AI to assist psychotherapists, and continuity with physical healthcare structures. Following an analysis and design phase based on the UML language, the platform was developed using React, FastAPI, and PostgreSQL hosted on Neon. It integrates a 24/7 multilingual companion chatbot, a diagnostic aid module powered by the CatBoost model, a therapeutic recommendation engine, and a structured electronic medical record (EMR). Validated through a rigorous testing process, the solution preserves the human dimension of care, with AI serving as an assistive tool rather than a substitute for the professional.