Master Informatique
Permanent URI for this collectionhdl:123456789/1389
Browse
313 results
Search Results
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.Item Plateforme intelligente d'analyse des symptômes pour le diagnostic préliminaire des maladies basé sur l’IA(University of Mohamed El Bachir El Ibrahimi - Bordj Bou Arréridj, 2026) * LOUNICI DOUNIA * BOUGEURRA HADIL; * BOUGEURRA HADILThis work presents MediAssist Pro, an intelligent web-based medical platform designed to improve the organization of medical work and support preliminary diagnosis. The application centralizes patient records, consultations, prescriptions, medical analysis requests and scanned results in one system. It provides role-based access for the administrator, doctor and medical secretary, ensuring that each user can access only the functions related to their responsibilities. The doctor can enter symptoms by text or voice, view the patient’s medical history and launch an artificial intelligence analysis. The system suggests possible diagnostic indications and useful recommendations, while the final medical decision remains the responsibility of the doctor. MediAssist Pro also makes it possible to generate prescriptions in PDF format and to import scanned analysis results, which can be summarized and interpreted cautiously by the AI module. The platform does not aim to replace healthcare professionals, but to provide a practical support tool that saves time, improves traceability and assists medical decision-makingItem INSAT : Plateforme intelligente de soutien psychologique et de thérapie en ligne basée sur l’intelligence artificielle(university of bordj bou arreridj, 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 professionalItem Plateforme intelligente d'analyse des symptômes pour le diagnostic préliminaire des maladies basé sur l’IA(university of bordj bou arreridj, 2026) LOUNICI DOUNIA; BOUGEURRA HADILThis work presents MediAssist Pro, an intelligent web-based medical platform designed to improve the organization of medical work and support preliminary diagnosis. The application centralizes patient records, consultations, prescriptions, medical analysis requests and scanned results in one system. It provides role-based access for the administrator, doctor and medical secretary, ensuring that each user can access only the functions related to their responsibilities. The doctor can enter symptoms by text or voice, view the patient’s medical history and launch an artificial intelligence analysis. The system suggests possible diagnostic indications and useful recommendations, while the final medical decision remains the responsibility of the doctor. MediAssist Pro also makes it possible to generate prescriptions in PDF format and to import scanned analysis results, which can be summarized and interpreted cautiously by the AI module. The platform does not aim to replace healthcare professionals, but to provide a practical support tool that saves time, improves traceability and assists medical decision-making.Item Design and Implementation of a Smart Real Estate Services Platform(university of bordj bou arreridj, 2026) ROUABAH Tayeb; BOUNABI OussamaThis thesis focuses on the design and development of a web and mobile platform dedicated to real estate and smart rental services. The main objective is to provide a modern and user-friendly solution that simplifies property searching, buying, renting, and booking through advanced filtering tools and interactive map services. The platform connects property owners with potential clients in a secure and efficient environment. It supports different types of properties, including apartments, hotels, rooms, clinics, agricultural lands, and industrial spaces. Users can explore detailed property information, locate properties using maps, and communicate directly with owners through the application. In addition, the system introduces a Smart Rental feature based on smart access management. After booking confirmation, tenants can receive temporary digital access codes or QR codes that can be integrated with smart lock systems, allowing secure and remote property access. This feature improves convenience, automation, and security, especially for short-term rentals and reservation services. Overall, the proposed platform represents a modern digital solution that enhances accessibility to real estate services, simplifies property management, reduces manual operations, and improves the overall user experienceItem Conception et développement d’une application mobile de gestion de restaurant ”smartRestoo(university of bordj bou arreridj, 2026) Maameri Houda; Sedira Fatima; Ben Hamadi NihadMaster’s degree in Computer Science. It focuses on the design and development of a mobile application dedicated to restaurant management, entitled SmartRestoo. This project primarily aims to modernize the restaurant sector by replacing traditional methods with an intelligent digital solution, contributing to improving service quality, reducing waiting times and avoiding order processing errors. This work was structured into two parts ; theoretical and practical : The theoretical part : it covers the study of the fundamental concepts of e-commerce and mobile applications, with a focus on the importance of user experience (UX/UI), information security standards and the safety of digital transactions. The practical part : it encompasses the analysis and design phase using the Unified Modeling Language (UML), followed by the implementation and development phase. On the technical side, the Flutter framework (with the Dart language) was used to develop an application dedicated to the Android system, connected to the Firebase platform as a cloud backend for data management, authentication and real-time notifications. The application offers two complementary interfaces : a customer interface allowing users to browse the menu, place orders and rate services, and a comprehensive administration interface providing a dashboard for monitoring statistics and managing orders flexibly.Item Traxio: A Multi-Tenant Real-Time Bus Tracking Platform(university of bordj bou arreridj, 2026) Houda ADDIS; Houda AZZOUGTransportation plays a vital role in daily life, making efficient fleet management and realtime transit tracking increasingly important for both transport operators and commuters. However, in Algeria, many private transportation services still rely on traditional management methods that provide limited visibility over fleet operations and little real-time information for commuters. To address these challenges, this project presents Traxio, a fleet management and real-time transit tracking platform designed to modernize transportation services. The platform is built using a cloud-based, multi-tenant Software-as-a-Service (SaaS) architecture, allowing multiple organizations to manage their fleets through a single system. It consists of a web application that enables transport operators to manage and monitor their transportation networks, and a mobile application that allows commuters to track bus locations in real time and access route information. The platform also includes an admin web application to manage operator subscriptions, operator accounts, and other platform information. Both web applications were developed using Laravel, while the mobile application was built using Flutter. The development process followed the Scrum agile methodology. By centralizing fleet management and providing real-time tracking capabilities, Traxio helps improve operational efficiency, reduce commuter uncertainty and waiting times, and support the digital transformation of transportation services in Algeria.Item Développement d'une plateforme de diagnostic RétinoCheck.com automatisée pour la rétinopathie diabétique basée sur une étude comparative de Deep Learning(university of bordj bou arreridj, 2026) Belaidi soulef; Ben hemmada HadjerDiabetes mellitus is a growing global health threat, and diabetic retinopathy (DR) is one of its most severe complications, leading to irreversible blindness. This thesis proposes an automated solution for the early screening of DR using artificial intelligence technologies. We designed and implemented a smart Web application powered by Deep Learning, specifically Convolutional Neural Networks (CNN). The system incorporates essential image pre-processing steps (such as Circle Crop and CLAHE) to enhance the visibility of retinal lesions and optimize diagnostic accuracy. The application automatically classifies fundus images into different severity stages (grades 1 to 4). The results demonstrate the effectiveness of this tool in assisting ophthalmologists with rapid and reliable diagnosis, thereby contributing to better patient care and prevention of vision lossItem Analyse et prédiction de l’attention du conducteur en conditions réelles de conduite(university of bordj bou arreridj, 2026) SAYAH ABDENNOUR; ISHAK MESSOUAFDriver attention analysis is an important research area for improving road safety and supporting advanced driver assistance systems. Predicting where drivers focus their attention helps identify the most relevant regions in a driving scene. However, this task is challenging because driver attention is influenced by many factors, including traffic conditions, moving objects, weather, and road context. This work focuses on the analysis and prediction of driver attention in real driving scenarios using the DR(eye)VE dataset, which contains driving videos, eye-tracking data, and saliency maps representing drivers’ visual attention. The proposed approach relies on deep learning to predict visual attention maps from driving images or video sequences. It exploits different sources of information, including RGB appearance, motion cues, and scene semantics. The model is evaluated using standard saliency prediction metrics such as Correlation Coefficient (CC), Kullback-Leibler Divergence (KL), and Information Gain (IG). The obtained results demonstrate the effectiveness of deep learning for modeling driver visual behavior and highlight the importance of attention prediction in intelligent transportation systems.Item Design and Implementation of an Intelligent Medical Assistant (MedBot)(university of bordj bou arreridj, 2026) Benchina Abderraouf; Saidat AhmedIn this thesis, we designed and developed a medical assistant named MedBot, intended to assist healthcare professionals during the medical consultation process. The proposed system integrates advanced artificial intelligence technologies, particularly the ChatGPT and Google Gemini language models, in order to analyze collected medical information and provide diagnostic assistance. MedBot also integrates speech recognition technology to automatically convert patients’ spoken responses into usable text. The system provides several features such as patient record management, medical summary generation, treatment suggestion, medical question catalog management, as well as biometric monitoring and pediatric growth curve tracking. The main objective of this work is to improve the efficiency of the medical consultation process while providing intelligent assistance to physicians without replacing their decision-making role.