https://dspace.univ-ouargla.dz/jspui/handle/123456789/8522 Mon, 09 Nov 2026 01:51:16 GMT 2026-11-09T01:51:16Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/41994 Titre: Real-Time Myocardial Infarction Detection Using PPG Signals and Machine Learning on Wearable Devices Auteur(s): Bensayah, Sirina Rihab; Korichi, Manar; Benlamoudi, Azeddine; Harrouz, Salah Eddine Résumé: Cardiovascular disease remains the leading cause of death globally, with myocardial infarction (MI) representing its most acute and time-critical manifestation. Current clinical diagnosis relies on hospital-based tools, namely the 12-lead electrocardiogram and serum troponin assays, which are effective but inaccessible during the critical prehospital period when early detection would have the greatest impact on patient outcomes. This thesis investigates whether photoplethysmography (PPG) signals acquired from wrist-worn wearable devices contain sufficient discriminative information to support machine learning-based MI classification, and which classifier is best suited for real-time deployment on resourceconstrained hardware. A publicly available PPG dataset from the UCI Machine Learning Repository was used, containing 2,576 samples with 2,000 amplitude features each, labelled as either Normal or Myocardial Infarction with near-perfect class balance. The experimental pipeline applied StandardScaler normalization, Principal Component Analysis dimensionality reduction from 2,000 to 50 components, and 5-fold stratified cross-validation. Four supervised classification algorithms were evaluated: Logistic Regression, Random Forest, Gradient Boosting, and Support Vector Machine. All four classifiers exceeded 95 percent accuracy on the held-out test set. Gradient Boosting achieved the highest Area Under the ROC Curve at 0.954, confirming its superior ability to capture nonlinear patterns in the PCA-reduced feature space. Logistic Regression achieved an identical accuracy of 95.5 percent with an AUC of 0.946 and is recommended for wearable deployment due to its minimal computational requirements and interpretable decision boundary. These results establish a viable proof-of-concept for continuous, passive MI detection on consumer wearables, with real-world clinical validation identified as the essential next step. Description: Telecommunication Systems Sun, 07 Jun 2026 00:00:00 GMT https://dspace.univ-ouargla.dz/jspui/handle/123456789/41994 2026-06-07T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/41991 Titre: Smart monitoring system design for voltage transformers using (Iot) and AI Auteur(s): Bennai, Ines; Ziban, Mohamed Fouad; Saggai, Abdelmoula Résumé: In order to broaden its operational efficiency and decrease unplanned failures that could compromise the continuity of electrical grids, this project intends develop and design a smart system for monitoring electrical transformers using Internet of Things (IoT) and artificial intelligence (AI) technologies. The main operational parameters of the electrical transformer, including temperature, humidity, voltage, current, oil level, and vibration, are measured by a set of sensors as part of the project concept. A microcontroller gathers and transmits this data in real time to a cloud platform, where it is stored, analysed, and displayed via an interactive control panel. The practical part of this job entailed constructing and programming the proposed system and merging all of its parts after researching the types and components of electrical transformers as well as their basic laws and circuits. Additionally, artificial intelligence methods were used to evaluate data and anticipate possible problems before they arise, enabling early intervention. The findings proved that the suggested method offers precise and efficient electrical transformer monitoring, lowers maintenance costs, increases the effectiveness of the monitoring and protection systems, and helps to improve the dependability of electrical Description: Embedded Systems Electronics Thu, 01 Jan 2026 00:00:00 GMT https://dspace.univ-ouargla.dz/jspui/handle/123456789/41991 2026-01-01T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/41985 Titre: Solution IoT pour l'optimisation et la surveillance de la distribution d'eau Auteur(s): BENISMAIL, Idriss; DADAMOUSSA, Elhadj Abdelkader Ayoub; HALOUA, Abdelghaffar; GUENDOUZ, Mohamed Elhachemi; GOUGI, chraf Imad Eddine; SAGGAI, Abdelmoula; ACHBI, Mohammed Said Résumé: Le projet Smart Flow Meter vise à concevoir un système intelligent de surveillance et de contrôle de la consommation d’eau basé sur les technologies IoT. Le système utilise une carte ESP32, un capteur de débit YF-S201, un écran LCD, une électrovanne et un module GSM SIM800L. Il permet de mesurer le débit d’eau, d’envoyer des alertes en cas de fuite ou de surconsommation et de contrôler l’alimentation en eau à distance. Le système intègre également Firebase, une application mobile et une plateforme de gestion pour améliorer la gestion des ressources hydriques. The Smart Flow Meter project aims to develop an intelligent water consumption monitoring and control system based on IoT technologies. The system uses an ESP32 board, a YF-S201 flow sensor, an LCD display, a solenoid valve, and a SIM800L GSM module. It enables water flow measurement, leakage and overconsumption alerts, and remote water control. The system also integrates Firebase, a mobile application, and a management platform to improve water resource management. Description: Instrumentations et système Thu, 01 Jan 2026 00:00:00 GMT https://dspace.univ-ouargla.dz/jspui/handle/123456789/41985 2026-01-01T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/41984 Titre: Deep Learning-Based Car Damage Detection using YOLOv8 Auteur(s): Benhammouda, Salsabil; Aoun, Douaa; Benlamoudi, Azeddine; Benaissa, lyes Résumé: This thesis presents a deep learning-based approach for automatic car damage detection, classification, and segmentation using computer vision techniques. In recent years, deep learning has emerged as a powerful solution for automating visual inspection tasks, espe- cially in the automotive sector where accurate damage assessment is essential for insur- ance, maintenance, and evaluation processes. The proposed work focuses on identifying and localizing different types of vehicle damages, including scratches, dents, broken glass, cracked parts, and damaged lights. To achieve this, state-of-the-art deep learning models such as YOLO, and DETR are implemented and analyzed. These models are widely used in object detection and image segmentation tasks due to their high performance and adaptability. The system is trained and evaluated using a custom dataset composed of Algerian car images, which reflects real-world conditions and adds a local context to the study. This dataset includes various damage annotations that allow for both de- tection and segmentation tasks. The main objective of this research is to compare the performance of different models using standard evaluation metrics such as mean Average Precision (mAP) and Intersection over Union (IoU). Furthermore, the study investigates how the use of a local dataset influences model accuracy and robustness. Ultimately, this work aims to contribute to the development of an efficient and practical system for automated vehicle damage assessment that can be applied in real-world scenarios. Description: Electronics of Embedded Systems Mon, 01 Jun 2026 00:00:00 GMT https://dspace.univ-ouargla.dz/jspui/handle/123456789/41984 2026-06-01T00:00:00Z