DSpace Community:http://dspace.ensta.edu.dz/jspui/handle/123456789/1542026-10-16T11:32:59Z2026-10-16T11:32:59ZAnalysis of Convolutional Neural Networks on Real-Time Multi-Core Embedded PlatformsLOUNNACI, SarahBENDOUDA, Djamila (Directeur de thèse)HLADIK, Pierre-Emmanuel (Directeur de thèse)http://dspace.ensta.edu.dz/jspui/handle/123456789/4492026-10-14T10:07:13Z2025-01-01T00:00:00ZTitle: Analysis of Convolutional Neural Networks on Real-Time Multi-Core Embedded Platforms
Authors: LOUNNACI, Sarah; BENDOUDA, Djamila (Directeur de thèse); HLADIK, Pierre-Emmanuel (Directeur de thèse)
Abstract: This article provides a bibliographical study of Convolutional Neural Networks (CNNs) architecture analysis and
methods of deploying them in embedded real-time multi-core platforms. We first review the main structures of CNNs and their representation as Directed Acyclic Graphs (DAGs). We then analyse the real-time execution challenges on multi-core architectures, focusing on shared-resource interference, common
arbitration mechanisms, and discuss how Worst-Case Execution Time (WCET) and Worst-Case Response Time (WCRT) can be estimated using tools like OTAWA and MIA. Next, we survey
existing analytical methods for timing analysis of CNN inference, including model representation formats and toolchains. Finally, we outline our ongoing research effort developing the MIND
(Model Inference Network Designer) tool to automatically extract
CNN structure into a DAG compatible with the MIA timing- analysis tool, and we end this article by giving some perspectives.
Description: Master : Programme Complémentaire d'Ingéniorat: Systèmes Embarqués : Alger: Ecole Nationale Supérieure des Technologie Avancées: 20252025-01-01T00:00:00ZFault Detection and Diagnosis of PV Systems Based on Corrected Performance Ratio Analysis and Adaptive Thresholds Using CNN-LSTM Hybrid Neural Network Prediction ModelADDALA, AbderrahimKHALED, ChahineDERMOUCHE, Reda (Directeur de thèse)CHOUDER, Aissa (Directeur de thèse)DROUICHE, Imane (Directeur de thèse)http://dspace.ensta.edu.dz/jspui/handle/123456789/4482026-10-14T09:57:36Z2025-01-01T00:00:00ZTitle: Fault Detection and Diagnosis of PV Systems Based on Corrected Performance Ratio Analysis and Adaptive Thresholds Using CNN-LSTM Hybrid Neural Network Prediction Model
Authors: ADDALA, Abderrahim; KHALED, Chahine; DERMOUCHE, Reda (Directeur de thèse); CHOUDER, Aissa (Directeur de thèse); DROUICHE, Imane (Directeur de thèse)
Abstract: In the model-based approach, a trusted and reliable photovoltaic (PV) array model provides an essential baseline for monitoring the system’s health and diagnosing any underperformance. To this end, this article proposes a threephase methodology for developing a robust PV plant model and implementing a fault detection and diagnosis mechanism, suitable for large-scale grid-connected PV systems. The first stage involves constructing a single-layer hybrid CNNLSTM model aimed at predicting photovoltaic power generation. This model uses real-world measured data obtained from a large-scale, gridconnected photovoltaic system operating in Algeria. In this architecture, the convolution layer acts as a feature extractor, identifying local patterns in the measured data. Meanwhile, the LSTM component captures temporal dependencies. In
the second phase, an automated inspection platform is developed, leveraging the evaluation of the
Corrected Performance Ratio (CPR) for each inverter within the operational photovoltaic (PV) system... Next, a lower threshold and an upper threshold set by Hampel identifier are defined and
processed, allowing the system to detect faults by generating a faulty signal. The diagnostic process is implemented by setting dynamic voltage and current thresholds derived from the prediction
model. These thresholds are then adjusted adaptively to improve the sensitivity of fault detection
for both voltage and current abnormalities. In the final phase, the proposed supervision system is implemented as a standalone graphical user interface (GUI) application based on the developed methodology. This validates its applicability for photovoltaic (PV) supervisory control and data acquisition (SCADA) systems. Evaluated case studies demonstrate the effectiveness of this approach in detecting typical PV systems faults, such as short circuits, string disconnections, and partial shading effects
Description: Master : Programme Complémentaire d'Ingéniorat: Systèmes Embarqués : Alger: Ecole Nationale Supérieure des Technologie Avancées: 20252025-01-01T00:00:00ZState of the Art on Facial Recognition and Liveness Detection TechnologiesYAKOUBI, KahinaLABIOD, WissamBOUZEGZEG, Amine (Directeur de thèse)CHOUAF, Seloua (Directeur de thèse)http://dspace.ensta.edu.dz/jspui/handle/123456789/4472026-10-12T14:20:07Z2025-01-01T00:00:00ZTitle: State of the Art on Facial Recognition and Liveness Detection Technologies
Authors: YAKOUBI, Kahina; LABIOD, Wissam; BOUZEGZEG, Amine (Directeur de thèse); CHOUAF, Seloua (Directeur de thèse)
Abstract: Facial recognition has become a crucial technology
in biometric authentication systems, but it remains vulnerable to
spoofing attempts, such as using fake photos or videos. As a result,
liveness detection plays an important role differentiating genuine
users from fraudulent ones. This work provides a state-of-the-art
review of the main technologies in facial recognition and liveness
detection. It first discuss recent deep learning-based advances in
facial recognition, particularly those involving angular margin
losses and embedding networks. Then, we analyze liveness
detection approaches, distinguishing between passive methods
(based on image analysis) and active methods (based on user
interaction). This study examines their performance, benefits,
limitations, and the latest trends and challenges in biometric
security.
Description: Master : Programme Complémentaire d'Ingéniorat: Systèmes de Télécommunications Et Réseaux : Alger: Ecole Nationale Supérieure des Technologie Avancées: 20252025-01-01T00:00:00ZRevue des Outils de Simulation et des Metriques de Performance pour les ́ Architectures de Villes IntelligentesBOUDJAMMALA, AbdessalamSARI, Mohammed IslamMOUZAOUI, Abdeldjallil (Directeur de thèse)CHOUAF, Seloua (Directeur de thèse)http://dspace.ensta.edu.dz/jspui/handle/123456789/4462026-10-12T14:26:46Z2025-01-01T00:00:00ZTitle: Revue des Outils de Simulation et des Metriques de Performance pour les ́ Architectures de Villes Intelligentes
Authors: BOUDJAMMALA, Abdessalam; SARI, Mohammed Islam; MOUZAOUI, Abdeldjallil (Directeur de thèse); CHOUAF, Seloua (Directeur de thèse)
Abstract: La croissance rapide des zones urbaines et la
complexite des infrastructures ont conduit ́ a l’ ` emergence du ́
concept de ville intelligente. Afin de concevoir et de valider ces
architectures avancees, l’introduction des outils de simulation ́
ainsi que l’utilisation des metriques de performance sont dev- ́
enues essentielles. Cette recherche propose une revue des outils
de simulation les plus couramment utilises dans ce domaine, ́
ainsi qu’une analyse des metriques permettant d’ ́ evaluer la ́
performance des solutions mises en œuvre.
Description: Master : Programme Complémentaire d'Ingéniorat: Systèmes de Télécommunications Et Réseaux : Alger: Ecole Nationale Supérieure des Technologie Avancées: 20252025-01-01T00:00:00Z