https://dspace.univ-ouargla.dz/jspui/handle/123456789/243 2026-04-15T21:32:25Z 2026-04-15T21:32:25Z Khaldi, Belal Zouaghi, Mohamed Mehdi Benecheikh, Adnane Abdelmoumine https://dspace.univ-ouargla.dz/jspui/handle/123456789/40295 2026-02-09T10:07:25Z 2025-01-01T00:00:00Z

Titre: ANOMALY DETECTION IN FLOW BASED IoT NETWORK TRAFIC USING CNN,SMOTE AND PCA Auteur(s): Khaldi, Belal; Zouaghi, Mohamed Mehdi; Benecheikh, Adnane Abdelmoumine Résumé: This research presents an optimized deep learning approach for network flow anomaly detection, combining data preprocessing, feature classification, and neural networks to improve detection accuracy. The methodology employs systematic data cleaning (handling missing values, normalization) and feature selection before applying machine learning classifiers (Random Forest/SVM) for preliminary anomaly identification. These processed features are then fed into deep learning models (CNN/LSTM) to capture complex temporal patterns in flow data. Experiments conducted on network traffic datasets demonstrate that this hybrid approach achieves superior performance compared to conventional methods, with quantitative improvements in both accuracy (99%) and F1-score (99,5%). The study specifically examines how different preprocessing techniques affect model performance and compares various classification-DL architecture combinations. Results indicate that proper data normalization and feature engineering significantly enhances the deep learning model's anomaly detection capability. This work contributes practical insights for implementing machine learning pipelines in network security systems, showing that a carefully designed preprocessing and classification stage can substantially improve deep learning outcomes. The findings are particularly relevant for developing more reliable intrusion detection systems capable of identifying both known attack patterns and novel anomalies. Description: Network Administration & Security

2025-01-01T00:00:00Z Benkherourou, Chafika Tidjani, Fatma Zahra https://dspace.univ-ouargla.dz/jspui/handle/123456789/40293 2026-02-09T10:00:44Z 2025-01-01T00:00:00Z

Titre: Développement d’une Approche Prédictive pour la Gestion d’une banque de Sang Auteur(s): Benkherourou, Chafika; Tidjani, Fatma Zahra Résumé: régression poly- nomiale Description: Informatique fondamentale

2025-01-01T00:00:00Z BENBEZIANE, Mohammed Temmar, Brahim Bouchenafa, Abdeldjalil https://dspace.univ-ouargla.dz/jspui/handle/123456789/40292 2026-02-09T09:54:03Z 2025-01-01T00:00:00Z

Titre: Federated Learning-based Anomaly Detection for IoT Security Attacks Auteur(s): BENBEZIANE, Mohammed; Temmar, Brahim; Bouchenafa, Abdeldjalil Résumé: The rapid advancement of network technologies has heightened the risk of device and data breaches, particularly during data sharing and storage processes. To mitigate these threats, Machine Learning (ML) and Deep Learning (DL)-based Intrusion Detection Sys- tems (IDS) have shown great potential. However, traditional training approaches that require centralized data aggregation often pose significant privacy and confidentiality concerns. Federated Learning (FL) addresses this issue by enabling local model training on edge devices, eliminating the need to share raw data, and instead securely aggregating model updates in a decentralized fashion. In this study, we introduce a unified IDS leveraging a hybrid CNN-LSTM model within an FL framework, using the realistic TON-IoT dataset to reflect actual IoT environments. Experimental results demonstrate the effectiveness of the proposed model, achieving a classification accuracy of 90.84% for multiclass detection and 92.02% for binary classifica- tion in a centralized setting, while maintaining competitive performance in the federated environment with 87.6% accuracy for multiclass and 88.5% for binary classification. These findings highlight the potential of combining CNN and LSTM architectures within an FL setup to build intelligent, privacy-preserving, and secure IDS solutions for IoT ecosystems. Description: Network Administration and Security

2025-01-01T00:00:00Z KHELIFA, MERIEM Slimani, Nadjat Salhi, Oumaima https://dspace.univ-ouargla.dz/jspui/handle/123456789/40290 2026-02-09T09:44:03Z 2025-01-01T00:00:00Z

Titre: Optimizing the Multidimensional Knapsack Problem Using Guided Genetic Algorithm and an AI-augmented Binary Water Optimization Algorithm Auteur(s): KHELIFA, MERIEM; Slimani, Nadjat; Salhi, Oumaima Résumé: This thesis optimizes the Multidimensional Knapsack Problem (MKP), one of the most prominent and challenging combinatorial optimization problems since it is intricate and contains multiple constraints. MKP is present in real-world issues such as resource allocation, task scheduling, and investment. The overall aim of this study is to evaluate the performance of two metaheuristics for MKP problem solving: the Guided Genetic Algorithm (GGA) and binary Water Optimization Algorithm (WOA). For enhancing the performance of WOA, we used a hybrid approach based on artificial intelligence techniques. A dynamic parameter prediction such as the number of flipped bits and the evaporation retention ratio is performed based on a Multi-Layer Perceptron (MLP) neural network. Graph Neural Networks (GNNs) are also adopted in order to utilize the structural relationships among items. In addition, reinforcement learning techniques are employed for enhancing the exploration and exploitation phases during the searching procedure. Experimental results indicate that the improved version of WOA (BWOA), augmented by AI techniques, can produce high-quality solutions in shorter convergence time compared to other traditional algorithms. This confirms the effectiveness of the proposed method in solving complex constrained optimization problems like MKP. Description: Industrial Computing

2025-01-01T00:00:00Z