Seifeddine Bouallegue
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Seifeddine Bouallegue has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Ridha Bouallegue
InnoV’COM Laboratory-Sup’Com, University of Carthage, Ariana, 2083, Tunisia
4 shared publications - Aymen Omri
Department of Software Systems, University of Doha for Science and Technology, Doha 24449, Qatar
3 shared publications - Rund Fareed Mahafdah
University of Carthage
3 shared publications Ridha Bouallegue
Innovation of Communicant and Cooperative Mobiles (InnovCom) Laboratory (SUPCOM), Higher School of Communications of Tunis, University of Carthage, Ariana, Tunisia
2 shared publications- Dorsaf Ghozlani
Innovation of Communicant and Cooperative Mobiles (InnovCom) Laboratory (SUPCOM), Higher School of Communications of Tunis, University of Carthage, Ariana, Tunisia
1 shared publication Hela Chamkhia
Computer Science and Engineering Department, Qatar University, Doha, Qatar
1 shared publication
Latest Publications
- 1 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Mobility and Security Management in Femtocell Networks
Gestion de la Mobilité et de la Securité dans les Résaux Femtocellulaires: Les réseaux de télécommunications sont soumis à des processus d'amélioration et d'optimisation continue. Chaque nouvelle itération apporte son lot de défis et limites. En effet, la croissance exponentielle des appareils de télécommunication, des stations de base aux équipements utilisateurs conduisent à de sérieux problèmes d'economie d'énergie. En plus des menaces à la vie privée, en particulier pour les réseaux sans fil car les canaux utilisés par les opérateurs peuvent également être utilisés par une oreille indiscrète quelconque. L'optimisation de l'utilisation du spectre est également un défi en raison du fait que le spectre disponible dans les systèmes de communication sans fil est devenu une ressource très rare en raison de la demande croissante. Les réseaux émergents, tels que les femtocells, souffrent également des défis mentionnés précédemment. Le travail de thèse actuel se concentre sur la proposition de solutions aux défis cités précédemment: l'efficacité énergétique, le partage du spectre et la sécurité. Le travail de recherche présenté dans cette thèse a porté sur trois axes principaux: Premièrement, trouver un moyen de réduire au minimum la consommation d'énergie des femtocellules dans les reseaux BWA femto/macro-cellulaire en diminuant le nombre d'événements de mobilité non désirées et l'introduction de nouveaux états de puissance pour la femtocellule. En second lieu, proposer une solution qui vise à réduire le temps de transmission prévu dans le temps de séjour de l'utilisateur secondaire (SU) dans la couverture d'une femtocellule en utilisant un algorithme basé sur le temps minimum prévu de transmission dans le temps de séjour de l'équipement utilisateur (UE). Enfin, introduire un nouveau modèle qui basé sur la sélection du meilleur relais qui maximise le taux de confidentialité et les avantages de l'augmentation du nombre de relais sous la contrainte de qualité de service à la destination.
- 1 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Mobility and Security Management in Femtocell Networks
Gestion de la Mobilité et de la Securité dans les Résaux Femtocellulaires: Les réseaux de télécommunications sont soumis à des processus d'amélioration et d'optimisation continue. Chaque nouvelle itération apporte son lot de défis et limites. En effet, la croissance exponentielle des appareils de télécommunication, des stations de base aux équipements utilisateurs conduisent à de sérieux problèmes d'economie d'énergie. En plus des menaces à la vie privée, en particulier pour les réseaux sans fil car les canaux utilisés par les opérateurs peuvent également être utilisés par une oreille indiscrète quelconque. L'optimisation de l'utilisation du spectre est également un défi en raison du fait que le spectre disponible dans les systèmes de communication sans fil est devenu une ressource très rare en raison de la demande croissante. Les réseaux émergents, tels que les femtocells, souffrent également des défis mentionnés précédemment. Le travail de thèse actuel se concentre sur la proposition de solutions aux défis cités précédemment: l'efficacité énergétique, le partage du spectre et la sécurité. Le travail de recherche présenté dans cette thèse a porté sur trois axes principaux: Premièrement, trouver un moyen de réduire au minimum la consommation d'énergie des femtocellules dans les reseaux BWA femto/macro-cellulaire en diminuant le nombre d'événements de mobilité non désirées et l'introduction de nouveaux états de puissance pour la femtocellule. En second lieu, proposer une solution qui vise à réduire le temps de transmission prévu dans le temps de séjour de l'utilisateur secondaire (SU) dans la couverture d'une femtocellule en utilisant un algorithme basé sur le temps minimum prévu de transmission dans le temps de séjour de l'équipement utilisateur (UE). Enfin, introduire un nouveau modèle qui basé sur la sélection du meilleur relais qui maximise le taux de confidentialité et les avantages de l'augmentation du nombre de relais sous la contrainte de qualité de service à la destination.
- Top Cited PapersOpen Access
- 8 January 2026
- Published by MDPI AG in Information
- Vol. 17 (1) , 60
Machine Learning Approaches for Early Student Performance Prediction in Programming Education
Intelligent recommender systems are essential for identifying at-risk students and personalizing learning through tailored resources. Accurate prediction of student performance enables these systems to deliver timely interventions and data-driven support. This paper presents the application of machine learning models to predict final exam grades in a university-level programming course, leveraging multi-modal student data to improve prediction accuracy. In particular, a recent raw dataset of students enrolled in a programming course across 36 class sections from the Fall 2024 and Winter 2025 terms was initially processed. The data was collected up to one month before the final exam. From this data, a comprehensive set of features was engineered, including the student’s background, assessment grades and completion times, digital learning interactions, and engagement metrics. Building on this feature set, six machine learning prediction models were initially developed using data from the Fall 2024 term. Both training and testing were conducted on this dataset using cross-validation combined with hyperparameter tuning. The XGBoost model demonstrated strong performance, achieving an accuracy exceeding 91%. To assess the generalizability of the considered models, all models were retrained on the complete Fall 2024 dataset. They were then evaluated on an independent dataset from Winter 2025, with XGBoost achieving the highest accuracy, exceeding 84%. Feature importance analysis has revealed that the midterm grade and the average completion duration of lab assessments are the most influential predictors. This data-driven approach empowers instructors to proactively identify and support at-risk students, enabling adaptive learning environments that deliver personalized learning and timely interventions.
- 8 January 2026
- Published by MDPI AG in Information
- Vol. 17 (1) , 60
Top Cited PapersOpen AccessMachine Learning Approaches for Early Student Performance Prediction in Programming Education
Intelligent recommender systems are essential for identifying at-risk students and personalizing learning through tailored resources. Accurate prediction of student performance enables these systems to deliver timely interventions and data-driven support. This paper presents the application of machine learning models to predict final exam grades in a university-level programming course, leveraging multi-modal student data to improve prediction accuracy. In particular, a recent raw dataset of students enrolled in a programming course across 36 class sections from the Fall 2024 and Winter 2025 terms was initially processed. The data was collected up to one month before the final exam. From this data, a comprehensive set of features was engineered, including the student’s background, assessment grades and completion times, digital learning interactions, and engagement metrics. Building on this feature set, six machine learning prediction models were initially developed using data from the Fall 2024 term. Both training and testing were conducted on this dataset using cross-validation combined with hyperparameter tuning. The XGBoost model demonstrated strong performance, achieving an accuracy exceeding 91%. To assess the generalizability of the considered models, all models were retrained on the complete Fall 2024 dataset. They were then evaluated on an independent dataset from Winter 2025, with XGBoost achieving the highest accuracy, exceeding 84%. Feature importance analysis has revealed that the midterm grade and the average completion duration of lab assessments are the most influential predictors. This data-driven approach empowers instructors to proactively identify and support at-risk students, enabling adaptive learning environments that deliver personalized learning and timely interventions.
- 20 November 2025
- Published by Springer Nature
- p. 597-613
Advancing Breast Cancer Prognosis: Machine Learning Models for Recurrence Prediction
- 20 November 2025
- Published by Springer Nature
- p. 597-613
Advancing Breast Cancer Prognosis: Machine Learning Models for Recurrence Prediction
- Open Access
- 12 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 90651-90667
Modified MCP-Based Modeling and Performance Analysis of 3-D Cellular Networks
In this paper, we introduce a new stochastic geometry model, the ‘Modified Matérn Cluster Process (MMCP)’, to provide an accurate representation of cell locations in a network. This model not only incorporates realistic constraints but also takes into account the clustered distribution of user equipment (UE). Specifically, UEs are assumed to cluster around small-cell base stations (SCBs), which adhere to a minimum separation distance and are organized according to a Matérn Hard-Core Process (MHCP) II, ensuring efficient spatial distribution and reduced interference. To further enhance network performance, we propose a novel transmission scheme specifically designed to mitigate interference. This innovative approach results in the development of a tractable analytical framework, which includes a detailed assessment of the non-interference probability, thereby optimizing resource allocation strategies across the network. Within this framework, we derive expressions for the successful transmission probabilities for both uplink and downlink communications. Additionally, we explore the average ergodic capacity, a crucial metric for evaluating the overall efficacy of the three-dimensional (3-D) MMCP. These derivations enable a deeper understanding of the model’s impact on network performance. To validate our theoretical findings, we conduct extensive Monte Carlo simulations, which demonstrate the accuracy of our proposed model. Our results highlight the critical importance of accounting for user distribution when evaluating dynamic system performance.
- 12 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 90651-90667
Open AccessModified MCP-Based Modeling and Performance Analysis of 3-D Cellular Networks
In this paper, we introduce a new stochastic geometry model, the ‘Modified Matérn Cluster Process (MMCP)’, to provide an accurate representation of cell locations in a network. This model not only incorporates realistic constraints but also takes into account the clustered distribution of user equipment (UE). Specifically, UEs are assumed to cluster around small-cell base stations (SCBs), which adhere to a minimum separation distance and are organized according to a Matérn Hard-Core Process (MHCP) II, ensuring efficient spatial distribution and reduced interference. To further enhance network performance, we propose a novel transmission scheme specifically designed to mitigate interference. This innovative approach results in the development of a tractable analytical framework, which includes a detailed assessment of the non-interference probability, thereby optimizing resource allocation strategies across the network. Within this framework, we derive expressions for the successful transmission probabilities for both uplink and downlink communications. Additionally, we explore the average ergodic capacity, a crucial metric for evaluating the overall efficacy of the three-dimensional (3-D) MMCP. These derivations enable a deeper understanding of the model’s impact on network performance. To validate our theoretical findings, we conduct extensive Monte Carlo simulations, which demonstrate the accuracy of our proposed model. Our results highlight the critical importance of accounting for user distribution when evaluating dynamic system performance.
- 16 April 2025
- Published by Springer Nature
- p. 108-118
An Optimized Bounding Box Technique for Enhanced Underwater Fish Detection
- 16 April 2025
- Published by Springer Nature
- p. 108-118
An Optimized Bounding Box Technique for Enhanced Underwater Fish Detection
- Open Access
- 23 December 2024
- Published by PeerJ in PeerJ Computer Science
- Vol. 10, e2576
Enhancing e-learning through AI: advanced techniques for optimizing student performance
The integration of Artificial Intelligence (AI) into e-learning has transformed conventional educational approaches, improving the learning process and maximizing student achievement. This study offers a thorough examination of how AI can be utilized to enhance e-learning results by employing advanced predictive methods and performance optimization strategies. The main goals consist of creating an AI-based framework to monitor and analyze student interactions, evaluating the influence of online learning platforms on student understanding using advanced algorithms, and determining the most efficient methods for blended learning systems. AI algorithms, known for their cognitive ability and capacity to learn, adapt, and make decisions, are employed to analyze and forecast student performance, thereby improving educational quality and outcomes. The practical results obtained by implementing machine learning and deep learning models, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), show substantial enhancements in forecasting different performance metrics. This research highlights the ability of AI to develop adaptable, effective, and successful e-learning environments, promoting enhanced academic achievement and customized learning experiences. The findings demonstrate that CNN outperformed other deep learning and machine learning algorithms in terms of accuracy during the prediction phase, showcasing the advanced capabilities of AI in educational contexts. Portions of this text were previously published as part of a preprint (https://doi.org/10.21203/rs.3.rs-4724603/v1).
- 23 December 2024
- Published by PeerJ in PeerJ Computer Science
- Vol. 10, e2576
Open AccessEnhancing e-learning through AI: advanced techniques for optimizing student performance
The integration of Artificial Intelligence (AI) into e-learning has transformed conventional educational approaches, improving the learning process and maximizing student achievement. This study offers a thorough examination of how AI can be utilized to enhance e-learning results by employing advanced predictive methods and performance optimization strategies. The main goals consist of creating an AI-based framework to monitor and analyze student interactions, evaluating the influence of online learning platforms on student understanding using advanced algorithms, and determining the most efficient methods for blended learning systems. AI algorithms, known for their cognitive ability and capacity to learn, adapt, and make decisions, are employed to analyze and forecast student performance, thereby improving educational quality and outcomes. The practical results obtained by implementing machine learning and deep learning models, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), show substantial enhancements in forecasting different performance metrics. This research highlights the ability of AI to develop adaptable, effective, and successful e-learning environments, promoting enhanced academic achievement and customized learning experiences. The findings demonstrate that CNN outperformed other deep learning and machine learning algorithms in terms of accuracy during the prediction phase, showcasing the advanced capabilities of AI in educational contexts. Portions of this text were previously published as part of a preprint (https://doi.org/10.21203/rs.3.rs-4724603/v1).
- 9 April 2024
- Published by Springer Nature
- p. 379-391
Examining University Students and Teachers’ Behavioral Intention to Upgrade Blended Learning Using an Extended TAM Model
- 9 April 2024
- Published by Springer Nature
- p. 379-391
Examining University Students and Teachers’ Behavioral Intention to Upgrade Blended Learning Using an Extended TAM Model
- 9 April 2024
- Published by Springer Nature
- p. 392-403
Applying Artificial Intelligence in the E-Learning Field: Review Article
- 9 April 2024
- Published by Springer Nature
- p. 392-403
Applying Artificial Intelligence in the E-Learning Field: Review Article
- Open Access
- 3 April 2024
- Published by MDPI AG in Electronics
- Vol. 13 (7) , 1344
Modeling and Performance Analysis of mmWave and WiFi-Based Vehicle Communications
Vehicle -to-vehicle (V2V) communications are crucial for enhancing road network safety and efficiency. With the increasing demand for bandwidth in V2V services, exploring innovative solutions has become imperative. This study explores a comparative analysis of mmWave and WiFi transmission technologies, with a specific focus on line-of-sight (LoS) and non-line-of-sight (NLoS) scenarios in both 2D and 3D modeling environments. The use of stochastic geometry tools allows a realistic modeling of the random positioning of vehicles within the V2V system framework, resulting in accurate expressions for the successful transmission probability (STP) and average throughput (AT) for both communication systems. To validate our analytical findings, Monte Carlo simulations have been employed, offering a comprehensive evaluation of mmWave and WiFi performance. Simulation results highlight that mmWave systems outperform in scenarios with short transmission distances and low vehicle density while WiFi systems demonstrate greater efficiency for longer transmission distances.
- 3 April 2024
- Published by MDPI AG in Electronics
- Vol. 13 (7) , 1344
Open AccessModeling and Performance Analysis of mmWave and WiFi-Based Vehicle Communications
Vehicle -to-vehicle (V2V) communications are crucial for enhancing road network safety and efficiency. With the increasing demand for bandwidth in V2V services, exploring innovative solutions has become imperative. This study explores a comparative analysis of mmWave and WiFi transmission technologies, with a specific focus on line-of-sight (LoS) and non-line-of-sight (NLoS) scenarios in both 2D and 3D modeling environments. The use of stochastic geometry tools allows a realistic modeling of the random positioning of vehicles within the V2V system framework, resulting in accurate expressions for the successful transmission probability (STP) and average throughput (AT) for both communication systems. To validate our analytical findings, Monte Carlo simulations have been employed, offering a comprehensive evaluation of mmWave and WiFi performance. Simulation results highlight that mmWave systems outperform in scenarios with short transmission distances and low vehicle density while WiFi systems demonstrate greater efficiency for longer transmission distances.