Management Information Systems, Information Systems, Artificial Intelligence, Software
58
Scopus Publications
Scopus Publications
An optimized SDN framework for the internet of things Zina Houhamdi, Mohamed Raid Athamena, Belkacem Athamena, Shorouq Eletter Discover Computing, 2026 Low-power wireless networks (LPWN) have traditionally been central to the Internet of Things (IoT) discussion. Nevertheless, as these networks grow more complex, their control architectures and protocols reveal significant limitations, particularly when dealing with multi–hop topologies and lossy channels. To tackle these challenges, there has been growing interest in adopting Software–Defined Networking (SDN), which has revolutionized data center and campus network management over the past decade by moving away from traditional vertical infrastructure. Despite its advantages, the centralized SDN model encounters substantial difficulties in the restricted settings of LPWN. The current study investigates the application of SDN concepts to dynamically and flexibly control Industrial IoT, with a focus on minimizing and managing SDN overhead. This paper presents a novel SDN architecture, Optimized SDN (OSDN), specifically designed for LPWN, along with simulated, experimental, and analytical findings. The results highlight that OSDN meets the diverse and complex traffic demands of Industrial IoT applications throughout LPWN and that challenges in integrating SDN in limited IoT networks can be successfully addressed. The key contribution of this study is enabling SDN-style programmability on highly resource-constrained IoT devices through a lightweight control protocol and overhead-reduction mechanisms, offering flexibility and control without compromising compatibility or performance.
Optimization of Control Plane for Load Balancing in SD-Wi-Fi Networks Belkacem Athamena, Mohamed Raid Athamena, Zina Houhamdi 2025 12th International Conference on Software Defined Systems Sds 2025, 2025 This paper proposes a novel control-plane loadbalancing approach that combines a Markov chain model (MCM) with Type-2 Fuzzy Particle Swarm Optimization (T-2FPSO). The Global Controller (GC) uses the MCM to forecast the future load states of Local Controllers (LCs); when a given LC is predicted to become overloaded, its traffic is proactively redirected to a lighter-loaded LC. Candidate target controllers are selected by T-2FPSO, which accounts for uncertainty and finds near-optimal reassignment decisions. Together, these components enable scalable, predictive load balancing across the control plane.
Control Plane Load-Balancing Optimization Zina Houhamdi, Mohamed Raid Athamena, Belkacem Athamena 2025 3rd International Conference on Intelligent Computing Communication Networking and Services Iccns 2025, 2025 This paper presents a novel two-tier load-balancing framework tailored for control plane management. The system relies on a global controller that intelligently allocates workloads among local controllers by tracking critical performance indicators, including CPU utilization, system load, and response latency. When a switch encounters an unfamiliar data flow during operation, it forwards the request to the global controller. The global controller evaluates real-time network conditions and delegates the flow to the most suitable local controller. The switch subsequently receives optimized routing instructions, ensuring reliable and efficient data delivery. The framework includes a traffic classifier combined with the Analytical Hierarchical Process (AHP) to improve performance further. This integrated method allows for real-time network flow prioritization while maintaining scalability and fair load distribution throughout the system.
Inheritance Modeling in Distributed Object-Oriented Design: An Extended G-Nets Model Zina Houhamdi, Mohamed Raid Athamena, Belkacem Athamena TEM Journal, 2025 The emergence of an object-oriented paradigm has been beneficial for complex software development, and this paradigm has been used to develop architectures for distributed systems. Many object-oriented architectures have been suggested for developing object-based software, and several attempts have been made to specify object behaviors formally. Nevertheless, investigations into bridging the gap between object implementation and object formal models are limited. This paper presents a formal approach to designing and implementing object-oriented software. Rather than applying formal methods only in the specification phase, the proposed model applies formal methods in the design phase that extends the well–known–net formalism (abstract Petri nets) to support system modeling as a set of independent and low-coupled modules. This paper describes the extension of standard G-nets to model class and inheritance in true parallel object-oriented design and incorporates the inheritance mechanism in G-nets. This paper investigates the problems related to inheritance anomaly in designing distributed object-oriented to analyze the proposed model. Consequently, the proposed formalism formally and explicitly models the inheritance in the G-net to preserve the basic Petri net model and exploit the Petri net tools for analyzing and simulating concurrent object-oriented design. An example is given to illustrate a detailed analysis of the proposed formalism; however, real experimental research is required to validate the practical significance of the presented approach.
Edge - Based Lightweight AI for Real - Time Intrusion Detection in IoT Networks Mohamed Raid Athamena, Zina Houhamdi, Belkacem Athamena 2025 12th International Conference on Internet of Things Systems Management and Security Iotsms 2025, 2025 The explosive growth of Internet of Things (IoT) deployments has introduced critical security challenges, as resource-constrained devices often lack the computer and energy to support traditional defenses. Signature-based IDS techniques cannot catch novel attacks, while heavyweight anomaly detectors (e.g., deep neural networks or SVMs) incur unacceptable latency and resource use. To address this, we propose an edge-centric intrusion detection framework that integrates lightweight AI models with edge computing. In our design, IoT devices send network data to a local edge gateway, which performs realtime anomaly detection using a pruned machine learning model (e.g., a small LSTM or decision-tree ensemble) optimized for limited hardware. This on-device approach reduces communication overhead and latency compared to cloud-based IDS (Intrusion Detection System). Key features are selected and optimized to keep the model compact (using techniques like tree-based feature importance) while retaining high detection capability. The expected impact is a low-power, real-time IDS that can promptly identify threats (e.g., IoT DDoS, spoofing, or data injection) with minimal false alarms, improving the robustness of smart homes, healthcare, and industrial IoT systems. Future work may extend this framework with adaptive learning at the edge and decentralized coordination for large-scale IoT security.
Big Data Potentials to Reduce Uncertainty in Strategic Decision-Making Process Zina Houhamdi, Belkacem Athamena 2024 25th International Arab Conference on Information Technology Acit 2024, 2024 Decision–making under uncertainty has been investigated in different domains during the past few years to examine how people make decisions. Recently, big data emerged and is recognized as a promising approach to assist companies in improving the quality of their choices. Several organizations face problems in taking advantage of big data tools. For this reason, it is important to study this topic further. Accordingly, this paper investigates how big data tools can help decision-makers reduce uncertainty in strategic decisions.This study reviews the literature on Strategic decision–making processes (SDMP) and big data and provides a complete view of how these concepts are connected and the impact of big data tools on the quality of the decision. After a comprehensive literature analysis, a model is proposed to solve this problem by analyzing the SDMP-making process to clarify the uncertainty in the decision–making process steps and assess how big data tools can be used by administrators in the decision-making process.The analysis's result discloses the potential for improving the strategic decision–making process under uncertainty. It also reveals that the uncertainty inherent to technology usage influences decision-makers' choices. Accordingly, a framework is proposed to assess the incorporation of big data analytics tools in companies to fully benefit from these tools' power.
AI in Diagnostic Imaging: An Overview Zina Houhamdi, Mohamed Raid Athamena, Belkacem Athamena 2024 Global Digital Health Knowledge Exchange and Empowerment Conference Knowledge Exchange of the State of the Art Research and Development in Digital Health Technologies Enable and Empower Stakeholders Engaged in Enriching and Enhancing the Patient Healthcare Journey Gdigihealth Kee 2024, 2024
Two-Sided Matching under Incomplete Information Zina Houhamdi, Belkacem Athamena, Ghaleb ElRefae Proceedings 2022 23rd International Arab Conference on Information Technology Acit 2022, 2022
Open-SBS: Smart Building Simulator Houssem Eddine Degha, Fatima Zohra Laallam, Okba Kazar, Issam Khelfaoui, Belkacem Athamena, Zina Houhamdi Proceedings 2022 23rd International Arab Conference on Information Technology Acit 2022, 2022
Fuzzy Logic and Deep learning Techniques for Covid-19 Detection Belkis Hassani, Khelili Mohamed Akram, Kazar Okba, Slatnia Sihem, Saad Harous, Belkacem Athamena, Zina Houhamdi Proceedings 2022 23rd International Arab Conference on Information Technology Acit 2022, 2022
A Smart Approach using Multi-agent System for Big Data Security Dounya Kassimi, Okba Kazar, Ezedin Barka, Abdelhak Merizig, Zina Houhamdi, Belkacem Athamena, Meftah Zaoui 2022 9th International Conference on Internet of Things Systems Management and Security Iotsms 2022, 2022
Blockchain Technology for Secure Shared Medical Data Mhamed Mancer, Khelili Mohamed Akram, Ezedin Barka, Kazar Okba, Slatnia Sihem, Saad Harous, Belkacem Athamena, Zina Houhamdi Proceedings 2022 23rd International Arab Conference on Information Technology Acit 2022, 2022
Retention contracts under hidden information Belkacem Athamena, Zina Houhamdi, Ghaleb El Refae 2021 22nd International Arab Conference on Information Technology Acit 2021, 2021
An execution model for exception handling in a multi-agent system 16th International Conference on Modeling and Applied Simulation Mas 2017 Held at the International Multidisciplinary Modeling and Simulation Multiconference I3m 2017, 2017
