Leading the next generation of intelligent technologies with efficient Edge-AI. Exploring the intersection of Artificial Intelligence, Internet of Things, and Edge Computing.
I am currently a Doctoral Researcher (Ph.D. Candidate) in Computer & Engineering Sciences at the Doctoral School 432 with the National Higher School of "Arts et Métiers" (ENSAM), and attached to CESI LINEACT Laboratory (Strasbourg, France), specializing in AI, IoT, and Edge Intelligence since December 2023.
My research focuses on developing efficient AI for resource-constrained edge devices and creating intelligent systems that can operate with minimal cloud dependency.
I am currently designing efficient AI paradigms by investigating the Computation & Communication Efficiency of Federated Edge Learning to establish reliable, resilient, scalable, and efficient edge intelligence.
Advancing the frontiers of AI, IoT, and Edge Computing through innovative research and practical applications
Designing novel, scalable, and efficient AI paradigms optimized for resource-constrained deployment with a focus on generalizability.
Creating interconnected systems that leverage distributed and collaborative intelligence for real-time decision making and automation.
Designing reliable, resilient, and highly personalized edge AI, with advanced learning paradigms leveraging spatiotemporal intelligence.
Exploring heterogeneous edge learning, secure machine learning algorithms, and collaborative AI across distributed edges with minimal cloud dependency.
Exploring Bio-Plausible learning paradigms, while leveraging efficiency and consistency for world models across varying environmental complexities.
A.-R. Baahmed, J.-F. Dollinger, M.E.A. Brahmia, M. Zghal
Internet of Things, 36:101868, 2026
As a core component of my Ph.D. thesis research, I authored this study introducing the novel HiFEL-OCKT methodology. Our approach addresses the realistic high heterogeneity of IoT ecosystems, and provides an efficient, scalable, and personalized temporal edge intelligence setting for IoT ecosystems. HiFEL-OCKT demonstrated its superior performance and efficiency compared to the state-of-the-art approaches, through extensive experiments on multiple IoT domains, including the Smart Buildings case study and the Industrial IoT case study (Aircraft Turbofan Engine).
A.-R.-E.M. Baahmed, J.-F. Dollinger, M.-E.-A. Brahmia, M. Zghal
The 20th International Wireless Communications & Mobile Computing Conference (IWCMC), 2024
As part of my Ph.D. thesis work, I authored this research proposing a comprehensive study to identify computational efficiency facets in federated edge learning, following a taxonomic methodology to investigate hyperparameter impact on the learning efficiency.
A.-R.-E.M. Baahmed, G. Andresini, C. Robardet, A. Appice
The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2023
As a core component of my Engineering and Master thesis, I authored this study introducing the novel E-GNNExplainer approach. Our approach consists of a single-instance explanation methodology for edge-classification graph neural networks-based network intrusion detection systems (NIDS).
Teaching experience given at CESI Strasbourg, France.
Fall 2025
Taught exploratory data analysis, data preparation, learning paradigms, ML algorithms, neural networks, model validation and evaluation, performance measures, results interpretation, and model fine-tuning.
Fall 2024 & Fall 2025
Taught the principles of object-oriented design and programming for modular, reusable, and maintainable software systems.
Fall 2024 & Fall 2025
Developed course materials on the arithmetic fundamentals in cryptography, while teaching their role in modern encryption techniques to ensure secure communication in the digital world as a fundamental science.
Fall 2024
Taught the core concepts of computer networks and system administration through hands-on projects in network communication.
Fall 2024
Developed course materials on the fundamental programming paradigms, while teaching each paradigm and its influence as a fundamental science.
Fall 2024
Covering key concepts such as filtering, Fourier transforms, and signal analysis, providing students with practical tools and a solid understanding of how to process and analyze signals using Python libraries.
A three-months internship project focused on developing a real-world Federated Edge Learning Platform for Smart Buildings, using Raspberry Pis as part of an IoT and edge computing infrastructure.
A one-week challenge project focusing on developing a computer vision-based deep learning model to deploy on an industrial welding robot arm.
End of study defenses and third-year students internship projects.
Doctoral School 432
Doctoral School 432
Doctoral School 432
Doctoral School 432
