Publications
-
A Review on Financial Fraud Detection: Techniques, Challenges, Solutions, and Perspectives
Financial fraud is one of the most serious criminal activities, resulting in losses exceeding hundreds of billions of dollars each year. Most existing fraud detection frameworks still use static rule sets or traditional Machine Learning (ML) models, which fail with decentralized systems characterized by anonymity and dynamic behavior. Despite recent developments, the deployment of advanced […]
-
A Review on Hierarchical Federated Learning: Architectures and Learning Algorithms
The rapid advancement of Hierarchical Federated Learning (HFL) has motivated researchers to explore novel algorithms and design strategies to address core challenges such as statistical heterogeneity, communication efficiency, and scalability. This study presents a comprehensive review of recent contributions over the past five years, focusing on HFL algorithms, including their architectural design and classification according […]
-
Securing Digital Twin System Using Blockchain: Application on Smart Home
Digital twins (DTs) offer a virtual representation of physical entities, enabling advanced monitoring, control, and predictive analysis, particularly in Internet of Things (IoT) environments. However, the integration of DTs in smart homes raises significant security and privacy concerns due to the volume of sensitive data generated and exchanged. This paper proposes a secure architecture for […]
-
A Comparative Analysis of Service Management Techniques in the Internet of Things
The Internet of Things (IoT) interconnects vast networks of heterogeneous devices across dynamic domains such as healthcare, industry, and smart cities, presenting critical challenges in real-time orchestration, resource efficiency, security, and scalability. To address these demands, diverse service management paradigms have emerged as essential frameworks. This review systematically analyzes existing IoT service management approaches, categorizing […]
-
A Review of Digital Twins in Smart Environments
Transcending static digital representations, a Digital Twin (DT) functions as a dynamic, computational counterpart of a physical asset, capturing its real-time state and behavior through continuous data exchange. This mirroring capability positions DTs as a key enabler of intelligent operations in complex smart environments, from optimizing energy usage in buildings to managing urban infrastructure and […]
-
A Review on Multi-Agent Deep Reinforcement Learning for IoT: Techniques and Applications
The Internet of Things (IoT) connects billions of devices across domains such as transportation, healthcare, agriculture, and energy-creating highly dynamic, distributed, and heterogeneous environments. These characteristics pose significant challenges for control, coordination, scalability, and adaptability. In response, Multi-Agent Deep Reinforcement Learning (MADRL) has emerged as a promising paradigm by combining the decision-making intelligence of reinforcement […]
-
Multi-Agent System for Solving the Vehicle Routing Problem: A Hybrid Metaheuristic Approach
This paper introduces a novel Multi-Agent System (MAS) designed to solve the Vehicle Routing Problem (VRP), a well-known optimization challenge in logistics. The proposed MAS integrates seven established metaheuristics—Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Golden Ball Algorithm (GBA), Hill Climbing (HC), Tabu Search (TS), and Simulated Annealing (SA)—using a Bi-directional […]
-
Des Jumeaux Numériques d’Enseignement : entre instrument et finalité de l’acte éducatif
Dans la continuité des Jumeaux Numériques (JN) industriels, la formation est devenue un champ d’application visé par le développement de Jumeaux Numériques d’Enseignement (JNE). À partir d’une étude sur l’introduction d’un JNE dans une formation d’ingénieurs, cet article se propose de comprendre dans quelle mesure le JNE peut être instrumenté comme objet pédagogique dans une […]
-
Systematic review and future directions in dynamic flexible job shop scheduling: a decade of research
This paper presents a comprehensive overview of the current state-of-the-art on Dynamic Flexible Job Shop Scheduling problems (DFJSSP). It reviews a wide range of studies that address different scheduling strategies, various types of disruptive events, and multiple objectives. The numerous solution methods developed in the literature and tested on significant benchmarks are also analyzed. This […]
-
Impact Detection in Fall Events: Leveraging Spatio-temporal Graph Convolutional Networks and Recurrent Neural Networks Using 3D Skeleton Data
Fall represents a significant risk of accidental death among individuals aged over 65, presenting a global health concern. A fall is defined as any event where a person loses balance and moves to an off-position, which may or may not result in an impact where the person hits the ground. While fall detection systems have […]
-
Effects of Thermal Activation on Mechanical Performance and Sustainability of Slag-Based Geopolymers
Ground granulated blast furnace slag (GBFS)-based geopolymers represent a viable binder system that combines mechanical efficiency with a significantly lower carbon footprint when compared to conventional Portland cement. This work examines how thermal curing between 20 ◦C and 80 ◦C affects setting time, mechanical performance, shrinkage, and porosity of GBFS-based geopolymers. Curing at 40 ◦C […]
-
Dynamic mechanical analysis of shape memory polymers: thermomechanical behavior and influence of thermal stimuli
This study explores the thermomechanical properties of polymethacrylate-based shape memory polymers (SMPs), focusing on hot water as a thermal stimulus for shape recovery. Using differential scanning calorimetry (DSC) and dynamic mechanical analysis (DMA), the research evaluates thermal transitions, viscoelastic behavior, and energy dissipation. DSC identified a glass transition temperature (Tg) of 67 °C, critical for […]