Publications
-
A memetic method for solving portfolio optimization problem under cardinality, quantity, and pre-assignment constraints
In industrial finance, portfolio selection has emerged as a critical challenge that has received considerable attention over the past few decades. The standard approach to this problem is the Markowitz mean–variance model, which seeks to balance two inherently conflicting objectives: maximizing returns and minimizing risk. This study investigates portfolio optimization under realistic constraints, including cardinality, […]
-
Deep Reinforcement Learning of Simulated Students Multimodal Mobility Behavior: Application to the City of Toulouse
This study presents a Deep Reinforcement Learning (DRL) approach to address the multimodal mobility behavior of daily commuters, focusing specifically on students’ home-university multimodal trips. The proposed mesoscopic model addresses key limitations of recent macro and microscopic models by balancing individual mobility preferences with significant group-level student factors. At its core, the model employs a […]
-
Integrating Centrality Measures in Federated Learning-Based Intrusion Detection Systems
Network Intrusion Detection Systems (NIDS) are mechanisms designed to improve security by monitoring networks for signs of potential intrusions. While data-driven deep learningbased NIDSs have been popular for their superior performance, they are limited by their reliance on large amounts of data, often processed in a centralized manner. Federated Learning (FL) has thus emerged as […]
-
A Novel Federated Learning Client Selection With Anomaly Detection Approach for IoT Systems
Federated Learning (FL) is emerging as a crucial approach to enhance data privacy and security, particularly in smart buildings and Internet of Things (IoT) ecosystems. By distributing learning across multiple clients, FL minimizes the need for centralized data transfers. This decentralized approach allows clients to collaboratively improve machine learning models without sharing raw data, and […]
-
A Secure Architecture for Digital Twins in Resource-Constrained Industrial Systems
Digital Twins (DT) are transforming the Industrial Internet of Things (IIoT) by providing virtual replicas of physical assets, enabling enhanced predictive analytics and data-driven decision-making. However, as Industry 5.0 integrates DT with generative AI technologies via APIs and tokens, security risks increase. Outdated modeling tools, coupled with vulnerabilities in resource-constrained environments, such as limited computational […]
-
Improving predictive maintenance: Evaluating the impact of preprocessing andmodel complexity on the effectiveness of eXplainable Artificial Intelligence methods
Due to their performance in this field, Long-Short-Term Memory Neural Network (LSTM) approaches are often used to predict the remaining useful life (RUL). However, their complexity limits the interpretability of their results. So, eXplainable Artificial Intelligence (XAI) methods are used to understand the relationship between the input data and the predicted RUL. Modeling involves making […]
-
A Continual Learning Approach for Failure Prediction under Non-Stationary Conditions: Application to Condition Monitoring Data Streams
Accurate forecasting of Remaining Useful Life (RUL) is crucial for predictive maintenance (PdM), permitting prompt actions that decrease downtime and maintenance expenses. Yet, conventional RUL estimation techniques often struggle to adjust to changing operational conditions and data drift, restricting their use in dynamic industrial settings. This research presents a continual learning framework designed for these […]
-
Artificial Intelligence Non-invasive Methods for Neonatal Jaundice Detection: A Review
Neonatal jaundice is a common and potentially fatal health condition in neonates, especially in low and middle income countries, where it contributes considerably to neonatal morbidity and death. Traditional diagnostic approaches, such as Total Serum Bilirubin (TSB) testing, are invasive and could lead to discomfort, infection risk, and diagnostic delays. As a result, there is […]
-
Optimizing Supplier Selection Under Risk: A Multi-Method Approach
This paper presents an innovative approach to optimize supplier selection while minimizing transportation costs in supply chain management. The methodology integrates Mixed Integer Linear Programming (MILP), Genetic Algorithm (GA), and a stochastic programming approach (MILP combined with Monte Carlo simulation, called MCLP) to address the complexities of supplier selection. The MILP model is designed to […]
-
The hidden face of the Proteus effect: Deindividuation, embodiment and identification
The Proteus effect describes how users of virtual environments adjust their attitudes to match stereotypes associated with their avatar’s appearance. While numerous studies have demonstrated this phenomenon’s reliability, its underlying processes remain poorly understood. This work investigates deindividuation’s hypothesized but unproven role within the Proteus effect. Deindividuated individuals tend to follow situational norms rather than […]
-
IdeAM: A serious game to foster creativity in Additive Manufacturing
This study investigates the potential of serious games (SG) to enhance creativity in additive manufacturing (AM). While AM offers unique opportunities to explore complex designs, traditional manufacturing methods often limit designers’ creativity due to cognitive biases formed by years of using conventional processes. This research aims to introduce IdeAM, a SG designed to foster creativity […]
-
Exploring Behavioral Dynamics to Enhance Collective Intelligence in Virtual Environments
Collective intelligence (CI) is a predictive measure of a group’sability to perform a wide variety of tasks. It is an essential conceptfor understanding team dynamics and enhancing team performance.While extensively studied in traditional environments such as faceto-face settings or online interactions, CI remains underexplored inimmersive Virtual Reality (VR). This thesis has three goals: (1) toanalyze […]
Chargement en cours…
Erreur : tout le contenu a été chargé.