Publications

• Article dans une revue

Combining real data and expert knowledge to build a Bayesian Network — Application to assess multiple risk factors for fall among elderly people

Gulshan Sihag, Véronique Delcroix, Emmanuelle Grislin-Le Strugeon, Xavier Siebert, Sylvain Piechowiak, François Puisieux

Building a prediction model based on both real data and expert knowledge can be challenging. We experienced this difficulty in our context of predicting fall risk factors in the elderly, where two sources of data were available: hand-reported information from medical consultations and expert…

Expert Systems with Applications, 2024, 252, pp.124106. ⟨10.1016/j.eswa.2024.124106⟩. ⟨hal-04649596⟩

• Article dans une revue

Topology optimization of curved thick shells using level set method and non-conforming multi-patch isogeometric analysis

Fernando Hübner Scherer, Malek Zarroug, Hakim Naceur, Andrei Constantinescu

We present a novel framework for topological shape optimization of curved non-conforming multi-patch and trimmed thick-shells subjected to external loads. Our method integrates the level set method (LSM) with a diffuse interface, a Hadamard shape derivative, and multi- patch isogeometric analysis (…

Computer Methods in Applied Mechanics and Engineering, 2024, 430, pp.117205. ⟨10.1016/j.cma.2024.117205⟩. ⟨hal-04758603⟩

• Communication dans un congrès

Ethical issues in the use of Generative Artificial Intelligence in performance management: Industrial case studies

Lamia Berrah, Damien Trentesaux, Frederic Guerre-Chaley

<div><p>Generative Artificial Intelligence (GAI) presents significant potential for managing Industry 4.0 companies performance, driving efficiency, reactivity and innovation and enhancing thus the performance. However, despite its advantages, the use of GAI also has several limitations…

SOHOMA 2024, Technical University of Applied Sciences. - Augsburg, Germany (Allemagne), Sep 2024, Augsburg, Germany. ⟨hal-04745414⟩

• Communication dans un congrès

An Efficient Decentralized Fine-grained Access Control for IoT Ecosystems over NDN

Ferhat Mecerhed, Youcef Imine, Antoine Gallais, Stefan Fischer, Mohamed Ahmed Hail

2024 International Conference on Software, Telecommunications and Computer Networks (SoftCOM), Sep 2024, Split, France. pp.1-6, ⟨10.23919/SoftCOM62040.2024.10721767⟩. ⟨hal-05031066⟩

• Communication dans un congrès

A Literature Review and Taxonomy Proposal of Industrial Symbiosis Practices

Soukaina Benchari, Cecilia Daquin, Emmanuelle Grislin-Le Strugeon, Yves Sallez

In response to the environmental repercussions of the linear economy model, the circular economy has emerged, aiming to reduce environmental impact while balancing economic and social aspects. Industrial ecology is a pillar of cir- cular economy, facilitating collaboration among local industries…

Int. Workshop on Service-Oriented, Holonic and Multi-Agent Manufacturing Systems for Industry of the Future (SOHOMA), Sep 2024, Augsburg, Germany. ⟨hal-04991038⟩

• Pré-publication, Document de travail

Modeling Resilient Ethics, Modéliser l’éthique résiliente

Bako Rajaonah, Enrico Zio

Moral priorities may change in extreme situations such as disasters, and stakeholders may find it difficult to select the most acceptable actions. We propose a social-ecological model of resilient ethics that can provide the best acceptable guideline for action under the most appropriate ethical…, Les priorités morales peuvent changer dans des situations extrêmes telles que les catastrophes, et les décideurs peuvent avoir des difficultés à déterminer les actions les plus acceptables. Nous proposons un modèle social-écologique d'éthique résiliente qui peut aider à sélectionner la…

2024. ⟨hal-04703643⟩

• Communication dans un congrès

Gray Wolf Optimization Algorithm for Fuzzy Logic Driver Behavior Model

Daniel Dcl Cisneros Lombera, Hossam Eddine Glida, Chouki Sentouh, Boussaad Soualmi, Jean-Christophe Popieul

In this study, we propose a fuzzy decision system for human involvement in a driver-vehicle-environment system, capturing takeover scenarios by different drivers. The driver’s behavior is influenced by environmental factors. Expert opinions, gathered through questionnaires, contribute to defining…

Driving Simulation Conference (DSC), Sep 2024, Strasbourg, France. ⟨hal-04731558⟩

• Communication dans un congrès

Accelerated NAS via pretrained ensembles and multi-fidelity Bayesian Optimization

Houssem Ouertatani, Cristian Maxim, Smail Niar, El-Ghazali Talbi

Bayesian optimization (BO) is a black-box search method particularly valued for its sample efficiency. It is especially effective when evaluations are very costly, such as in hyperparameter optimization or Neural Architecture Search (NAS). In this work, we design a fast NAS method based on BO.…

33rd International Conference on Artificial Neural Networks (ICANN), Sep 2024, Lugano, Switzerland. ⟨10.1007/978-3-031-72332-2_17⟩. ⟨hal-04611343⟩

• Article dans une revue

Fixed-Time Fault-Tolerant Adaptive Neural Network Control for a Twin-Rotor UAV System with Sensor Faults and Disturbances

Aymene Bacha, Abdelghani Chelihi, Hossam Eddine Glida, Chouki Sentouh

This paper presents a fixed-time fault-tolerant adaptive neural network control scheme for the Twin-Rotor Multi-Input Multi-Output System (TRMS), which is challenging due to its complex, unstable dynamics and helicopter-like behavior with two degrees of freedom (DOFs). The control objective is to…

Drones, 2024, 8 (9), pp.467. ⟨10.3390/drones8090467⟩. ⟨hal-05074853⟩

• Thèse

Wear of hot forging tools : towards an objective optimization of the durability., Usure des outils de forgeage à chaud : vers une optimisation objective de la durée de vie

Nasrine Boualem

During the hot forging process, tools are subjected to severe cyclic mechanical and thermal loads. These extreme forming conditions can damage the tools through the development of abrasive wear, cracking, and thermal and mechanical fatigue. These damages compromise the mechanical strength of the…, Durant le processus de forgeage à chaud, les outils sont soumis à des chargements mécaniques et thermiques cycliques sévères. Ces conditions de formage extrêmes peuvent endommager les outils par le développement d'usure abrasive, de fissuration, de fatigue thermique et mécanique. Ces dommages…

Mechanics [physics.med-ph]. Université Polytechnique Hauts-de-France, 2024. English. ⟨NNT : 2024UPHF0026⟩. ⟨tel-04779884⟩