Résultats de recherche

Formulaire d'inscription - Défense publique de thèse - Guillaume Maître Nom Prénom Adresse e-mail Assistera à la réception qui suivra la défense Oui ( optionnel ) Non ( optionnel ) Désire une vignette de parking Oui ( optionnel ) Non ( optionnel ) Souhaite un certificat pour l'assistance à la défense Oui ( optionnel ) Non ( optionnel ) Pour le traitement de votre demande, les données sans mention « optional » doivent obligatoirement être complétées. Lorsque vous soumettez ce formulaire, les données complétées sont transmises à l’UNamur et utilisées pour donner suite à votre demande. Pour en savoir plus sur la protection de vos données et sur vos droits This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

JuryProf. Benoit Frénay, Université de Namur (Promoteur)Prof. Isabelle Linden, Université de Namur (Co-Promoteur) ;Prof. Xavier Devroey, Université Namur (Président) ;Prof. Claire Lobet, Université de Namur ;Prof. Florentin Kucharczak, Université de Montpellier ;Mr. Achimi Hassaini, Thales Alenia SpaceMr. Olivier Dequenne, AISIN Europe.AbstractThis thesis proposes a robust, interpretable, and transferable deep-learning framework for anomaly detection in safety-critical domains such as industrial quality control and medical diagnostics. These two fields, though distinct, share major challenges: class imbalance with limited abnormal samples, and the need for trustworthy and real-time decisions under strict reliability constraints. The main objective is, thus, to build methods with minimal supervision (training with normal data only) while allowing a human-aligned interpretability.The approach combines artificial intelligence unsupervised generative modeling with supervised classification, focusing on patching techniques, local representation, and interpretable scoring. Four key contributions structure this work:(i) Generative Adversarial Network Anomaly Detection through IntermediatePatches (GanoDIP), a Generative Adversarial Network (GAN) architecture for high-resolution, industrial anomaly localization at the patch level.(ii) Vector Quantized Generative Adversarial Network Anomaly Detectionthrough Intermediate Patches (VQGanoDIP), an extension with vector-quantized latent representations and composite scoring for improved reconstruction and fidelity.(iii) Cycle Generative Adversarial Network-Anomaly Detection (CGAN-AD), a conditional image translation model that integrates both normal and abnormal data for enhanced domain transfer in industrial and medical settings.(iv) Trustworthy approximated partial AUC (tapAUC), a loss function that enforces the Zero False Negative constraint, for high recall in critical scenarios.These models are deployed in real-world use cases. The framework is integrated into an active production line to detect unexpected components (such as screws) in printed circuit boards, delivering interpretable decisions with minimal false alarms. In the medical domain, the approach is adapted to well perform in Positron Emission Tomography (PET) based coma receptivity analysis, and some techniques are incorporated for an ovarian cancer segmentation application. These results demonstrate not only technical efficiency but also organizational viability through human-in-the-loop deployment and real-time scalability.Together, these contributions establish a modular, constraint-aware, and explainable anomaly detection paradigm, advancing the field towards trustworthy and human-centered artificial intelligence in high-stakes environments.

Nos conférenciers principaux pour 2026 sont la professeure Roosmarijn Vandenbroucke (Université de Gand) et la professeure Nelly Litvak (Université technologique d'Eindhoven). Plus d'infos sur le site "Women in science"

Le F.R.S.-FNRS vient de publier les résultats de ses différents appels 2025. Il s’agit des appels « Crédits & Projets » et « WelCHANGE » ainsi que les appels « FRIA » (Fonds pour la formation à la Recherche dans l’Industrie et dans l’Agriculture) et « FRESH » (Fonds pour la Recherche en Sciences Humaines) visant à soutenir des thèses de doctorat. Résultats pour l’UNamur ? 28 projets sélectionnés témoignant de la qualité et de la richesse de la recherche à l’UNamur. 

Terminator pour parler d’IA ? Wall-E pour parler de la dépendance technologique ? The Truman Show pour évoquer les réseaux sociaux ? Dans un nouvel ouvrage, deux professeurs de l’UNamur, Anthony Simonofski (transformation numérique- Faculté EMCP – Institut NaDI) et Benoît Vanderose (Génie logiciel – Faculté d’informatique – Institut NaDI), proposent un voyage à la croisée du numérique et de l’imaginaire cinématographique. 

Le Namur Digital Institute (NaDI) lance un cycle de rendez-vous originaux : « Les Séances du Numérique ». Des films suivis de débats avec des experts et expertes pour comprendre les défis du numérique et stimuler la réflexion collective. Un projet porté par Anthony Simonofski, Anne-Sophie Collard, Benoît Vanderose et Fanny Barnabé. 

Le professeur Elio Tuci vient d'obtenir un financement Crédit de Recherche du FNRS. L'institut naXys s'est spécialisé dans l'analyse des systèmes complexes, qu'il s'agisse d'astronomie et de cosmologie dynamique, de biologie mathématique, d'optimisation en optique, de complexité économique ou encore de l'étude de la stabilité et de la robustesse de ces systèmes. L’institut est structuré en 6 axes de recherche : Space, Bio, Optics, Eco, Robust et Robotics. 

The workshop will feature:A keynote presentation on public value and AI implementation at VRT.Sessions on discoverability, user agency, and explainability.Discussions on regulation, including perspectives on the AI Act and transparency in media.An interactive session showcasing AI-driven prototypes.The event will also highlight our project’s latest findings. Join us for a day of thought-provoking discussions, knowledge exchange, and networking opportunities!Would you like to attend? Places are limited and will be allocated on a first-come, first-served basis, so register as soon as possible. Registration will close on April 11, 2025. More information here

SynopsisOver recent years, the development of agent-based models has allowed researchers to advance their understanding of naturally occurring collective behaviours. Swarm robotics, a field studying the design of decentralised robot swarms, has emerged following the replication of some collective behaviours in artificial groups of robots. The first part of this thesis provides novel techniques for the aggregation of heterogeneous swarms. First, we enhance an existing controller for an aggregation problem on two sites through the use of informed robots. We show that our simplified approach offers a wider range of operating conditions and a greater flexibility. Second, we provide a new method for the aggregation of robot swarms with adaptive random walks. We separately study cue-based aggregation with a swarm of robots only sensing private information and neighbour-based aggregation with a swarm of robots sensing social information. We show that a trade-off can be obtained with a heterogeneous swarm composed of the two robot types, forming a dense cluster near the minimum of an environmental cue. Private and social information also play a key role in the evolution of biological processes inside animal groups. Dispersal, the movement of an animal from site of birth to site of reproduction, is strongly affected by the acquisition and the use of information. Since experimental research is often difficult to conduct while accounting for multiple information sources and environmental variability, the use of agent-based models offer an opportunity to study the evolution of dispersal and its associated costs linked to private and social information in a controlled setting. The second part of this thesis provides an agent-based model of dispersal including the acquisition of information and its associated costs. Throughout three case studies, we observe the evolution of genes linked to the acquisition of information and the obtained dispersal strategies in different scenarios. Jury members Prof. Wim Vanhoof, Président, Université de Namur, BelgiqueProf. Elio Tuci, Secrétaire, Université de Namur, BelgiqueProf. Timoteo Carletti, Membre interne, Université de Namur, Belgique Prof. Eliseo Ferrante, Membre externe, Vrije Universiteit Amsterdam, Pays-BasProf. Mauro Birattari, Membre externe, ULB, Belgique Prof. Andreagiovanni Reina, Membre externe, Universität Konstanz, Allemagne 

Obtenir instantanément la traduction en langue des signes (LSFB) d’un mot écrit en français : voilà ce que permet MOSI (Du mot au signe). Ce nouvel outil est le fruit d’une collaboration entre l’Université de Namur, l’asbl École et Surdité et l’asbl LSFB, soutenue par la Fondation Roi Baudouin.

Synopsis The spreading of internet-based technologies since the mid-90s has led to a paradigm shift from monolithic centralized information systems to distributed information systems based upon the composition of software components, interacting with each other and of heterogeneous natures. The popularity of these systems is nowadays such that our everyday life is touched by them.Classically concurrent and distributed systems are coded by using the message passing paradigm-according to which components exchange information by sending and receiving messages. In the aim of clearly separating computational and interactional aspects of computations, Gelernter and Carriero have proposed an alternative framework in which components interact through the availability of information placed on a shared space. Their framework has been concretized in a language called Linda. A series of languages, referred to nowadays as coordination languages, have been developed afterwards. In addition to providing a more declarative framework, such languages nicely fit applications like Facebook, LinkedIn and Twitter, in which users share information by adding it or consulting it in a common place. Such systems are in fact particular cases of so-called socio-technical systems in which humans interact with machines and their environments through complex dependencies. As coordination languages nicely meet social networks, the question naturally arises whether they can also nicely code socio-technical systems. However, answering this question first requires to see how well programs written in coordination languages can reflect what they are assumed to model.This thesis aims at addressing these two questions. To that end, we shall use the Bach coordination language developed at the University of Namur as a representative of Linda-like languages. We shall extend it in a language named Multi-Bach to be able to code and reason on socio-technical systems. We will also introduce a workbench Anemone to support the modelling of such systems. Finally, we will evidence the interest of our approach through the coding of several social-technical systems. The Jury Prof. Wim Vanhoof - University of Namur, BelgiumProf. Jean-Marie Jacquet - University of Namur, BelgiumProf. Katrien Beuls - University of Namur, BelgiumProf. Pierre-Yves Schobbens - University of Namur, BelgiumProf. Laura Bocchi - University of Kent, United KingdomProf. Stefano Mariani - UNIMORE University, Italy Participation upon registration. Register here