Scientific Publications of the University of Toulouse II Le Mirail
Not a member yet
92205 research outputs found
Sort by
Explainable quantum convolutional neural network for attack detection in healthcare IoMT systems using SHAP and Grid5000 computing
No full textInternational audienceThe growth of the Internet of Medical Things (IoMT) improves patient care and data analysis, but it alsomakes healthcare systems newly vulnerable to cyberattacks.Current intrusion detection systems (IDS) strug-gle to work with the many different IoMT protocols. More importantly, they are ”black boxes” that can’texplain their decisions, which is a major problem in healthcare where safety is critical. This paper pro-poses a hybrid explainable quantum convolutional neural network (QCNN–SHAP) framework for accurateand transparent attack detection in IoMT environments. The QCNN exploits quantum feature encoding andentanglement to capture complex correlations in high-dimensional IoMT traffic data, while SHAP (SHapleyAdditive exPlanations) provides feature-level interpretability for each detection decision. We tested our modelon the CICIoMT2024 dataset, a benchmark for multi-protocol IoMT security assessment, using the Grid5000distributed computing platform. The proposed QCNN–SHAP model achieved a detection accuracy of 98.05%,outperforming current models like CNN, LSTM–Autoencoder, and Transformer–XAI models while maintain-ing explainability and moderate computational cost. SHAP analysis showed that key network features suchas packet size variance, flow duration, and protocol type were the most influential in identifying attacks. Theresults validate the model’s robustness, interpretability, and suitability for real-time IoMT intrusion detectionin healthcare contexts
A Multi-LLM Agent System for Modular Ontology Population: A Case Study on ADHD
No full textInternational audienceModular ontologies play a crucial role in structuring and interpreting complex knowledge, where they enable the representation of contextual information from diverse sources. To fully exploit these ontological models, a population phase is essential, involving the enrichment of the ontology with concrete instances. However, the automatic population of such ontologies from heterogeneous sources remains a significant challenge. Traditional rule-based or supervised learning approaches require extensive human supervision and often lack generalizability. The use of Large Language Models (LLMs) has recently emerged as a promising alternative, but their limitations become evident in complex modular architectures. This study proposes a multi-agent approach for the automatic population of modular ontologies. Each agent is an LLM guided by precise instructions and enhanced with appropriate tools, dedicated to one or more ontological modules. Our methodology combines advanced prompt engineering techniques with strategies for hallucination mitigation to ensure extractions that are both accurate and compliant with the ontology’s specifications. Our experimental setup involves extracting RDF triples from diagnostic PDF reports and activity schedules stored in a MongoDB database, aimed at the automatic population of an ADHD ontology. The results show that our multi-agent approach consistently outperforms mono-agent methods relying on a single LLM, regardless of the configuration used. We observe significant gains in precision, recall, and F1-score as well as a notable reduction in errors and hallucinations. This study demonstrates both the feasibility and effectiveness of a multi-agent architecture for the automatic population of a modular ontology
Adaptive Agents in Spatial Double-Auction Markets: Modeling the Emergence of Industrial Symbiosis
No full textInternational audienceIndustrial symbiosis fosters circularity by enabling firms to repurpose residual resources, yet its emergence is constrained by socio-spatial frictions that shape costs, matching opportunities, and market efficiency. Existing models often overlook the interaction between spatial structure, market design, and adaptive firm behavior, limiting our understanding of where and how symbiosis arises.We develop an agent-based model where heterogeneous firms trade byproducts through a spatially embedded double-auction market, with prices and quantities emerging endogenously from local interactions. Leveraging reinforcement learning, firms adapt their bidding strategies to maximize profit while accounting for transport costs, disposal penalties, and resource scarcity. Simulation experiments reveal the economic and spatial conditions under which decentralized exchanges converge toward stable and efficient outcomes. Counterfactual regret analysis shows that sellers' strategies approach a near Nash equilibrium, while sensitivity analysis highlights how spatial structures and market parameters jointly govern circularity.Our model provides a basis for exploring policy interventions that seek to align firm incentives with sustainability goals, and more broadly demonstrates how decentralized coordination can emerge from adaptive agents in spatially constrained markets
Long‐Term Effects of Xenotransplantation of Human Enteric Glia in an Immunocompetent Rat Model of Acute Brain Injury
No full textInternational audienceAcute brain injuries are characterized by extensive tissue damage, resulting in functional deficits in patients. The capacity of nerve tissue to self‐regenerate is insufficient, thus therapies based on exogenous cells are urgently needed. Human enteric glia (EG) have interesting intrinsic properties that make them a valuable candidate for regenerative medicine. Malonate‐induced acute brain injury is performed in the motor cortex of female rats, causing extensive tissue damage and long‐lasting sensorimotor deficits. Human EG are isolated, expanded and administered intranasally in awake immunocompetent rats. To determine the long‐term safety and efficacy of human EG treatment, longitudinal evaluation of sensorimotor function, post‐mortem tissue analysis and the fate of human EG are assessed thirty‐six‐weeks post‐injury. Transplanted human EG are well tolerated in immunocompetent rats. Thirty‐six‐weeks post‐injury, intranasally delivered human EG are detected in the rat brain, mainly in the injured motor cortex. They engraft and integrate with the host tissue, and enhance endogenous angiogenesis and neurogenesis. Notably, mature neurons derived from human EG are found and appear enveloped by oligodendrocytes, form synaptic connections with the host tissue, and are differentiated. This is the first study demonstrating the feasibility, safety and efficacy of intranasal administration of human EG for treatment of brain injury
Multi-criteria and multi-stage environmental study of Pl@ntnet service for the year 2024
No full textIn this study, we focus our investigation on Pl@ntNet, a citizen science platform, which re- lies on Artificial Intelligence (AI) models to identify plant species. Pl@ntNet provides a large-scale infrastructure supporting millions of users in over 200 countries. At this stage of deployment, and with years of experience developing the platform, Pl@ntNet is committed to understanding the environmental impacts of its identification service and contributing to the search for reduction opportunities. Our investigations assess the associated environmental impacts of Pl@ntNet for the year 2024. We based our approach on multi-criteria LCA, considering multiple impact type and the different life-cycle phases
Dispersion for the Schrödinger equation on the line with short-range array of delta potentials
No full textWe study dispersive properties of the one-dimensional Schrödinger equation with a short-range array of delta interactions. More precisely, we consider the self-adjoint operator obtained by perturbing the free Laplacian on the line with a real-valued sequence of Dirac delta potentials and belonging to weighted ℓ^1(Z) spaces. Under suitable decay assumptions on the coupling constants and in the absence of a zero-energy resonance, we establish the L^1 (R) → L^∞ (R) dispersive estimate with decay rate |t|^{-1/2} for the associated Schrödinger group. The proof relies on a limiting absorption principle in weighted spaces, explicit representation of the resolvent kernel in terms of Jost solutions and Born series expansion of the Friedrichs extension of the perturbed operator
Use as directed? A comparison of software tools intended to check rigor and transparency of published work
No full textInternational audienceThe causes of the reproducibility crisis include lack of standardization and transparency in scientific reporting. Checklists such as ARRIVE and CONSORT seek to improve transparency, but they are not always followed by authors and peer review often fails to identify missing items. To address these issues, there are several automated tools that have been designed to check different rigor criteria. We have conducted a broad comparison of 11 automated tools across 9 different rigor criteria from the ScreenIT group. We found some criteria, including detecting open data, where the combination of tools showed a clear winner, a tool which performed much better than other tools. In other cases, including detection of inclusion and exclusion criteria, the combination of tools exceeded the performance of any one tool. We also identified key areas where tool developers should focus their effort to make their tool maximally useful. We conclude with a set of insights and recommendations for stakeholders in the development of rigor and transparency detection tools. The code and data for the study is available at https://github.com/PeterEckmann1/tool-comparison
Investir, produire, exporter : les actionnaires de la Compagnie du Levant et les manufactures languedociennes (1670–1695)
No full textEn s’intéressant aux actionnaires de la Compagnie du Levant, cet article examine le rôle des investisseurs privés dans la mise en œuvre de la politique industrielle colbertiste en Languedoc. À travers les trajectoires de trois actionnaires — Pennautier, Fredian et Magy —, l'article montre comment ces acteurs articulent capitaux privés, réseaux institutionnels et soutiens publics pour relier les manufactures drapières aux circuits d'exportation méditerranéens, donnant naissance à une forme originale de « capitalisme d'interface » à la fin du XVIIe siècle