This project explores how advanced artificial intelligence models can analyze network traffic while keeping sensitive data fully encrypted. Building on recent research using CryptoKAN neural networks, the project studies whether model compression techniques can make encrypted intrusion detection faster and more practical without reducing detection accuracy. The intern will first adapt and evaluate encrypted AI […]

Le projet de recherche vise à identifier et analyser différents modèles d’affaires en alimentation développés par des coopératives ou des organismes à but non lucratif (OBNL) en économie sociale au Québec. Ces organisations, engagées dans le développement de systèmes alimentaires territoriaux durables, proposent des approches variées pour combiner mission sociale et viabilité économique. La stagiaire […]

L’épilepsie touche des millions de personnes dans le monde et se manifeste par des crises soudaines qui peuvent être difficiles à prévoir ou à détecter automatiquement. Aujourd’hui, les médecins utilisent principalement l’électroencéphalogramme (EEG) pour analyser l’activité du cerveau et identifier les signes annonciateurs de ces crises. Cependant, l’interprétation des signaux EEG est complexe et nécessite […]

La pratique du vélo de montagne connaît une croissance rapide au Québec, mais il n’existe aucune progression pédagogique claire pour les jeunes de 7 à 14 ans. Cette lacune entraîne des risques accrus d’accidents et des défis pour les centres de vélo, notamment en matière d’assurance. Ce projet de 6 mois vise à développer une […]

This Mitacs project aims to transform hospital blood bank operations into a predictive, efficient, and data-driven system using ten years of real hospital data. Traditional blood bank systems lack analytical and forecasting capabilities, leading to shortages, overstocking, and wastage. The project will develop an end-to-end AI framework that forecasts blood demand, optimizes inventory, detects shortages […]

Chronic pain is one of the most common and debilitating conditions worldwide, placing a significant burden on healthcare systems. (1) In musculoskeletal injury rehabilitation, fear-avoidance beliefs—where athletes avoid movement due to fear of pain or reinjury—are strongly associated with greater pain, reduced function, and prolonged recovery. (2) Yet, this psychosocial dimension has yet to be […]

This project will examine the connections between migraine and multiple sclerosis (MS), two common neurological conditions that affect millions of people worldwide. While migraine causes severe headaches and MS can lead to long-term physical and cognitive challenges, research suggests that these conditions may share underlying immune and inflammatory mechanisms. By systematically reviewing existing human and […]

This project, conducted in collaboration with TÉLUQ University, aims to systematically review and evaluate the efficacy and safety of emerging nanobody-based therapies designed to target amyloid-ß and tau aggregates—the two hallmark proteins implicated in the development and progression of Alzheimer’s disease. Nanobodies, due to their small size, high stability, and strong binding specificity, represent a […]

This project focuses on understanding how concrete and similar building materials behave as they age, crack, and deteriorate. Material modeling is a way of using computer simulations to predict how a structure will react to forces such as weight, weather, and damage over time. By improving these simulations, engineers can better evaluate the safety of […]

Large Language Models (LLMs) are increasingly used in everyday life, yet they often make decisions based on internal assumptions and tendencies that users cannot see. These hidden patterns, called inductive biases, shape how models interpret concepts, judge situations, and respond to people. Understanding these biases is essential for building safer and more trustworthy AI systems. […]

This project aims to develop advanced deep learning models that combine graph-based neural networks with Kolmogorov-Arnold Networks (KAN) to improve the analysis of 3D point cloud data. These models will be applied to real-world problems such as identifying tree species from laser scanning data and studying brain connectivity from medical imaging. The collaboration will benefit […]

The project develops new optimization methods for a complex industrial scheduling problem involving multiple hoists moving parts through electroplating tanks under strict timing and safety constraints. Unlike existing models, the project focuses on a dynamic setting where new tasks can appear during production and where multiple hoists share tracks and must coordinate movements. The work […]