Le projet vise à développer un agent d’intelligence artificielle auditable capable d’extraire, d’organiser et d’analyser automatiquement des données financières provenant de documents non structurés déposés auprès de la SEC par des entreprises cotées, sur plusieurs années. Ces documents peuvent inclure, par exemple, des rapports annuels, des états financiers et d’autres publications d’entreprise. L’objectif est de […]

This project aims to detect and analyze automated bots responsible for spreading misinformation on various social media platforms by identifying abnormal patterns of behavior. By using data science and artificial intelligence methods, such as machine learning and network analysis, combined with insights from political science, the research will map how false information spreads online and […]

The proposed project will improve Global Maritime Canada’s document intake and record-keeping process by developing an AI-assisted workflow that streamlines how project documents are reviewed, organized, and logged into an existing internal environment. By reducing repetitive manual steps and standardizing the information captured at intake, the project aims to improve operational efficiency and the quality […]

This project develops a practical analytics framework to examine how early-stage quantum startups present their business models, target markets, and commercialization plans. Using structured data collection and interpretable machine learning methods, the project will assess whether startups’ technical positioning aligns with clear and realistic market pathways. The result will be a transparent Commercialization Alignment Index […]

By leveraging personalized gamification and persuasive technology, this project aims to improve motivation and engagement in introductory computer science (CS1) courses, which are often associated with low persistence and high dropout rates. A growing body of research shows that gamification, when grounded in motivational theory, can positively influence learner engagement; however, generic, one-size-fits-all approaches frequently […]

le projet développe des modèles prédictifs pour anticiper la demande future, permettant ainsi de stabiliser la planification et de réduire les achats d’urgence coûteux. Simultanément, une analyse rigoureuse des flux financiers identifiera les opportunités d’optimisation budgétaire et évaluera la performance de l’écosystème de fournisseurs. L’originalité du projet réside dans la conception d’un modèle capable de […]

Le paludisme, aussi appelé la malaria, est l’une des maladies infectieuses les plus meurtrières au monde. Elle est causée par le parasite protozoaire Plasmodium. Malgré les avancées significatives dans la compréhension de ce parasite, plusieurs enjeux persistent, notamment le développement de résistances aux traitements antipaludiques actuels. Cette problématique renforce l’urgence de découvrir de nouveaux composés […]

This project aims to develop and test a “digital twin” (a realistic virtual copy) of an Urban Air Mobility system, such as air taxis operating in a city, to support safer and faster operational decisions. Using a simulated city environment of Montréal and realistic flight scenarios, the project will model key elements such as vehicle […]

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 […]

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 […]

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 […]

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 […]