L’acquisition de données d’imagerie de diffusion est suceptible à un important problème de variabilité à travers les différents sites d’acquisition (e.g. Sherbrooke vs. Montréal) et à travers les fabricants (e.g. Siemens vs Philips). Puisque ces données de diffusion ne sont pas invariantes aux protocoles et scanners utilisés, il s’agit d’un problème de taille pour les […]

Dans les centrales hydroélectriques, les groupes turbine-alternateurs sont réparés et installés selon un calendrier de travaux. Compte tenu de leur taille, d’autres pièces doivent être déplacées pour accéder aux pièces à démonter, réparer ou à installer. Afin de déterminer le plan d’aménagement des pièces, plusieurs contraintes doivent être respectées : 1) le calendrier des travaux, […]

In this project, we build on these preliminary works and explore the capabilities of different machine learning techniques anomaly detections and predictions of network degradation issues. We also plan to develop ap-proaches to help Cable Network Operation teams triage and diagnose cable network issues efficiently. The results of this project will help Cable Network companies […]

There has been a dramatic increase in digital well-being products in recent years and there is a market saturated with ineffective user experiences and little to no sustainable, desired behavioural change. By assessing and enhancing the effectiveness of a personalized approach to digital well-being app interaction through machine learning and emotion-driven adaptive computing, we can […]

This project aims to predict demand and inventory shortages for better inventory management in health care institutions. This will initially allow for a reduction in the expenses generated by emergency orders placed during a stock shortage. Indeed, it will be possible for the establishment to order a larger quantity of the product from the supplier […]

The main objective of this research project is to evaluate and analyze the effect of music in well-being and state of flow of the human participants. First, we intend to design a set of scenarios, in which we collect qualitative and quantitative data via micro-phenomenology and biofeedback techniques. Then we analyze the collected data to […]

Schedulability analysis aims at determining whether task executions complete before their specified deadlines. It is an important activity in developing real-time systems. However, in practice, engineers have had difficulties applying existing techniques mainly because the working assumptions of existing methods are often not valid in their systems. Specifically, uncertainties in real-time systems and hybrid scheduling […]

Market makers facilitate trading in electronic financial markets by simultaneously offering to buy and sell the same asset at any given time. Their role is to provide price stability and increase market liquidity to improve its overall efficiency. Digital assets markets are extremely fragmented and present both challenges and opportunities for market makers. These latter […]

When utilizing and implementing ML for prediction using administrative health data, two key issues are ML algorithm evaluation and generalizability21. Current approaches evaluate model performance by quantifying how closely the prediction made by the model matches known health outcomes. Evaluation metrics include sensitivity, specificity, and positive predictive value, as well as measures such as the […]

The interns will work on improvements to algorithms using geometry and deep learning for estimating human pose of individuals and the distance between them. This is a difficult task to do from videos as it involves 1) the detection and 2) 3D metric reconstruction of persons in all kinds of poses and apparel. The interns […]

In AI safety, compliance ensures that a model adheres to operational specifications at runtime to avoid adverse events for the end user. This proposal looks at obtaining model compliance in two ways: (i) applying corrective measures to a non-compliant Machine Learning (ML) model and (ii) ensuring compliance throughout the model’s training process. We aim to […]

As Building Automation Systems (BAS) are becoming a standard in commercial buildings, and additional 3rd party applications can help buildings owners gain insights from their BAS, structured metadata management becomes the key to success. However, as converting traditional sensors naming convention to structured tagging systems is an expensive and time-consuming process, this project aims at […]