This project aims to employ cutting-edge deep learning models to address the critical issue of water leakage in water distribution networks (WDNs). Leakage in WDNs leads to significant water wastage, infrastructure damage, service disruption, and even contamination. The proposed approach leverages Convolutional Neural Networks (CNNs) trained explicitly for optimizing leak detection. Using synthetic datasets that […]

We proposed a breath analyzer to identify viruses by utilizing an affordable fiber coupler. This sensor captures the optical absorbance spectrum, which contains the unique signatures of viruses present in the breath. The device is user-friendly: simply exhale into the analyzer to receive results. Our product addresses the traditional challenges of virus detection, eliminating high […]

A Comprehensive Solution for Healthcare Organizations, Newcomers, and Non-medical Education Background Individuals. The product aims to address the root cause problem of bias in healthcare workforce recruitment and create a more inclusive and efficient healthcare workforce in Canada through the implementation of an AI-powered Healthcare Recruitment and Career Journey Solution.

Object handovers, which involve the action of giving and receiving objects, are an integral task for human-robot collaboration. Current human-to-robot handover systems rely on learning from sampled human expert trajectory data [5]. These data are usually difficult to gather, as two humans must hand over many different objects while recording the human motion with a […]

SilicoLabs’ software revolutionizes psychology/neuroscience research by harnessing XR to create real-world simulations. Researchers import their 3D models, video, audio, images and creating dynamic interactions between them and the participant – all without writing a single line of code! Researchers determine which variables they want to track (e.g., number of times an object is picked up) […]

This project will investigate the impact of TikTok’s emergence as a platform characterized by de-contextualized, algorithm-driven content. Understanding the distinctions between TikTok’s design principles and those of other platforms is essential for comprehending their influence on user interactions, from constructive engagement to polarization. The research will employ agent-based models of opinion dynamics, calibrated using data […]

EPAID Technology: EPilepsy AI-Driven Technology aims to automate electrophysiological signal processing practice to assist clinicians in the treatment of epilepsy. We will partner with Springboard, who provides strategically positioned resources to Atlantic Canadian universities and colleges alike, helping them transfer both knowledge and technology into the private sector.

Les ingénieurs utilisent les précipitations maximales probables (PMP) pour concevoir des infrastructures résistantes aux aléas hydrométéorologiques. La PMP est définie par l’Organisation Mondiale Météorologique (OMM) comme la quantité maximale d’eau pouvant s’accumuler en une période donnée dans une région, indépendamment des tendances climatiques à long terme. Une mauvaise estimation de la PMP peut entraîner des […]

Pain is a complex unpleasant experience that varies from a person to another. Learning, priors and expectations are known to have a substantial influence on subjective pain experience. For example, having expectations or being told that an event will be painful can be sufficient to shift a person’s pain experience into a more painful realm. […]

Typical natural language understanding (NLU) models like the ones deployed in virtual assistant (VA) systems are designed to work for a finite set of pre-defined domains. Ideally, if the text representation of a spoken utterance does not belong to the supported set of domains the NLU model would produce a response with low confidence score […]

Ce projet de recherche s’inscrit dans le cadre d’un projet du Centre d’excellence international de Montréal en intelligence artificielle (CEIMIA) dont le but est d’étudier comment l’intelligence artificielle peut contribuer à une meilleure découvrabilité des contenus culturels francophones, et à en traiter les enjeux, dans le contexte actuel des écosystèmes culturels et numériques. La littérature […]