projet: Développement d’un prototype de simulation utilisant la réalité virtuellepour la formation des infirmières en traumatologie

Le but du projet est de développer un prototype de simulation d’un patient virtuel permettant aux étudiantes infirmières de pratiquer des séquences d’action difficilement reproductibles dans la vraie vie. Différentes recherches seront réalisées en lien avec le développement de cet outil et son utilisation pour la formation des infirmières. Dans ce stage, le stagiaire travaillera […]

Read More
Clustering de questionnaires de satisfaction clients

L’objectif de ce projet de recherche est d’améliorer la compréhension des membres par les conseillers de la Fédération des caisses Desjardins. Pour ce faire, nous avons mis en place une solution permettant d’analyser l’information provenant des appels et des discussions par chat. Grâce à différents algorithme de traitement automatique du langage, nous pouvons extraire les […]

Read More
Multimodal Representation Learning for Pregnancy Care

Machine learning for healthcare promises to improve our diagnostic ability, to plot optimal treatment plans, and to smooth clinical operations and lower costs. But, central to these promises is a strong, generalizable numerical representation of a patient’s prior medical history that is reflective of clinical similarity and amenable to modeling. Learning such a representation is […]

Read More
Path Planning for Resilient Multi-robot Connectivity

Robotics and automation are radically transforming industries—from manufacturing to services—as well as societies. Collaborative multi-robots, in particular, have the potential to greatly improve the performance of any spatial task (e.g., exploration and surveillance) much like distributed computing impacted information science. One fundamental, enabling property of these systems is the ability for their members to exchange […]

Read More
Dance Like the Machine’s Watching

We are proposing an investigation of techniques and technologies to support media-enhanced group performances that integrate different performative art forms (dance, theatre, clown, voice, choral) with responsive mixed reality technologies and public data sets. We will work with a group of young performers (13-17 years old) and a local Vancouver choreographer to deeply investigate, with […]

Read More
Investigations and Analysis of Industrial Internet of Things Ecosystems

Rimot monitors, controls and provides insights into remote critical infrastructure through the use of enabling technologies such as data analytics, security and advanced networking. Critical research areas in data analytics, security and advanced networking are beneficial for the creation of unique intellectual property and commercialization opportunities for Rimot. This project will focus on the investigations […]

Read More
Microcontroller development and integration for high voltage bushing condition monitoring through wireless communication

It has been demonstrated in the previous research that monitoring only one point as the sole region of insulation degradation is not sufficient for operational safety of high-voltage bushings. Therefore, monitoring a wider volume of the high stress region inside the bushing using ECT sensing becomes a necessity for earlier detection of defects. In this […]

Read More
Adversarial Examples and Uncertainty

While neural networks can classify images with very high accuracy, it was shown in 2013 (original paper by Szegedy et al) that it is also possible to make very small perturbation to an image so that the network misclassifies it (e.g. so that a panda is classified as an airplane). Many variations of this effect […]

Read More
Measured and perceived differences between writing on digital and analog surfaces

Digital devices have the potential to play a positive role in the classroom. For example, longhand note-taking has been shown help learners better remember what they’ve learned than typing notes on a keyboard. With younger generations more accustomed to using digital devices in their everyday lives, it is important that the educational system finds a […]

Read More
Sélection d’un ensemble d’amorçage pour l’apprentissage actif appliqué à la prédiction structurée

L’apprentissage automatique est une tâche d’intelligence artificielle où un algorithme apprend une certaine tâche à partir d’exemples. Ce projet a pour objectif de réduire autant que possible la quantité de tels exemples qui doivent être vus par un algorithme pour atteindre des niveaux de performance acceptables. La raison étant que ces exemples sont souvent produits […]

Read More
Next Generation User Product Documentation

Product documentation is an important information tool connecting any business to its end-users and customers. Comprehensive product documentation will likely result in positive evaluation of the products by the customers and may influence their future purchasing decisions. Many studies show product documentation remains an essential element of any new product even for modern electronic devices […]

Read More