Classification de déchets en environnement industriel : étude pilote en milieu contrôlé

La compagnie Wastack vise à développer un système permettant d’identifier différents types de déchets néfastes dès leur arrivée aux sites d’enfouissement afin d’éviter que certains matériaux tels que les batteries, les écrans d’ordinateur ou les pneus s’y retrouvent alors qu’ils devraient être traités ailleurs. L’objectif du projet est de fournir une rétroaction continue aux citoyens […]

Read More
Détection de l’état de « flow » en temps réel par électroencéphalographie et apprentissage machine durant une expérience ludique

Les amateurs de jeu vidéo sont bien familiers avec la sensation d’être profondément captivés par un jeu au point de perdre la notion du passage du temps, tout en état capables de hautes performances sans se fatiguer mentalement. Cet état psychologique particulier a été baptisé « flow » par le psychologue hongrois Mihaly Csikszentmilhayi qui […]

Read More
Presentation and Manipulation Techniques for Geospatial Visualizations using Augmented Reality

Headworn display (HWD) augmented reality devices, such as the Magic Leap and HoloLens provide new opportunities to enhance interactive data visualizations. While immersive HWDs provide a straightforward way to render 3D and immersive visualizations, there are opportunities to improve 2D visualizations as well. This research program considers how 3D spatial metaphors enabled by AR can […]

Read More
Scalable System Services: Programming Practices and Tool Support

Scalable systems must seamlessly grow to absorb large data sets and incorporate increasing numbers of processing units within in various communication fabrics. Broadly considered, this concept applies to cores sharing memory, processors sharing a bus, nodes sharing a network in a grid/cluster/cloud, or services sharing compositions of components. Ironically, attempts to add more resources-whether they […]

Read More
Immersive Visual Analytics for Large Industrial Data

We investigate new possibilities for industrial data visualization and analysis with the latest Virtual Reality and Augmented Reality (AR/VR) technologies. In this cluster research, we will apply the state-of-art visual analytics methodologies to the forestry, manufacturing and mining industries, and evaluate the potential benefits for the newly introduced technologies. The research outcome may benefit industrial […]

Read More
Approximate Online Bilevel Optimization for Learning Data Augmentation

In this project we aim to automatically learn an augmenter network by using an approximate online bilevel optimization procedure. We plan to learn a augmenter network that generates a distribution of transformations that minimizes the loss on a validation set. By unfolding the gradients of the training loss, we will optimize the loss on validation […]

Read More
The virtual fitting of clothing to a custom avatar

The proposed research involves the development of software capable of fitting a piece of clothing to an avatar based upon customer measurements. The development would include the creation of avatar geometry from photographic information and the computer simulation of fabric based on physics. The project would also include interfacing with clothing merchants through the partner […]

Read More
Translational Oncology Research Data Analysis and Quality Assurance

The proposed project seeks to better understand and study the effective application of data processing tools and quality assurance systems in clinical research. Data from clinical trials is crucial in the pharmaceutical industry because it provides indicators of safety and efficacy of drug treatments for patients. However, processing and reporting on the large amounts of […]

Read More
Ground Truth

The goal of the project is to develop a predictive model that will help to make a better estimate of the relative altitude using only the barometer sensor inside the Notio device. This measurement of a precise relative altitude is crucial since it is used to compute the slope, which is an important data for […]

Read More
Detecting Attacks on Connected Vehicles

Attacks on connected vehicles require special attention and there is a need for new sophisticated security solutions that will cover the integration of different domains in connected vehicles and help proactively address potential threats to connected vehicles. The overall goal of this project is to provide various security solutions for integrity, access control, availability, and […]

Read More
Sectorisation géographique multivariable en pré-optimisation du Problème du Voyageur de Commerce avec fenêtres de temps

Le projet consiste à développer des algorithmes permettant de créer des secteurs pour les clients de Fastercom. Afin d’y parvenir, différentes méthodes de Machine Learning seront évaluées et implémentées. Cette création de secteurs permettra d’améliorer la performance des algorithmes de la compagnie en découpant le gros problème d’optimisation de tournées de véhicules en petits problèmes […]

Read More
Adaptive Information Extraction from Clinical Patient Records

Among the applications of computer science in the field of health care and biomedicine, the processing of clinical patient records is one of the increasingly important topics for improving the Electronic Health Records (EHR) systems. A practical use of EHR systems is to help improve the decision making process for the physicians. The goal of […]

Read More