Projets novateurs réalisés

Understanding Real-time Particle Systems for Health, Entertainment and VR

The proposed research is a collaboration between Persistant Studios’ PopcornFX and SFU’s iVizLab to collaboratively work on ways to understand the processes involved in content creation using a real-time particle system. The iVizLab’s research focuses on using real-time visuals with the biodata from the users as one of the main interfaces to create affective systems that can intelligently interact with the users. In creating the visuals for the iVizLab, it is important to be able to create content that can be modified in real-time with the incoming data. The intern will be working closely with the partner organization to work on understanding complex design processes and to break them down into simpler components to better understand the involved processes. Further, the intern will be working on ways to document these processes and share this with the community of PopcornFX users in the industry and world-wide.

Chaire de recherche industrielle dans les collèges du CRSNG en fabrication de composantes aérospatiales en matériaux composites

Ce projet vise à répondre aux besoins des industriels canadiens aérospatiaux d’aujourd’hui, spécialisés dans la fabrication de composantes en matériaux composites. Ces besoins ont été définis avec plusieurs PME et donneurs d’ordres, dont Bombardier Aérostructures et Services d’Ingénierie, Hutchinson Aéronautique et Industrie Canada, SphèreCo, Texonic, Lubricor, Génik et PCM Innovation. Ce projet se concentrera sur le développement de procédés de fabrication et de matériaux efficaces, afin d’augmenter la productivité, renforcer la compétitivité de l’industrie locale à l’échelle mondiale et ainsi rapatrier la fabrication de pièces composites au Canada. Dans un deuxième temps, ce projet permettra de combler le besoin criant en personnel hautement qualifié auquel l’industrie des composites fait face.
Effectuée partenariat avec le CTA, ce projet permettra également d’établir une synergie efficace et pérenne entre la recherche universitaire et collégiale.

Simplification of long sentences

The task of sentence simplification can present itself in multiple forms. It could consist in correcting the punctuation of a sentence like so:
Avant : J’ai acheté un bateau je l’aime beaucoup.
Après : J’ai acheté un bateau. Je l’aime beaucoup.
However, a sentence can be both long and written correctly. In this case, it would require a reformulation in multiple sentences like so:
Avant: J’ai acheté un grand bateau à la foire nautique qui a eu lieu à Montréal plus tôt cette année et j’ai pu l’essayer cet été dans les eaux du lac Massawippi lors d’un récent voyage dans les Cantons de l’Est.
After: J’ai acheté un grand bateau à la foire nautique qui a eu lieu à Montréal plus tôt cette année. J’ai pu l’essayer cet été dans les eaux du lac Massawippi lors d’un récent voyage dans les Cantons de l’Est.
The task should be accomplished using deep learning and has to work both in french and in english.

Preventing Risk for Metabolic Syndrome in Workaholics: An Intervention

Tendencies towards workaholism have been linked to poor health and increased risk for diabetes and other chronic condition. A health improvement program that is interwoven within the workplace and leverages the ubiquitous use of smartphones has good potential of benefiting the workforce. The aim of this research project is to evaluate Transform, a digital health program created by Blue Mesa Health. The program is designed to prevent diabetes by helping people adopt healthier lifestyles. More specifically, this study will look at the impact Transform has on weight, physical activity workplace performance and stress management. Blue Mesa Health seeks to develop a strong research portfolio on Transform in order to provide a high-quality intervention that is both effective and competitive. BMH has plans to begin serving Canadians in 2019. Establishing collaborative partnerships in the Canadian academic arena is valuable to the growth and success of the company.

Applied next generation AI accelerator algorithm hardware co-optimization: using quantization, sparsity and hardware constraints during neural net training

This work aims to explore software and hardware co-optimization for deep neural network (DNN) inference applications. Once a model is trained to sufficient accuracy, the model is used to make inference or predictions based on this trained model. With increasing performance, more people are using these models for tasks such as translation, self-driving cars and speech recognition. This has greatly increased the demand for high performance inference hardware. The goal for this project is to investigate novel techniques to reduce latency and power consumption during inference while maintaining the same model accuracy.

Link predicting in court

The company Lexum is an undisputed leader in the development of information retrieval tools for the law – statutes, regulations and decisions of courts and tribunals. The project is to improve a new tool offer by the company. The tool is used to retrieve a list of legal subjects from a factual description. With that list extract, the tool provides a list of potential related document.

AI to predict emergency visits

ClosedLoop.ai is an AI-based predictive analytics platform that goes beyond traditional claims-based risk scores to use all patient-related healthcare data to provide both clinicians and care managers with a full breadth of timely, transparent and accurate predictions of health outcomes. ClosedLoop.ai helps value-based providers confidently answer a variety of health-care questions like, which patients are most likely to be readmitted to the hospital? Or which of my patients would most benefit from establishing a relationship with a primary care provider? The objectives are to evaluate the performance of seven prediction models that answers these kinds of questions and to improve one of the seven prediction models by identifying and training a deep learning algorithm.

Power network transfer capability

Hydro-Québec is a public utility that generates and distributes electricity. Despite selling most of its electricity in Québec, its most lucrative sales are in the neighboring markets. To ensure the best possible quality of service, the transmission system must remain stable, but to maximize profits, the company also wants to increase its transmission capacity to maximize energy exports. The transfer limit is now conservatively estimated based on a certain combination of simulated network configurations. This project aims to more accurately estimate the transfer limits of the electric grid and the uncertainty of these estimated limits. Recent advances in machine learning, especially in deep learning, in conjunction with more traditional algorithms used in computer science, have the potential to improve these estimates and therefore augment exports for Hydro-Québec.

Probing Polycyclic Aromatic Hydrocarbons in Photodissociation Regions

Polycyclic Aromatic Hydrocarbons (PAHs) are a large class of complex organic molecules made of carbon and hydrogen that are ubiquitous throughout the space, accounting for up to 15% of the cosmic carbon. These molecules are made of fused benzene rings resulting in a honeycomb structure with hydrogen atoms at the edges of the molecule. They are typically observed through their characteristic infrared emission bands caused by fluorescence of PAHs upon absorbing UV photons. Emission from PAHs originate in the regions of the interstellar medium called Photodissociation Regions (PDRs) – regions where photons > 13.6 eV are absent. PDRs are characterized by their physical conditions such as gas density and the radiation field strength which are not uniform throughout the PDR. These variations in the physical conditions gets reflected in the properties of PAHs such as size, charge state and molecular structure. TO BE CONT’D

Satellite Solar Radiation Nowcasting

The main duty of Hydro-Québec is to repond efficiently to the energy demand of customers, in a safe and secure way while remaining competitive in the markets as well. The main goal of this start-up project is to support Hydro-Québec in developing a future-oriented energy system by proposing innovative technical solutions. Among these solutions, deep learning has been the final choice. Using a deep learning approach, satellite images, weather model outputs and data from solar radiation measurement stations, will be use for the development of a solar radiation nowcasting model. This project will have impact on several business functions related to: PV forecasting, demand forecasting, hydrology, etc.

The effects of Bisphenol A and Bisphenol S on cross-talk between primary human adipocytes and primary human muscle cells

Bisphenol A (BPA), and its analog bisphenol S (BPS) are synthetic compounds commonly found in plastic products, and chronic exposure has been associated with adverse health outcomes such as the development of insulin resistance and type 2 diabetes (T2D). Low levels of these pollutants can transfer from polymers to food or water and can accumulate in adipose tissue due to lipophilicity. Furthermore, adipocytes release hormones, such as adiponectin, that enable cross-talk with skeletal muscle. Therefore, we will investigate the effects of BPA and BPS on adipocyte metabolism and cross-talk with the skeletal muscle. Specifically, we will look at lipid and glucose metabolism primary human adipocytes treated with BPA and BPS. In addition, primary skeletal muscle cells will be exposed to the conditioned media of adipocytes treated with these pollutants, in order to investigate cross-talk between these tissues. TO BE CONT’D

Implementation of a prediction tool for the viscoelastic behavior of textile composites in the industry (Pratt and Whitney Canada).

This project consists in implementing a numerical tool that will be able to evaluate the

viscoelastic behavior of textile composites. The first step will be devoted to adapt the

numerical tools to adapt them to industrial requirements and preferences. Then, the tool

will be validated with the help of the operational knowledge of the industrial partner in

textile composites. Finally, the procedures for using this code will be documented. This

project is part of a larger Collaborative Research and Development project and is

therefore of considerable interest to the industrial partners.