Energ-AI: Artificial Intelligence in Electrical Power Engineering

Classical engineering, referring to the three fields of civil, mechanical and electrical engineering, is currently based on traditional working methods. For example, the validation of plans is often done in paper version and the engineer must interpret photos and drawings manually, which introduces a risk of error due to the human factor. In addition, the shortage of labor in this area means that the economic potential of this industry in Canada cannot be exploited to its full value.

Enrichment strategy for cardiovascular clinical trials

Cardiovascular clinical trials try to demonstrate the benefit of a medication on populations where the number of participants with the targeted disease is very low. The low efficacy of treatment is partially due to the diversity of diseases and of the population. To improve the efficacy of treatment, it is necessary to improve the recruitment of participants that are at greater risk of the studied disease through a process known as “population enrichment”.

Analysis of concentrically loaded braced frame using continuous end plate

The project consists in developing a design procedure for beam-column-bracing connection using welded end plates. This type of connection is simpler to fabricate, however, at present, the design standards do not specifically provide for their design calculations.

Making cannabinoids in microalgae factories

Algae-C is a company specialized in algal biomass production. It enables on-site production of algae for a wide variety of sectors (aquaculture, nutraceutical, cosmetic and biofuel). To date, many fuels, pharmaceuticals and cosmetic products are extracted from plants. These valuable plant natural products (PNPs) are often produced in low quantities in plants and extraction methods can be long and expensive. Thus, there is much interest in metabolic engineering for developing microbial platforms to produce specific PNPs.

Association automatique entre symboles et textes dans des documents d’ingénierie

La plupart des documents d’ingénierie comportent des symboles pour caractériser les systèmes qu’ils représentent. Ils comportent également des annotations (identifiants, notes, spécifications) sous forme textuelle pour préciser certaines propriétés importantes ou identifier les composants. Si l’association entre les symboles et les composants est intuitive pour un expert humain, il en va autrement pour un ordinateur. Ce projet vise à permettre la découverte automatique de tels liens d’association par un ordinateur, en utilisant des techniques d’apprentissage automatique.

Seq2Hypergraph: Link prediction on knowledge graphs using relation conditioned Transformer Networks

Learning from relational data is crucial for modeling the processes found in many application domains ranging from computational biology to social networks. In this project, we propose to work on developing new modeling techniques that combine the advantages of the approaches found in two fields of study: Machine Learning (through graph neural networks and transformer networks) and Statistical Learning (through statistical relational learning methods).

Énergie transactionnelle et client participatif : portrait des initiatives extra-Québec

Partout à travers le monde, le marché de l’énergie se renouvelle constamment afin d’assurer une bonne efficacité et fiabilité. Qui plus est, des citoyens choisissent d’être plus proactifs et autonomes par rapport à leur consommation d’énergie en la produisant eux-mêmes (prosommateurs). Parmi les stratégies émergentes sur le marché, les échanges d’énergie en pair à pair (P2P), en communautaire et dynamiquement vers l’opérateur de réseau, qualifiés d’énergie transactionnelle se taillent une place importante, car elle permet aux clients de produire, emmagasiner et vendre sa propre énergie.

Development of a Proof of Concept for a System to Increase Success Rates of Organ Transplant and Donation Matches

Transplantation is the preferred treatment for patients whose kidneys have failed. There is an ever-growing gap between patients in need for a transplant and available donors. In response to this need, there has been an increase transplantation of donors who experienced circulatory determined death (DCD). However, many potential DCD donors fail to end up in transplantation.

Système aéroporté sans pilote de détection de cibles humaines dans l’eau

Le projet de détection et de reconnaissance de personnes sur une étendue d’eau permettra de minimiser les pertes humaines en intervenant le plus rapidement possible lors d’une situation d’urgence. Le temps de survie d’une personne à l’eau est très limité, sous certaines conditions quelques minutes et il varie en fonction du port de ceinture ou costume de flottaison, de la température de l’eau et de la condition physique de la personne. Il est donc crucial de retrouver rapidement les personnes dans une telle situation.

Metaheuristic Approaches to Feature Engineering and Model Architecture Optimization for Financial Time Series Prediction

Predictive modeling of financial data, especially trading activity or asset prices, is a very challenging task. There are a number of novel approaches to feature engineering, data preparation and model architectures that aim to mitigate some of the problems that arise from non-stationarity and other issues typically found in financial time series data.

Pages