Modèles d’apprentissage automatique pour la prédiction des prix des transactions énergétiques du Parquet d’Hydro Québec

Une des grandes difficultés pour les négociants du Parquet des transactions énergétiques à Hydro Québec est de prédire les prix des transactions, vu la nature volatile de ces derniers. Plusieurs données sont disponibles afin de permettre aux négociants de choisir leur stratégie. Parmi ces données se trouvent des données météorologiques, les facteurs géopolitiques, l’offre et […]

Read More
Transactional Fraud Detection with Machine Learning

The rates of fraud attempts have been increasing dramatically since the beginning of the pandemic. Always trying to protect its members and clients, Desjardins is collaborating with researcher to improve the state of the arts in real time transactional frauds detection using sophisticated machine learning techniques.

Read More
Les déterminants de la coparentalité au Québec

Ce projet vise à mieux comprendre les facteurs influençant la façon dont les parents partagent les responsabilités en lien avec leurs enfants (relation de coparentalité) au Québec. En comparaison avec le reste de l’Amérique du Nord, le Québec présente une réalité particulière, avec un niveau élevé d’enfants dont les parents ne sont pas mariés toute […]

Read More
Research on EMI Impacts of a Paralleled GaN-based PFC

The proposed project will be a collaboration between the Ottawa (ON) based integrated circuit (IC) company, Power Integrations Inc. and RIGA lab at University of Manitoba. The objective is to reduce power losses and meet international industrial standards for Power Factor Correctors. The result of this research project will assist the company to identify the […]

Read More
Explainable Fuzzy Deep Neural Networks for Cyber Threat Attribution

Threat attribution is crucial to detect attacks as early as possible and understand how attacks will proceed and the likely scope. This project will propose an explainable fuzzy deep neural network for cyber threat attribution. We obtain transparency and explainability via extracting fuzzy rules from DNN for cyber threat attribution. Indeed, this model, via providing […]

Read More
AI Education Platform – Advanced Learning and Integrated Control for AI-Incorporated LEGO Robots

Recent advances in sensing, edge-computing devices (e.g., Raspberry Pi and Jetson Nano) and artificial intelligence (AI) techniques, especially deep learning (DL) models for computer vision and speech tasks, together have led to exponentially increasing AI applications in military, civilian and education scenarios. It is widely agreed that AI will be the driving force of the […]

Read More
Fairness-aware Matching for Dynamic Predictive Behavior Matching

Web-based chat services are widely used by millions of customers today. However, few of them satisfy both service providers and recipients (customers).For instance, customers are continually complaining about long wait times and inadequate service. The technical challenge is to keep both the customers and the agent happy. To solve these difficulties, we plan to model […]

Read More
Intersections of HIV and COVID-19 vulnerabilities and strengths among marginalized populations: A mixed methods study

The COVID-19 pandemic has severely affected communities that are already vulnerable to negative health, mental health, and economic outcomes, such as young people of colour and young sexual and gender minorities, including those at risk for and living with HIV. This project will train youth, age 18 to 25 years, from marginalized communities as collaborators […]

Read More
Neuro-inspired cognitive architectures for artificial metacognition and social learning

Since artificial intelligence will play a crucial role in our daily lives, it is important that, along with increased task performance, socially intelligent agents will be able to cooperate efficiently with humans. However, human social cognition is a recent evolutionary event that relies on an advanced cognitive architecture. While the unconscious brain, also referred to […]

Read More