Innovative Projects Realized

L’appréciation juridique du risque relatif aux cyberattaques dans les activités critiques

Dans notre monde automatisé et interconnecté, la cybermenace connaît une hausse spectaculaire, avec des attaques informatiques de plus en plus fréquentes et sophistiquées, y compris sur des infrastructures critiques. Ce projet analyse les risques causés par ces cyberattaques sur des secteurs d’activités indispensables à la sécurité et au bon fonctionnement de la société, tels que la santé, le transport, et l’administration publique. Qu’elles soient motivées par des raisons financières ou géopolitiques, ces attaques ont des conséquences bien réelles, comme l’interruption de services d’urgence et de services administratifs, la divulgation massive de données à caractère personnel et de données sensibles. Entre le droit et la cybersécurité, ce projet contribue à renforcer la protection et la résilience des systèmes d’information, y compris des systèmes d’intelligence artificielle, pour finalement mieux protéger les droits des citoyens. Il s’inscrit dans la coopération historique entre la France et le Canada sur le numérique, pour construire une réponse internationale face à ces nouvelles menaces et garantir un cyberespace de confiance.

Prédiction Personnalisée du Risque de Diabète

Le diabète de type 2 est une maladie chronique en forte augmentation qui touche des millions de personnes et représente un défi majeur pour les systèmes de santé. Il résulte de l’interaction de plusieurs facteurs, dont la génétique, l’état de santé, le mode de vie et l’environnement. Une détection tardive peut entraîner des complications graves, comme des maladies cardiovasculaires ou rénales.

Les méthodes actuelles d’évaluation du risque reposent principalement sur des questionnaires ou des mesures cliniques simples. Bien qu’utiles, elles ne tiennent pas pleinement compte des différences individuelles et offrent une prédiction souvent limitée. Les avancées récentes en intelligence artificielle permettent désormais d’analyser de grandes quantités de données de santé, mais la plupart des modèles existants utilisent un seul type de données.

Ce projet vise à développer un outil innovant basé sur l’intelligence artificielle capable de combiner des données cliniques, génétiques et comportementales pour estimer de manière plus précise et personnalisée le risque de diabète de type 2. En permettant une identification plus précoce des personnes à risque, cette approche contribuera à améliorer la prévention, à soutenir les décisions cliniques et à favoriser une médecine plus personnalisée, au bénéfice des patients et du système de santé.

Directional Sensitivity of the Proprioceptive Sense of Force

Normal movements are generated via controlled activation of motor units (MUs), which consist of motoneurons and their innervated muscle fibers. To support the wide range of movements humans perform daily, it’s been suggested that MUs are recruited and fire depending on the direction of applied force. The proprioceptive sense of force, which is the ability to accurately sense and reproduce a given force, is essential for successful movement, yet becomes impaired with aging, injury, or neuromuscular disorders, making everyday tasks difficult or impossible. Recent work has assessed how force sense changes with age and motoneuron excitability, however, these studies were limited to simple joint movements. Therefore, this project aims to analyze how multidirectional MU behaviours contribute to force sense, so that findings can be directly applied functionally, such as within rehabilitation programs. To do this, we will use high-density surface electromyography to record muscle activity from the deltoid during force reproduction tasks, where participants match forces in either the same or different directions. Data will be collected using an end-point controlled robotic arm attached to a load cell. The collaboration between the two laboratories will combine complementary expertise, strengthen a pre-existing partnership, and support future joint-publications and training opportunities.

Bridging Cognitive and Motor Reserve Across Cultures: Linking Lifestyle and Aging in Canada and Italy

This project will explore how balance-based physical activities such as tai-chi, yoga, dance, and martial arts may help protect memory, thinking, mobility, and overall brain health as people age. Although many studies show that lifestyle habits can support healthy aging, much less is known about how different countries measure brain and cognitive health in older adults. By bringing together researchers at Concordia University in Canada and the University of Padova in Italy, this study compares how different cultures assess and understand cognitive and motor aging. Using balance tests, cognitive assessments, and non-invasive brain-activity measures, this collaboration aims to identify lifestyle habits that support healthy aging and to develop more inclusive, culturally responsive tools for assessing brain health in older adults worldwide. Both institutions will benefit from this collaboration through the exchange of complementary expertise, with Italy contributing strengths in ecological neuropsychological assessment and Canada contributing experience in brain-activity and balance-based research. Ultimately, this partnership will strengthen international ties and support long-term advancements in aging science across both countries.

A Comparison of Supply Chain Liability Between Canada and the EU

As an advanced form of Corporate Social Responsibility (CSR), supply chain liability extends companies’ responsibilities along the Global Value Chain (GVC). Thus, top brands (the primary entities in the GVC) can be held accountable for the conduct of their suppliers (secondary contractors). For labour issues, Supply Chain Responsibility has the potential to center and enforce the needs of workers. Courts in Canada and Europe hold divergent attitudes toward supply chain liability. Nevertheless, in recent years, the EU and Canada have both endorsed supply chain liability regulations. They are the Corporate Sustainability Due Diligence Directive (CSDDD) in the EU and the Fighting Against Forced Labour and Child Labour in Supply Chains Act in Canada. This project aims to compare Canadian and EU approaches to supply chain liability, including their scope, enforcement and extra-territorial jurisdiction. Comparing the Canadian and EU approaches from the perspective of extra-territorial jurisdiction can fill a gap in the understanding of supply chain liability. My project will benefit Canada’s legislative approaches, companies’ compliance, and affected communities’ access to supply chain liability.

Applied AI Solution Development V2

This project aims to help Rogers Communications bring real-world AI and Generative AI (GenAI) solutions to life across Business units like Customer Care, Network, HR and Rogers Business. A team of five interns from the University of Waterloo will work with Rogers’ Data & AI Strategy team to turn identified promising use cases into working solutions. Their focus will be on building small-scale models (called MVPs), testing them with users, tracking their performance, and preparing them for wider use. Another intern will be specially allocated to work on AI governance at Rogers with the Data & AI Strategy team, developing enterprise AI governance frameworks. This project will speed up Rogers’ ability to adopt AI in a responsible and scalable way, while also giving students hands-on experience in a real business setting. Ultimately helping Rogers improve service, efficiency and innovation while training the next generation of AI talent.

Integrated Machine Learning Framework for Optimizing Residual Material Selection in Environmental Remediation

This project will develop an easy-to-understand and transparent machine learning system that helps identify the best residual materials to clean up environmental contamination, especially in areas affected by mining. Materials such as biochar, zeolite, dolomite, and wood ash are already known to help remove pollutants like heavy metals, phenolic compounds, acid mine drainage, and gases, but current research is scattered and often hard to compare. To address this, the project will bring together information from laboratory tests, pilot experiments, and long-term field studies into one organized dataset. Using this combined data, the intern will build machine learning models that can compare materials and recommend which option works best for a specific contamination scenario. The project will also include simple explanation tools to show why the model makes each recommendation and how confident it is in its predictions. Field data from the Abitibi-Témiscamingue region, where mining and forestry activities produce large amounts of residual materials, will be used to test and refine the system. By the end of the project, the participating institutions will benefit from a practical decision-support tool that improves environmental management, supports sustainable reuse of industrial by-products, and strengthens collaboration between research, industry, and local communities.

High temperature characterization and modeling of GaN transistors

This research project makes use of computer-based models in order to investigate the high temperature behavior of Gallium Nitride (GaN) power transistors. The GaN technology is finding more and more applications in different sectors like energy, transportation, and industrial systems due to the possibility of making power converters smaller and more efficient. The understanding gained from the project’s temperature effect study will be applicable to design and reliability of future power electronics, thus facilitating the development of new technologies. The partnership between the home and host institutions not only enhances the skill set in device physics, simulation, and modeling but also paves the way for more extensive joint research on advanced semiconductor materials in the long run.

Participatory Mapping for Assessing Social Cumulative Effects of Extractive Industries in Rio de Janeiro, Brazil

This project will explore how extractive industries, such as offshore oil and gas, have affected the Maria Joaquina Quilombola community in Rio de Janeiro, Brazil. Using participatory methods, such as community workshops and mapping, the study will document how the community has experienced social cumulative effects. The project seeks to enhance understanding and evaluation of these impacts on Quilombo communities, with the goal of improving assessment, monitoring, and mitigation strategies. More broadly, the study addresses the persistent neglect of social and cumulative impacts and offers a case study to inform best practices in impact assessment. Collaboration between Concordia University and the State University of Rio de Janeiro (UERJ) will strengthen research partnerships between Canada and Brazil, facilitate knowledge exchange on participatory assessment methods, and support future academic collaborations.

Check Fraud Network Detection Using Graph Neural Networks (GNNs)

(1) Partner Activities: Nasdaq Verafin is a global leader in financial crime management, providing advanced fraud detection and anti-money laundering solutions to financial institutions. The company processes millions of transactions daily, including check-based payments, to identify suspicious patterns and prevent financial crimes.
(2) Challenges: A critical challenge in check fraud detection is identifying sophisticated fraud rings that operate across multiple accounts and institutions. Traditional rule-based systems analyze transactions in isolation, missing network-level patterns where fraudsters use stolen or counterfeit checks systematically. Single-transaction analysis results in high false positive rates and fails to detect coordinated fraud schemes involving altered payees, check washing, and organized fraud rings.
(3) Anticipated Benefits: This GNN-based approach will provide Nasdaq Verafin with a powerful network-aware fraud detection capability, enabling identification of fraud rings and coordinated attacks that conventional methods miss. By analyzing checks within their relational context—incorporating image similarity, account relationships, and transactional patterns—the system will significantly reduce false positives while improving detection of organized fraud schemes. This innovation will enhance Verafin’s competitive advantage, strengthen its fraud prevention platform, and provide clients with more sophisticated protection against emerging check fraud tactics, ultimately reducing financial losses across the banking industry.

Intelligent OCR Routing System for Cheque Processing

(1) Partner Activities: Nasdaq Verafin is an industry leader in developing advanced anti-financial crime solutions, helping financial institutions worldwide detect and prevent fraud and money laundering through its sophisticated data analysis platform.
(2) Challenges: The primary challenges this project addresses are the significant operational cost associated with processing millions of cheque images for fraud analysis. Relying exclusively on premium, paid OCR services is expensive and not scalable. The previous project successfully created a system to mitigate this, and the challenge now is to evolve that system into a more intelligent and granular solution to maximize efficiency.
(3) Anticipated Benefits: The economic benefits for Nasdaq Verafin are direct and substantial. The initial research established a baseline demonstrating significant cost reductions in OCR processing by intelligently routing a large portion of images to open-source engines. This continuation project will deliver even greater savings by developing a more granular, field-specific routing system and a dynamic, machine learning-powered feedback loop for continuous optimization. This innovation will not only lead to further direct cost savings but also improve the scalability and efficiency of Nasdaq Verafin’s platform, strengthening its competitive advantage by making core services more technologically advanced and cost-effective.

Réseaux de neurones graphiques pour le routage d’énergie dans les réseaux électriques intelligents

This project aims to make power grids smarter and more efficient by using a type of artificial intelligence called Graph Neural Networks along with Deep Reinforcement Learning. Just like a GPS finds the best route for a car, our system will find the optimal paths for electricity to travel, especially from clean but unpredictable sources like solar and wind. This will help reduce energy waste, lower costs, and make the power supply more reliable for everyone. For the participating institutions, this collaboration creates a powerful link between Canadian and Algerian researchers, combining their expertise to produce cutting-edge research, train highly skilled students, and strengthen their global reputation as leaders in artificial intelligence and sustainable energy technology.