Projets novateurs réalisés

Machine learning methods for automatic diagnosis, severity assessment, prognosis, and disease understanding of COPD

Chronic Obstructive Pulmonary Disease (COPD) is a progressive, debilitating, chronic respiratory disease that affects 600 million people worldwide and is responsible for 3 million deaths worldwide each year. Given the recent advances in artificial intelligence (AI) and the availability of large datasets from both the public and private sectors, our project applies AI to analyze large-scale medical datasets and develops tools capable of performing accurate diagnosis, severity assessment, and prognosis of COPD. Working in parallel, our project also aims to use AI to identify relevant biological markers that can predict current disease status and future progression. Ultimately, the tools developed and experimental results obtained throughout our research period will guide our partner organization in developing protocols for drug target discovery and validation, as well as therapy evaluation.

Projet de recherche : Etude de la relation entre pression artérielle à l’effort et performances cognitives

La préservation des fonctions cognitives constitue un enjeu majeur de santé publique au Canada dans un contexte de vieillissement démographique. Cette évolution s’accompagne d’une augmentation des maladies cardiovasculaires, souvent liées à l’hypertension artérielle, ainsi que des troubles neurocognitifs. Or, leur détection repose fréquemment sur des évaluations réalisées à des stades avancés, limitant les possibilités d’intervention précoce. Il est donc nécessaire d’identifier des prédicteurs simples, accessibles et fiables de la performance cognitive.

Plusieurs travaux ont montré que la rigidité artérielle (Joly, 2017) et la capacité cardiorespiratoire (Ahmadi & Mekari, 2024 ; Predovan et al., 2021) sont associées aux performances exécutives. Cependant, leur mesure nécessite des équipements spécialisés, parfois peu adaptés à la pratique de terrain.

Dans cette perspective, la pression artérielle à l’effort apparaît comme un indicateur particulièrement pertinent. Moins influencée par les conditions environnementales que la PA au repos (Lund-Johansen, 2002), elle a déjà été identifiée comme prédicteur du développement des maladies cardiovasculaires (Idzik et al., 2024 ; Schultz et al., 2026), elles-mêmes associées au déclin cognitif et à la démence (Harrison et al., 2014). Son étude représente ainsi une piste prometteuse pour identifier un prédicteur simple des performances cognitives.

Demande pour un projet de modélisation et analyse de la dynamique des écosystèmes forestiers face aux incendies

Les forêts canadiennes sont de plus en plus vulnérables aux incendies, sous l’effet des changements climatiques et des pratiques de gestion traditionnelles. Le projet Pyrosilviculture explore des approches de sylviculture adaptative pour améliorer la résilience des forêts face aux perturbations liées au feu.
L’objectif est de développer et tester des méthodes pyrosilvicultures capables de gérer efficacement la biomasse combustible tout en préservant les services écosystémiques et la biodiversité. Ces méthodes intègrent une gestion multi-objectifs pour évaluer l’efficacité des interventions sur la santé et la résistance des forêts.
Le projet mettra en place deux sites de démonstration au Québec pour tester, implémenter et suivre ces pratiques. Les résultats permettront d’évaluer comment la sylviculture adaptative peut réduire les risques d’incendie, optimiser la gestion de la biomasse et soutenir la durabilité des écosystèmes forestiers.
En combinant recherche appliquée et démonstration sur le terrain, la pyrosilviculture vise à fournir des solutions scientifiques concrètes pour des forêts plus résilientes et une gestion forestière innovante.

Model Application for Estimating Total Suspended Solids in Eastern Amazonian Waters

Suspended sediments influence water quality, ecosystem functioning, and navigation in rivers and coastal environments. In the Eastern Amazon, estuarine systems such as the Guamá River and Guajará Bay experience intense variability in suspended sediment concentrations due to the combined effects of river discharge and tidal dynamics. These processes produce changes in water turbidity and optical properties, making continuous monitoring challenging using field measurements alone.
This project aims to improve the estimation of Total Suspended Solids (TSS) in Amazonian coastal waters by integrating satellite remote sensing, in situ observations, and machine learning techniques. Multispectral satellite imagery will be combined with field-based TSS measurements to develop models capable of capturing the optical and hydrodynamic complexity of tide-dominated environments.
By explicitly accounting for tidal influence and optical variability, the project addresses key limitations of existing TSS monitoring approaches, which are often developed for river-dominated systems.
The results will include multi-temporal maps of suspended sediment distribution, providing valuable information for environmental monitoring, water resource management, and navigation planning. The project also strengthens international collaboration and develops transferable methods applicable to other dynamic coastal and estuarine systems.

Multi-Objective Optimization for path planning: Comparing MOAstar to MOACO, older adults case study

As populations age, many older adults face increasing difficulty moving safely and comfortably through their cities due to challenges such as limited walking endurance, steep slopes, poor lighting, and the need for regular rest. This project aims to improve pedestrian route planning by developing and comparing methods that generate routes adapted to older adults’ needs, considering factors such as distance, slope difficulty, and access to rest amenities. By testing these approaches on real urban environments in different countries, the project will contribute to safer, more comfortable, and more inclusive mobility for older adults. At the same time, it will strengthen the participating institutions’ expertise in intelligent transportation systems and data-driven urban mobility, support the training of highly qualified researchers, and advance research on inclusive, age-friendly mobility solutions.

Developing a User-Friendly Digital Platform for Coastal and Conservation Guardian Volunteers

This project will be conducted in collaboration with Island Nature Trust (INT) to develop a user-friendly digital platform for volunteers in their Coastal Guardian and Conservation Guardian Programs. Currently, the organization faces an innovation challenge in coordinating and supporting a geographically dispersed network of volunteers, many of whom have limited technical experience. Also, existing processes for scheduling, training, data collection and communication rely on multiple platforms and manual updates. The new platform will centralize these functions into a single, accessible hub where volunteers can access training materials, submit surveys, share photos, coordinate schedules, and view interactive maps highlighting priority sites. By streamlining volunteer engagement and program coordination, this project strengthens community participation and improves conservation outcomes.

Lowering Costs in Biotherapeutics: Raman Spectroscopy for Real-Time Antifoam Detection in Perfusion Bioreactors

This project aims to improve the production of monoclonal antibody (mAb) based medicines by developing a novel method for measuring antifoaming agents within perfusion bioreactors used to produce mAbs. Antifoams are necessary to keep bioreactors running smoothly, but they are also widely believed to contribute to reactor membrane fouling, which increases costs and severely limits how long these manufacturing systems can operate. During the placement, the intern will work with the host institution to develop and validate a Raman spectroscopy–based method to measure antifoam concentrations in real time, then bring this method back to the home institution for use in ongoing perfusion bioreactor research. The project benefits the host institution by applying its advanced analytical expertise to a new and practical manufacturing challenge, while the home institution gains new analytical tools, trained personnel, and transferable methods that strengthen its continuous biomanufacturing research capacity. Together, this collaboration supports more efficient bioprocess development and contributes to long-term improvements in biologics manufacturing research.

ML-optimization of tensor contraction operations (TCOs) in the PyBEST software package

The main goal of this project is to integrate advanced machine learning techniques into the open-source PyBEST quantum chemistry software package to substantially accelerate quantum chemical calculations through the automated selection of optimal computational strategies. The project specifically targets the AI-driven optimization of tensor contraction operations (TCOs), which constitute the primary computational bottleneck in many quantum chemistry methods. By enabling data-driven prediction of the most efficient contraction schemes and execution pathways across different problem sizes and hardware configurations, the proposed approach will significantly reduce time-to-solution, enhance scalability on modern GPU architectures, and improve computational resource efficiency, while preserving numerical accuracy and scientific reliability.

NouLife: Synthesis of Linked Conjugates

In 2023, Innovotech acquired a 60% interest in NouLife Sciences Inc., a company that developed the intellectual property for the linking of two antioxidant molecules commonly used in skin care products – alpha lipoic acid and acetyl-L-carnitine – into one molecule. The linking of the two molecules has been indicated by NouLife to increase the beneficial properties of the separate molecules by improving their penetration through the skin, thus promoting antioxidant activity and improving overall skin health as a result. Innovotech used the intellectual property to create three different conjugated molecules, and the next step is to confirm that the linking of the molecules provides more effective antioxidant activity in skincare applications, focusing initially on permeability, solubility, and antioxidant properties. This testing of the linked molecules will seek to confirm that the linkage itself significantly improves the function of the molecules with respect to skin treatment so as to encourage their use in nutraceutical and cosmetic applications. The proposed project is to work with collaborators at the University of Alberta to synthesize the additional quantities of the conjugated molecules needed for the next phase of testing.

L’origine leibnizienne du principe de la moindre action

Ce projet vise à rechercher dans la dynamique de Leibniz une nouvelle compréhension de la notion d’action de Maupertuis qui pourrait, croit-on, résister aux critiques des commentateurs qui ont suggéré que la quantité d’action est définie par Maupertuis de manière ad hoc et réhabiliter la preuve métaphysique de Maupertuis. J’avance l’hypothèse selon laquelle l’action de Maupertuis est une notion métaphysique qu’il est possible de préciser mathématiquement par l’usage de principes métaphysiques adéquats, de la même manière que Leibniz le fait dans Dynamica de potentia.

Scheduled Tandem Parking to Relieve Parking Demand at Commuter Organizations

This project develops and validates a tandem parking simulation and operating framework for large commuter organizations such as hospitals, universities, and municipal complexes facing persistent parking shortages. Conducted in partnership with pointA, a non-profit supporting sustainable commuter programs, the study explores how assigning two vehicles to a shared stall can safely and reliably increase effective capacity without new construction. Using shift-based data, stochastic modeling, and discrete-event simulation, the PhD intern will test pairing rules, buffer times, and participation rates to quantify utilization gains and blocking risks. The outputs—a simulation model, operational handbook, and planning guidelines—will provide evidence-based insights for future pilot implementation, helping organizations expand parking efficiency, reduce congestion, and improve access within existing footprints.

How Generative AI Changes Problem Solving in Software Development

Use of generative artificial intelligence (GenAI) has skyrocketed in software development. Although gains in workers’ productivity have received significant recent attention, little is known regarding the deeper long-term effects of these tools. Researchers from the University of Victoria, Canada and the University of Zurich, Switzerland are conducting an experimental study to evaluate the potential risks the technology poses to the critical thinking skills of software developers. The results of their research will help ensure GenAI is responsibly integrated into software engineering education curriculum at the participating institutions, and beyond benefiting mentors in the field, inform individual software developers.