Innovative Projects Realized

« Lieux de mémoire » et transmission aux générations futures : une perspective archéologique. Études de cas sur des sites autochtones et euro-canadiens au Québec

Ce projet s’intéresse aux « lieux de mémoire » au Québec. La transmission volontaire d’une mémoire et d’un héritage par les populations passées aux générations futures crée des sites archéologiques particuliers, dont les traces sont délibérément conçues pour traverser le temps.

La découverte en 2023 d’une « capsule temporelle » dans le « monument Price », obélisque construit à Chicoutimi en 1881 en hommage à la famille Price à la tête de la compagnie du même nom, active dans le commerce du bois, des pâtes et papiers, est un double exemple de ces « lieux de mémoire » québécois ; à la fois par le monument lui-même et par la capsule temporelle qu’il renferme. Bien qu’un engouement se développe au XIXe siècle pour les capsules temporelles, les « lieux de mémoire » peuvent prendre des formes multiples et préexistent à la colonisation du Québec. Par l’art rupestre, les Premières Nations ont volontairement marqué la pierre. Ce mode d’expression symbolique ancestral est présent partout dans le monde sous différentes formes ; et contrairement à l’art pariétal en grotte, les sites d’art rupestre du Bouclier canadien sont bien visibles en pleine lumière.

Smartphone-Based Quantification for Rapid Lateral Flow Assay Interpretation Using Advanced Image Analysis

A quick and simple, point of care test is being developed to detect traumatic brain injuries using saliva samples. The prototype test uses biotechnology to measure the presence of certain protein markers of injury, resulting in a change of colour and/or location of colour in the test material. The interpretation of the results can be variable, depending on the user. Therefore, an imaging system using smart phones will be developed to standardize the detection and interpretation of the results and reduce user variability. This project will develop the image processing capabilities and validate its performance on laboratory test samples.

Waterlogged Robotics sensor platform

“THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW”

LuCID Dryer Process Optimization

The project concentrates on MEMS (Micro-Electro-Mechanical Systems) fabrication process optimization. MEMS devices comprise suspended structures, such as cantilevers, gyros, membranes, etc., which are created by removing sacrificial material around them in order to have these structures released to perform their designated function. Currently, these structures are being released with the use of either dry etch or chemical vapor techniques. Wet chemistry release of suspended structures is favorable: minimized costs, parallel process and most importantly reduced impact on the environment. Challenge in achieving successful release using wet chemistry is the stiction of these structures to substrate or other parts of the device drying step at the end of wet chemistry process. State of the art equipment located in C2MI facility allows use of wet chemistry process followed by chemical drying in order to prevent stiction of these structures. Hence, design and optimization of this dry sequence will minimize significantly MEMS devices manufacturing costs and environmental hazards.

Adaptation du protocole de l’Indice de Biodiversité Potentielle dans les forêts boréales mixtes du Québec

Pour évaluer le succès des pratiques d’aménagement durable des forêts au Québec, il est nécessaire d’avoir accès à des outils de diagnostic non-seulement efficaces en termes de qualité des données récoltées, mais aussi facile à appliquer sur le territoire. Pour l’évaluation de l’impact de l’aménagement sur la biodiversité, les outils actuels manquent toutefois soit de précision, soit sont trop demandant en temps et en moyens pour pouvoir être utilisés de manière significative. L’objectif de ce projet est donc d’adapter le protocole de l’Indice de Biodiversité Potentielle (IBP) pour les forêts boréales mixtes du Québec. Ce protocole permet un diagnostic rapide de la qualité et de la diversité des habitats forestiers (par exemple le bois mort, les arbres habitats ou les milieux humides). Il a démontré son efficacité et sa facilité d’application dans les forêts européennes, mais il n’a toutefois jamais été utilisé en Amérique du Nord ou dans des forêts boréales, y compris en Europe. Nos objectifs sont donc d’adapter les seuils de l’IBP au contexte des forêts boréales mixtes du Québec pour discriminer efficacement les forêts à haute valeur écologique, ainsi que d’évaluer si les données de télédétection peuvent permettre de prédire les scores d’IBP des peuplements forestiers.

Leak Detection and Localization in Water Distribution Networks Using Machine Learning

Water distribution networks, which provide clients drinking water, are prone to leaks. Leaks are a critical area of concern, as they cost billions of dollars each year, and can allow water-born pathogens into drinking water, which is a public health concern. Current leak detection methods are very labor intensive, as many of them require experienced operators, or require surveys to be filled out. In contract, Digital Water Solution’s hydrant.ai is a device that can be installed on fire hydrants, which, listens to these water networks using hydrophones, which are similar to microphones, but are designed to work well underwater. This research project will study the performance of these devices in detecting and localizing leaks across pipe networks that vary in shape. Further, a leak detection and localization algorithm will be developed, which will leverage recent advances in artificial intelligence and machine learning.

Effet des éclaircies précommerciales et commerciales sur la sévérité des feux dans les forêts boréales conifériennes de l’Est du Canada

En 2023, les feux de forêt au Québec ont brûlé plus de 1,5 million d’hectares dans la forêt aménagée. La communauté forestière a été particulièrement surprise que ces feux aient touché principalement des forêts jeunes issues de coupes. Jusqu’à présent, les connaissances sur les incendies se concentraient sur les paysages naturels dominés par les vieilles forêts. Cependant, la faible occurrence des feux au Québec dans les dernières décennies a pu masquer les interactions entre l’aménagement forestier et le risque d’incendie.
Avec l’augmentation prévue des feux en raison des changements climatiques, il est urgent de déterminer si les feux de 2023 sont une exception ou si les pratiques forestières augmentent ce risque. Ce projet se concentre sur l’impact des éclaircies précommerciales et commerciales dans les forêts de pin gris et d’épinette noire. L’objectif est d’évaluer si ces pratiques, qui visent à favoriser la croissance des arbres, réduisent ou augmentent le risque de feu. Les résultats permettront de guider les gestionnaires forestiers pour renforcer la résistance des forêts boréales face aux incendies.

Software Bug Detection using Federated Learning Models: A Comparative Study

This research aims to advance the field of federated learning by addressing privacy, domain shifts, and personalization challenges, particularly in the context of mobile and digital healthcare. By developing robust and scalable solutions, the proposed framework has the potential to significantly enhance patient care, diagnostics, and personalized treatment while maintaining stringent privacy standards

L2M – Link Between Worlds

The Link Between Worlds is a project that focuses on bringing creative expression to peoples and communities that typically are not given a voice. The objective of The Link Between Worlds is to create sustainable and repeatable film creation opportunities for Indigenous people to grow and learn skills in the film industry, creating an outlet for job creation, entrepreneurship and healing through storytelling. In addition to learning how to bring a film to life creatively, we will teach the business of filmmaking through completed projects that will be brought to the marketplace with ownership as well as a potential financial source of income and repeatability. The partner organization will benefit directly through association with this project as it supports awareness and support through the current matter of Truth and Reconciliation.

L2M – Video based movement analysis

I am transforming the smartphone into a portable lab. The goal is to unlock a wealth of movement data that can be used for health and performance metrics. My business aims to democratize access to lab-quality movement data, making it accessible from the comfort of your home. This work will contribute to the overall field of sports sciences and benefit the partner organization with new technology.

Hydrogen supply chain design

The research focuses on designing and optimizing hydrogen supply chains (HSC), from production to consumption, to enhance the flexibility, efficiency, and cost-effectiveness, contributing to the global energy transition towards renewable sources. The project will develop and refine mathematical models, validate these models with real-life data, and integrate sustainability metrics to ensure environmental and economic viability. The project will foster interdisciplinary and international collaborations by coupling expertise about supply chain analytics and optimization with hydrogen production with experts from École de technologie supérieure (ÉTS) in Canada and Universidad de La Sabana in Colombia. The project is expected to significantly contribute to clean energy goals worldwide, enhance innovation capacity, and provide valuable insights into the logistics and efficiencies of hydrogen supply chains.

External Validation of MERCI, a machine learning algortihm for the early detection of retinal toxicity.

Chronic diseases incur a significant socio-economic cost to both patients and the health care system. Physicians must continuously monitor and modify therapies to best meet the patients’ changing requirements, often requiring regular health care visits for specialized testing.
Hydroxychloroquine (HCQ) is a disease-modifying antirheumatic drug often prescribed to patients with chronic inflammatory diseases such as rheumatoid arthritis and systemic lupus erythematosus (SLE). HCQ is generally safe but can occasionally cause sight threatening damage to the eye. It is recommended that patients treated with HCQ receive annual eye care appointments with a battery of specialized testing including visual fields, optical coherence tomography, retinal imaging and multifocal electroretinography.
We developed “The Multifocal Electroretinogram Classification Interface (MERCI)”, a machine learning approach to automate the identification of patients at risk of vision loss due to HCQ. By establishing and maintaining an open, accessible and sustainable archive of high-quality bio-specimens and rich annotated clinical data from diverse clinical populations recruited from multiple centers across Canada, this proposal will validate the performance of the MERCI algorithm and support it’s uptake as a clinical tool.