Innovative Projects Realized

Applying Adaptive Bayesian Learning Model in the Fastest Change Detection of Mental Health Patients’ Category

In customized healtchare systems, the service providers tailor the health services based on the different types of patients. However, the actual type of a patient is hidden from the decision-maker. The observed signals form a partial picture that is an estimate of the actual state of the subject. The decision maker’s knowledge about the actual type of the patients can play an essential role in the performance of the tailored treatment and the patient’s satisfaction. We propose a stochastic control system to model the situation. We consider the joint monitoing and learning system in which all parameters are unknown. The objective is to detect a random change in the patient’s state while simultaneously learning about the system properties and parameters. The partner will benefit from participating in this project because they will be able to improve the participants satisfaction by implementing new algorithms and comparing it to benchmark results.

Scalable Multi-chain Graph-based User Profiling Framework for EVM-Compatible Blockchains

The ultimate level of privacy is a double-edged sword. On the one hand, it guards honest users’ private information; while benefiting criminals to perform fraudulent activities anonymously. Blockchain as a decentralized environment is not prone to this problem. Decentralization enables bad actors to conduct wash trading, money laundering, tax evasion, scam, and fraud, to mention a few. Previous studies only focused on detecting a limited set of fraudulent activities. However, the primary purpose of this work is to make a framework that facilitates building different types of forensic tools for all EVM-compatible blockchains. The project will be done in several phases, including labeling and classifying addresses using state-of-the-art Machine Learning (ML) and graph-based solutions.

Investigation of suitability and feasibility of home dialysis – An Evaluation to enhance capacity planning

Chronic Kideney Disease can require patients to undergo dialysis or transplantation as treatment options. Ontario Renal Network (ORN) is responsible for setting the strategic direction of services, their aim is to improve the quality of life of every patients. The project will try to define suitability criteria for home dialysis patients by analyzing historic patient data. Once factors affecting suitability are discovered, the success score for each patient can be developed. This analysis can then be applied to new incoming patients. This can then assist the ORN to allocate resouces more appropriately and also to test and set viable potential targets.

Fast quantitative magnetic resonance imaging of the brain using sparsity and low-rank image reconstruction constraints

Quantitative magnetic resonance imaging (qMRI) is increasingly used in research to map the microstructure and composition of the brain non-invasively. In contrast to conventional “weighted” MR imaging, qMRI requires the acquisition of several images with different contrast weightings. The data at each voxel is subsequently fit to a signal equation to extract features of the tissue. These quantitative maps can be compared directly across subjects and time points to detect subtle differences in tissue microstructure due to experience or disease.

While qMRI has many advantages, its translation to the clinic has been limited due to the long scan times. The objective of this project is to implement novel imaging acquisition and reconstruction techniques that will significantly shorten the scan time without compromising image quality. We will evaluate the result on image quality and qMRI reproducibility in a group of healthy controls scanned at the Montreal Neurological Institute.

An investigation of the Canadian government’s in-year financial tracking operations

The proposed project intends to make an evaluation of the Canadian public sector’s use of technology in budget tracking operations. The purpose is to make a recommendation on a technological “future state” to address the discovered shortcomings and to mitigate future operational failures, as well as evaluating the impact of adopting such innovative technology. The partner organization will benefit from interns approaching this research from a financial, technological, and business process perspectives, considering both existing and novel enterprise solutions. More specifically, the work will consider the merit of a purpose-built enterprise-grade databasing platform for in-year budget tracking operations that facilitates the communications between managerial and financial teams.

Recyclage et revalorisation des plastiques souples sans marché

Dans ce projet, on propose de développer des applications afin de recycler les sacs plastiques en fin de vie. Pour ce faire, des études seront menées afin de déterminer la composition de tous les sacs disponibles par un centre de tri afin de les transformer, seuls ou avec d’autres matières résiduelles, dans des pièces moulées. En particulier, on cherche ‘produire du mobilier urbain extérieur pour une rue commerciale d’environ 150 m dans le Géoparc mondial UNESCO de la ville de Percé qui servira de vitrine technologique pour des développements futurs. Ces résultats pourront ensuite mener à d’autres projets pour inclure une plus grande liste de plastiques à valoriser afin de les dévier des sites d’enfouissement et/ou de l’incinération dans un objectif de développement plus durable.

La généalogie au Québec et la révolution des données de masse : mobiliser des partenariats pour comprendre le passé

L’Institut généalogique Drouin (IGD) possède la collection de documents généalogiques la plus vaste au Canada. Une collection composée de plusieurs de millions de documents historiques de natures et de longueurs très variées. Bien qu’elle soit aujourd’hui entièrement numérisée, la majorité de cette collection ne peut malheureusement être intégrée dans les outils de recherche développés par l’IGD pour sa clientèle de généalogistes, puisque les documents ne sont ni transcrits ni indexés. Or, étant donné l’ampleur de la collection, la transcription manuelle des documents n’est pas une option réaliste.
Le stage vise l’exploration et la comparaison de différentes technologies de reconnaissance optique des caractères (ROC), dans le but d’en tester la viabilité pour la transcription de divers types d’archives et de documents historiques du Québec et des environs. Le logiciel Transkribus de reconnaissance des écritures manuscrites (REM), développé par la coopérative européenne READ-Coop, sera le principal logiciel testé, mais ses performances seront comparées avec celles d’autres logiciels de ROC et de REM, afin d’aider l’IGD à identifier les meilleures solutions technologiques pour transcrire et indexer sa collection.

Development of a novel, rapid tool for non-typhoidal Salmonella detection and risk assessment for poultry.

Salmonellosis is a significant concern to public heath. Salmonella contaminated food is the main source of human infections. Emergence of novel Salmonella serovars with increased pathogenic potential and multidrug resistance led the industry to look for better diagnostic tools for in-depth characterization of the organism. Moreover, rapid detection of Salmonella serovars prevalent in poultry industry is a timely necessity to prevent outbreaks and mitigate timely control and prevention measures. This research study proposes in-depth characterization of Salmonella isolates using Oxford Nanopore whole genome sequencing platform. Project data will provide rapid determination of serovars, antimicrobial resistance profile and virulent traits. A metagenomic approach will be developed and validated to detect the Salmonella serovars directly from diagnostic samples and eventually improve the overall turnaround time, as compared to the traditional culture method. The organization partner will be the main laboratory for the entire project. It will benefit by improving diagnostic workflows and strengthening the relationships with the poultry industry.

Les systèmes alimentaires territoriaux au Québec : enjeux, projets porteurs et vision commune

La crise de la COVID a mis en lumière, plus que jamais, l’importance de l’accès à une alimentation saine, locale et durable pour tous et toutes. Elle a aussi mis en lumière les actions d’une diversité de réseaux et d’approches ayant chacun ses forces et ses aspirations. Malheureusement, les synergies entre l’ensemble de ces initiatives tardent à s’organiser. Souvent l’arrimage entre des actions territoriales et des actions sectorielles ne se réalise pas. Pour accélérer les apprentissages mutuels et les collaborations entre les divers réseaux, quels sont les outils et les stratégies déjà existants et ceux à développer collectivement? Le projet du Forum sur les systèmes alimentaires territoriaux (SAT) permettra de réunir, concerter et mobiliser les acteurs en faveur de la mise en place de SAT partout au Québec et d’identifier des modèles et des stratégies porteurs.

Intelligent and Autonomous Monitoring of Peak Demand Avoidance in Commercial Refrigeration Systems

The utility service providers calculate the peak demand charges based on the highest level of power consumption that a facility uses in any interval (usually 15 mins) during the billing cycle. The peak demand charges in facilities such as supermarkets could represent nearly up to 40% of the total utility bill. In supermarkets, besides the building, refrigeration systems could potentially play a major role in affecting the peak demands. Traditional threshold-based load shedding rules are not effective in controlling the peak demand of the refrigeration system since tailoring the power demand solely due to the reduction of the peaks above a specific threshold could create new peaks with higher values in the future. To reduce the peak demands effectively, forecasting methods to estimate the power demand based on historical data and weather predictions and operational optimization methods to improve the power demand flexibility are required. The goal of this project is to develop highly accurate forecasting/optimization systems using neural networks and machine learning models to reduce the peak demands based on refrigeration systems and expand the capabilities of existing edge devices for autonomous decision-making.

Chemical nanosynthesis of laser filters for aviation applications

Protection from laser light has become increasingly important due to the proliferation of cheaper and more powerful laser systems, especially in regards to interference with aircraft operations. Laser attacks, otherwise known as laser illuminations can be serious safety risks for aircraft operations as it can cause temporary flash blindness or irreversible injuries to the eyes of the pilot during takeoff or touchdown. Such incidents are increasing at an alarming average annual rate of 63% over the past ten years. The goal of this project is to aid in the development of a platform thin film filter technology called metaAIR that can be adhesively applied on the inner surface of an aircraft’s cockpit glass window and block any laser beams of predetermined light wavelengths. Large-scale metaAIR films will be superior to existing inadequate laser filtering solutions and reasonably cheap to fabricate, providing passive, hassle-free laser protection.

Potential of seaweed to mitigate effects of ocean acidification on young oysters

As we burn coal and gas worldwide, excess carbon molecules are released into the atmosphere. The ocean absorbs much of this carbon through a process called ocean acidification (OA), which impacts the growth of marine organisms with shells and skeletons. This increase in oceanic acidity has ecosystem-wide impacts and threatens our global food security. Fortunately, algae have been shown to remove carbon from the ocean, providing us with a tool for OA reduction that is also a nutritious food source. Studies show that algae increase OA tolerance in organisms sensitive to acidity, such as single-celled plankton (foraminifera) and shellfish.
This proposed research project will examine the potential for sugar kelp, a widely consumed macroalgae, to increase OA tolerance in the Pacific oyster, a widely consumed shellfish. More specifically, the study will test whether growing sugar kelp in tanks with Pacific oyster larvae decreases the negative effects of OA on the larvae. The research will occur at Cedar Aquaculture Research and Development, where adult oysters will be held in flow-through tanks with ambient seawater before reproducing.