Projets novateurs réalisés

Optimisation des processus T.I. pour la Ville de Trois-Rivières

L’administration de la Ville de Trois-Rivières se compose d’environ 1 300 employés dévoués à un objectif commun ; offrir des services publics de grande qualité aux Trifluviens ainsi qu’à leurs employés tel qu’une meilleur mobilité du personnel de bureau en mode hybride, une meilleure approche des temps de déplacement véhiculaire sur le réseau routier de la ville et le développement de solution logicielle.

C’est pour cette raison que la Direction des technologies de l’information souhaite saisir cette opportunité afin d’avoir le personnel qualifié pour participer activement à la transformation technologique du monde municipal, le tout, décliné en cinq projets permettant d’optimiser les services de la ville.

Advance Machine Learning for Medical Survival Analysis

In this Mitacs Cluster project, we aim to investigate and improve performance of deep survival models developed by Ortho Biomed Inc., our industrial collaborator. The main objective is to predict clinical outcomes, such as time of death, and the time of organ failure before and after surgery, more accurately and more efficiently. Architecturally, Ortho Biomed Inc. has developed two Deep Neural Network (DNN)-based model types, One2Seq and Seq2Seq, where the former (the One2Seq model) can accept one observation per patient. The Seq2Seq model, on the other hand, can accept longitudinal observations, i.e., multiple observations over time per patient. The outputs of both model types are interpretable and can be a probability distribution function (PDF), regression value, or binary occurrence of an event. Because of superior performances and interpretability of their models over other state-of-the-art solutions, Health Canada selected Ortho Biomed Inc. to build a prototype product. However, the company targets further improving performance of their underlying models using recent advancements in DNN architectures.

Realistic Synthetic Dataset Generator

The goal of the project is to assess the viability of current synthetic data generation systems. If the generated synthetic data is accurate enough without providing sensitive details it can be used to train machine learning models without needing to share sensitive information. The particular application of this project is to computer logs which can contain sensitive information about the computer systems themselves or the individuals using them. If synthetic data can be generated accurately, it could be used to generate more accurate anomaly detectors Arctic Wolf may be able to implement in their monitoring suites without needing to put the data subject’s privacy at risk.

Tourisme en Mauricie : diagnostic de la durabilité des activités

Dans un cadre de développement durable (DD), le tourisme doit être équitable sur le plan économique, viable sur le plan écologique et bénéfique pour les populations locales. La région de la Mauricie renferme une importante variété de paysages et d’offres de produits touristiques par rapport aux autres régions du Québec. Selon Tourisme Mauricie, il y a un manque de connaissances sur le tourisme durable (TD). Ce stage postdoctoral vise principalement à poser un diagnostic de la situation du TD en Mauricie en s’appuyant sur les outils de la Chaire éco-conseil : Grille de priorisation des cibles des Objectifs du DD, Grille d’analyse de DD et gestion des gaz à effet de serre. Ce stage contribuera à approfondir la connaissance et la place de cette activité en Mauricie et déterminera les actions à entreprendre face aux enjeux écologiques, sociaux, culturels, économiques, éthiques et de gouvernance que rencontrent les entreprises touristiques.

Textile-based immunosensors for sweat biomarkers: A case study for measuring cortisol

The portable user friendly devices can help us monitor our health status without any need to refer clinics. This capability is good to timely and efficacious medical interventions. This project aimed at realizing this device by making the key component involved in recognizing the biomarkers. We will synthesize the component at first using available inexpensive materials to reduce the production cost of the device and then will test different physic-chemical and biological factors so as to make sure that the results of the tests by this device are correct and indicator of real health status independent of any external interferences. The device should also be mechanically and chemically stable to be used for a long term usage.

Characterizing and Optimizing polyurethane cementitious composite mixtures

In industrial areas like manufacturing units, logistics centers, and warehouses, floors are exposed to heavy traffic along with high mechanical loads and possible chemicals contact. This promotes the use of polymeric cementitious flooring compositions such as epoxy resin-based flooring compositions and polyurethane (PU) cementitious systems. The latter showed outstanding mechanical properties and do not suffer from the drawbacks associated with epoxy resin-based compositions. PU system is composed of two different binding systems: polyurethane (diisocyanate) binders and hydraulic binders. This resulted in a very complex system wherein during curing of the components of two binders, a number of reactions occur simultaneously. However, some undesirable cross interactions between the two systems (such as isocyanate compound reaction with water) may jeopardize superior performance. Hence, the proposed project aims initially to fully characterize the main composition for PU flooring products. This will be followed by evaluating fresh and hardened properties under laboratory and simulated filed-like conditions. Based on the primary results potential improvements to overcome drawbacks and defects will be proposed and examined.

Regulation of granulosa cell autophagy and estradiol production by microRNA in the pig ovary

Fertility improvement is important in both human being and livestock industry. Increasing the oocyte competence is one of the most critical measures for fertility improvement. miRNAs are small non-coding RNAs which can regulate the estrogen production in the ovarian follicles which in turn affecting the oocyte development and competence. However, its underlying mechanism remains unknown. In this project, we hypothesize that miRNAs might affect the cell autophagy, a physiological activity that cell converts those redundant or damaged components to nutrient units which can be used to synthesize survival-related critical proteins. Uncovering this mechanism providing us a new target to improve oocyte competence which is of great significance to both humans and animals.

Development of the Next-generation Automated Mobile Recycling System

Mobile recycling, as part of efforts to help reduce the greenhouse emissions, is a novel type of recycling type emerged in recent years. The U-Cycle automated mobile recycling system located in Newfoundland and Labrador is a typical paradigm. This research project focuses on developing methodologies for multiple modules for the next-generation mobile recycling, including mechanism, power system, hardware and software, and human-machine interaction, by means of improving the U-Cycle system. Based on extensive research experience in robotic system design and the close collaboration with our partner, the proposed system is expected to showcase significant advantages in providing reliable power supply, sustainable mechanism, advanced human-machine interaction and remote management, that can promote widespread applications of such systems.

Innover en phytotechnologie afin de végétaliser les sols d’argiles en milieu riverain

Afin de limiter la dégradation des sols, fortement accélérée par les activités humaines, T2 Environnement, une entreprise de services et conseils en environnement, souhaiterait poursuivre ses efforts en recherche et développement dans ce domaine afin de générer et proposer des solutions innovantes pour ses clients dans le respect de l’environnement. Ainsi, ce projet a pour objectif de raffiner les techniques de végétalisation via une implantation localisée et la sélection d’espèces végétales adaptées, afin de pallier aux défis de la croissance racinaire dans les sols d’argile et permettre au sol et à l’écosystème riverain de se régénérer. Que ce soit dans une optique environnementale, économique, ou simplement à des fins esthétiques, la végétalisation des rives à l’aide des phytotechnologies, c’est-à-dire à l’aide de végétaux pour résoudre des problèmes environnementaux, représente une option verte, durable et efficace.

Maximizing the information transfer rate of a textile-based myoelectric interface

The electrical activity of muscles can be recorded from the skin and used to control external devices. Advances in this technology have the potential to allow a broad range of users with disabilities to control assistive technologies. This project will develop a system that uses sensors embedded in garments to measure muscle signals, and artificial intelligence to personalize how those signals can best be used to control assistive technologies for a given person’s pattern of muscle weakness after spinal cord injury. The intern will be responsible for developing and testing artificial intelligence algorithms, while the partner organization will develop the textile sensors. The activities undertaken in this project will result in sensors that can be used in a variety of applications and thus have broad benefits for the partner organization’s activities.

Identification of Cost-Effective Recycling Strategies for High-Performance Thermoplastic Prepreg Production Waste

The use of composites in transportation vehicles has been increasing for many years without a proportional response in the commercialization of recycling technologies to deal with this composites waste. Most of the waste generated during manufacturing and end-of-life is currently either landfilled or incinerated. Governments around the world recognize that such practices represent an obstacle in the effort to mitigate climate change and have, therefore, started implementing legislation such as the European Waste Framework Directive to promote waste reduction and recycling. The proposed research focuses on identifying recycling strategies for high-performance thermoplastic waste generated by the material supplier Teijin. Engineering and economic tools will be used to guide research and ensure the recycling solutions developed are technologically and economically viable. Cost-volume-profit analysis will be used to select promising combinations of waste material, recycling technology, and application. Thereafter, experimentation and process simulation will be used to develop the down-selected strategies.

Synergistic Effects of Psychological Risk Factors in Child and Youth Anxiety

Individual risks of anxiety are multi-dimensional such that multiple combined risks (biological, cognitive, and social risks) influence the susceptibility of anxiety. This research aims to explore individual risk factors that may increase the susceptibility of anxiety in a clinical sample of children and youth. From this study, we may develop a long standing partnership with Pathstone Mental Health. It is our mission to bridge the gap between academic and applied clinical research, with the hope to apply some of our findings to the partner organization to indirectly benefit participants and their families, and to assist in the pursuit of mental health treatment and prevention of anxiety.