Projets novateurs réalisés

Evaluating the effectiveness of Central Coast BC fishery closures

This research evaluates the effectiveness of commercial salmon fishery closures in British Columbia’s Central Coast, where salmon populations have rapidly declined in recent decades. In response, the Canadian government closed several commercial fisheries, including the Central Coast chum gillnet fishery. While intended to support recovery, closures carry major socio-economic consequences. The project assesses whether the 2021 closure helped rebuild target and bycatch populations using statistical analyses of empirical data (e.g., catch, abundance, and socio-economic indicators). In collaboration with the Central Coast First Nations (through CCIRA) and the Wild Salmon Center, the intern will also apply bioeconomic modelling to simulate future management scenarios. This work supports community-informed, science-based recovery planning and equitable access to fisheries. The results will inform collaborative governance between First Nations and the federal government, modelling future scenarios where conservation goals are met while addressing the needs of local harvesters and communities.

Evaluating the effects of a virtual reality relaxation intervention for inpatients in forensic psychiatry: a multicenter clinical trial.

People hospitalized in forensic psychiatry require specialized care due to the complexity of their clinical profile. The risk of violent behaviour and the context of captive care bring challenges to the treatment. Virtual reality is one way of addressing these issues. Several applications have been developed and studied in mental health, notably to facilitate relaxation. It is well known that stress can contribute to violence, and that patients in detention are likely to experience distress. Yet no studies have been carried out specifically on virtual reality relaxation intervention for this clientele. The aim of this project is to evaluate the effect of a virtual reality relaxation intervention (VRelax) for people hospitalized on forensic psychiatry units. Specifically, we aim to determine whether the intervention can have a positive impact on distress, relaxation and coping skills. To achieve this, we will conduct a clinical trial involving patients (n = 81) hospitalized in two similar institutions in Sweden and Canada. The results of this project will contribute to our limited knowledge of the most effective treatments for forensic psychiatry patients. Virtual reality relaxation interventions could represent a low-intensity, resource-efficient intervention to improve the well-being of forensic psychiatric patients.

3D Data Capture and Cleaning Intern

This project will deliver a mobile, real time 3D data capture and inspection system for industrial augmented reality workflows. Leveraging recent advances in 3D Gaussian Splatting, we will implement a lightweight iPad Pro app that reconstructs surfaces with =?1.5?mm accuracy at 30?FPS. Captured point clouds will be automatically cleaned, meshed, and compared against CAD ground truth by an on device AI module, flagging deviations in under 200?ms. The result will reduce manual QC effort by up to 70?% for FabStation’s steel fabrication clients, while advancing Canadian leadership in XR, computer vision, and AI enabled manufacturing.

Improving International Student Success: Examining College Policies and Strategies for Recruitment and Employment Support in Ontario and British Columbia

This research project explores the challenges that international students face when studying and trying to find jobs in Canada, especially in public colleges in Ontario and British Columbia. Last year, the research team reviewed existing studies and policy documents to understand the broader issues. With this extension, the team will now speak directly with international students through interviews and focus groups to learn about their real-life experiences—particularly in light of new immigration and employment policies introduced last year. The goal is to better understand how these policy changes are affecting students’ success in school and their ability to find meaningful work after graduation. The findings will help the partner organization—along with colleges and policymakers—create better supports for international students and improve their employment outcomes in Canada. This project will also build stronger partnerships between researchers and community stakeholders to ensure international students are treated fairly and given opportunities to thrive.

Towards an AI-Driven and Intuitive Chat Interface for Generating Visualizations

As data analytics and visualization become indispensable across diverse fields, the complexity of datasets often hinders non-experts from effectively exploring and interpreting crucial insights. Yet, advances in artificial intelligence (AI) techniques, especially natural language processing (NLP), and visual analytics present an opportunity to close this gap by providing conversational approaches to data exploration. The goal of this research is to design, develop, and evaluate an AI-driven and intuitive chat interface for generating visualizations within the Engage Nova Scotia’s Quality of Life Analytics System. We lay the groundwork for achieving this goal by investigating how visual context and scaffolding can be integrated with a natural language interface such that individuals without detailed knowledge of the underlying dataset can generate useful visualizations and correctly interpret them. Specifically, we will design functional prototypes of chat interfaces showcasing different visual context and scaffolding strategies (e.g., interactive overviews, dynamic visual cues, progressive disclosure, etc.), conduct a comparative user study to assess the interfaces’ effectiveness, usability, and user experience, and offer practical recommendations based on evaluation findings. This work contributes to the democratization of data exploration by reducing technical and knowledge barriers for interactively generating insightful visualizations.

Real-time AI-Powered Cells Segmentation

Sanofi, a leading pharmaceutical and healthcare company, continues to seek highly qualified personnel to achieve the goals of incorporating machine learning into various processes, which will allow for optimal development of its vaccines. Sanofi has a critical goal of combining smart data, such as those obtained through image analysis and flow cytometric assessments with artificial intelligence to have a digital twin of every process in manufacturing. Appropriate cell segmentation practices are critical to performing optimal analysis of images and in performing flow cytometry. One key challenge is the need to collect and process inline and offline data to obtain target cell/cellular entities trends either directly or via inference for appropriate cell segmentation. This process can be resource intensive, inefficient, and prone to generating images that are difficult to interpret. Interpretation of the images using machine learning will foster better understanding of the data to reveal information on cell diameter, cell circularity, light phase and cell count. Overall, they will be incorporated into knowledge database as per harbingers of productivity or root cause of possible ailments in the process. This approach could be implemented across multiple business units of Sanofi, such as Speciality Care, General Medicines and Vaccines.

Soins de Vie Plus : un programme de sécurité des soins qui favorise l’autonomie des aînés à domicile grâce à l’intelligence artificielle

Le projet Soins de Vie Plus, porté par Equinoxe en en collaboration avec OROT, vise à offrir une solution de télésurveillance
intelligente permettant aux aînés de vivre en toute sécurité à domicile. Grâce à un système sans caméra, sans bouton et dispositif à porter sur soi, Soins de Vie Plus utilise des capteurs acoustiques avancés pour détecter, prédire et prévenir les événements à risque tels que les chutes, le déclin cognitif, les erreurs de médication et les infections précoces.

Cette approche proactive permet non seulement de réduire le risque d’hospitalisation et de prolonger l’autonomie des aînés, mais aussi d’améliorer la coordination des soins en fournissant aux proches aidants et aux professionnels des rapports réguliers sur l’état de santé des bénéficiaires.

Le projet s’inscrit dans une perspective d’innovation en santé numérique et de vieillissement en milieu de vie, en accord avec les objectifs d’envisAGE, MEDTEQ+ et AGE-WELL. Il vise à démontrer l’impact d’une telle technologie sur la qualité de vie des aînés et de leurs proches, tout en contribuant à alléger la pression sur le système de soins de santé.

Collaborative Underground Autonomous Ground Vehicles (AGVs) for Mining Logistics Tasks

This research project aims to develop and implement an advanced autonomous navigation system for ground vehicles in underground mining environments, coupled with an innovative intention signaling system to enhance human-robot interaction.
The project leverages cutting-edge research in mobile robotics, adapting techniques such as Spatial Augmented Reality (SAR) and advanced human detection technologies to the unique challenges of underground mining. By combining autonomous navigation with clear intention signaling, the project aims to significantly enhance safety and efficiency in mining operations.
This research has the potential to revolutionize underground mining practices, reducing human exposure to hazardous environments while optimizing resource allocation and operational uptime. The outcomes of this project could position Canada’s mining sector for sustained growth and competitiveness in the global market, while also establishing the industrial partner as a leader in mining automation technology.

Module d’analyse intelligente des documents de transfert d’entreprise

Hadaly optimise les processus de fusion et acquisition grâce à l’intelligence artificielle. Sa plateforme automatise l’organisation, l’extraction et l’analyse des documents transactionnels, facilitant ainsi les due diligences et accélérant la prise de décision.
Ce projet vise à résoudre la lourdeur des analyses documentaires dans les transferts d’entreprise. Actuellement, acheteurs, vendeurs et conseillers doivent examiner manuellement des centaines de documents pour identifier les risques et valider la conformité, un processus long et sujet aux erreurs.
Le module d’analyse intelligente structurera et indexera automatiquement les documents transactionnels, permettant une classification avancée et l’extraction des informations clés (clauses juridiques, indicateurs financiers, engagements contractuels). Cette innovation réduira le temps d’analyse, limitera les coûts et améliorera la transparence des transactions.
Sur le plan économique, le projet renforce la compétitivité des PME en facilitant leur accès aux marchés de la transmission d’entreprise. Sur le plan social, il contribue à la pérennité des entreprises en simplifiant les processus de relève et en sécurisant les transactions, un enjeu crucial face au vieillissement des entrepreneurs et au besoin croissant de succession.

Maximizing science return for time sensitive in-situ surface investigations at the lunar south pole with co-ordinated instrument operations through characterizations of landing sites of interest

This project’s research would aid planning of the Canadian Lunar Rover mission to the Moon’s south pole with the goal to maximize the science return of the mission. The lunar south pole is of interest to space exploration for finding water-ice that could be a resource for future exploration, but is a difficult environment to explore due to the extreme cold in darkness that can affect the rover and its instruments. Each lunar day/night can also last up to two Earth weeks, requiring 24-hour rover operations from Earth over the sunlit period. While a goal of the rover is surviving a lunar night, consistent operation plans determined pre-launch are needed to optimize the limited time, reduce idle decision-making time, and ensure consistency between working shifts. The proposed work would use newer datasets to map the landing sites and surrounding regions in greater detail than previously conducted and inform operational plans and science targets. The work would generate “recipes,” combinations/sequences of rover science instruments, to maximize the scientific return of observations based on the targets the rover expects to encounter: ground rubble; rocks; impact craters; permanently shadowed regions thought to trap water ice. The work would combine the findings of the mapping and instrument recipes to determine effective operations plans based on the planned rover traverses at the proposed landing sites for the rover mission. This work would greatly benefit the partner organization Canadensys Aerospace Corporation, the mission contractor, by aiding in the planning, return, and overall success of the mission.

High-Performance Activated Carbon for Energy Storage: Leveraging Hybrid Feedstocks of Bitumen, Biomass, and Plastic Waste

With the growing global demand for energy and the need for sustainable solutions, advanced energy storage technologies like supercapacitors (SCs) are becoming more important. SCs offer a balance between traditional batteries and capacitors, but their performance relies on high-quality electrode materials, with activated carbon (AC) being a promising option. However, current AC materials have limited physical and chemical properties, which are not suitable for SC, and are made from scarce resources, leading to supply challenges. This project aims to improve AC production by using abundant and underutilized resources like bitumen, biomass, and plastic waste, creating a cost-effective, high-performance AC with enhanced properties while promoting environmental sustainability. The goal is to scale up production, address AC limitations, and help Canada’s progress in its advanced material technologies for applications in energy storage from electronics to electric vehicles.

Les symptômes traumatiques et l’adaptation chez les personnes surveillantes-sauveteuses en lien avec les incidents et événements potentiellement traumatiques en contexte aquatique

Les personnes surveillantes-sauveteuses sont formées par la Société de sauvetage au Québec afin de prévenir et d’intervenir en lien avec les incidents et traumatismes dans un contexte aquatique. Leur mandat en est d’abord un de surveillance et de prévention. Elles sont aussi formées pour intervenir lors de situations liées à la noyade et aux autres incidents et traumatismes pouvant avoir lieu en contexte aquatique. Ainsi, dans le contexte de leur travail, elles sont à risque d’être confrontées à des événements potentiellement traumatiques (Rooke et de Terte, 2024) et en ressentir des répercussions sur le plan de l’adaptation et des symptômes. Ce projet vise à identifier les meilleures pratiques pour la prévention des symptômes traumatiques chez les personnes surveillantes-sauveteuses. De plus, ce projet permettra d’identifier les facteurs associés à l’adaptation et la croissance post-traumatique après un événement potentiellement traumatique dans un contexte de surveillance aquatique chez les personnes surveillantes-sauveteuses.