Innovative Projects Realized

Design and Development of a Chatbot-based Personalized Healthcare Tool to Support People with HIV

Large language models (LLMs), AI systems trained on vast amounts of online textual data with advanced language processing capabilities, have garnered significant interest in healthcare applications. Health chatbots integrate language models and various algorithmic tools to assist in decision-making, potentially revolutionizing patient self-management and reducing disparities in healthcare access.
However, previous work has shown notable threats to the equitable global deployment of LLMs. These include their tendency to perpetuate racial and gender bias through stereotype-laden responses and their variable performance across groups. For example, Hispanic and Black descriptors are most likely to alter judgments about relevant LLM outputs. Thus, it is critical to assess how LLM-based chatbots propagate existing biases that may amplify health disparities.
Using the retrieval augmented generation technique and an agentic workflow approach, we developed the LLM-based MARVIN chatbot for multiple health conditions, including HIV. MARVIN also integrated a triage algorithm to detect medication adherence barriers. This project will conduct bias/equity-related validation tests on MARVIN implementing the triage algorithm, including assessing gender, cultural, racial, and socioeconomic biases, as well as the chatbot’s performance in different languages. This will help ensure equitable implementation of LLM-chatbots based on LLMs, thereby advancing the development and implementation of human-centered health AI products.

Large deformation finite element modelling for benchmarking stability analysis of sensitive clay slopes

The proposed research project aims to address the significant natural hazard of large-scale landslides in sensitive clays, which can cause substantial economic loss, environmental disaster, infrastructure damage, and fatalities. The partner organization, WSP, specializes in geotechnical engineering services, including geohazard assessment from landslides and slope failure. This project will explore the applicability of advanced large-deformation finite element (FE) modeling techniques to better understand and solve the complex process of landslides in sensitive clays, particularly in regions like eastern Canada and Scandinavian countries. The anticipated outcome is that large-deformation FE modeling will provide a more accurate explanation of the initiation and progression of landslides, overcoming the challenges of existing modeling tools, leading to improved safety and mitigation strategies. The project involves collaboration between WSP and Memorial University, with the results contributing to technical workshops, conference and journal publications, and the intern’s PhD thesis.

Process Innovation to Scale Cansbridge Fellowship’s Impact

This project aims to support The Cansbridge Fellowship in scaling its operations to meet growing demand while maintaining its mission of empowering Canada’s future entrepreneurial leaders. By redesigning the program framework, integrating advanced technology, and developing innovative marketing strategies, the project will provide the organization with scalable solutions to expand its reach and impact. Interns will bring expertise in business strategy, technology, and marketing to identify gaps, propose creative innovations, and enhance engagement with underrepresented groups. The expected benefit is a stronger, more efficient organization poised to support a larger network of emerging innovators and drive greater contributions to Canada’s entrepreneurial ecosystem.

Development of a Process for Manufacturing Synthetic Hydrocarbon Fuel from Captured Carbon Dioxide

This project would seek to develop an integrated system incorporating a reverse water gas shift (RWGS) reactor to convert carbon dioxide and hydrogen into carbon monoxide and water, aiming for maximum production of carbon monoxide. RWGS is an endothermic, catalytic, equilibrium-limited reaction, so the project team will seek to develop efficient, novel catalysts and supports, an optimal reactor design, and an efficient separation/recycling system so as to minimize wastage of unreacted raw materials. The work would build on and incorporate results from previous and ongoing funded projects in this area. High quality carbon monoxide is a very valuable industrial chemical, and can be used to manufacture products including liquid transportation fuel that is fungible to users of current conventional petroleum based fuels. The use of carbon dioxide, which is currently regarded as a problematic waste product of major industries like power generation, as a raw material for RWGS could represent a novel economic opportunity for large emitters.

EWOOL | LOGICIEL

1. Question de recherche :
Comment centraliser efficacement les flux de communication internes dans une organisation, en proposant une structure permettant une gestion autonome des informations entre les départements ?
2. Activités principales et défis de l’organisation partenaire :
L’organisation partenaire est une entreprise multisectorielle dont les départements fonctionnent en silos, avec des outils et processus variés pour la gestion des communications. Les activités principales consistent à coordonner les flux d’information, planifier les opérations et assurer la transparence entre les équipes.
Les défis identifiés incluent :
• La dispersion des informations sur plusieurs outils non connectés.
• Un manque de visibilité globale sur les échanges inter-départements.
• Des pertes de temps liées à la recherche et à la duplication des informations.
3. Avantages sociaux ou économiques attendus du projet :
• Efficacité accrue : Réduction du temps consacré à la recherche d’informations grâce à une centralisation efficace.
• Amélioration de la collaboration : Renforcement des interactions entre les départements grâce à un accès simplifié et uniforme aux données.

• Créativité et innovation : Une meilleure gestion des flux d’information encourage une réflexion stratégique et collaborative.
• Optimisation des ressources : Réduction des coûts liés à la duplication des tâches et aux inefficacités de communication.
• Satisfaction des employés : Des outils simples et accessibles amélioreront l’expérience des équipes dans leur travail quotidien.

Modélisation géospatiale du Port de Montréal: vers un jumeau numérique

Le fleuve Saint-Laurent est essentiel pour le développement économique du Québec, car il sert de route principale pour le transport de marchandises et d’entrée en Amérique du Nord. Compte tenu de son intense activité, le Saint-Laurent a été choisi comme site pilote pour tester une nouvelle norme internationale, la norme S-100 de l’Organisation Hydrographique Internationale (OHI). Cette norme vise à uniformiser les produits et services maritimes en intégrant différentes données nautiques numériques.
L’objectif du projet est de créer une modélisation en 3D du Port de Montréal, le plus grand port du Québec en termes de tonnage. Cette modélisation s’inscrit dans un effort plus large de création d’un modèle servant d’inspiration pour un futur « jumeau numérique » du port, c’est-à-dire une maquette numérique qui respecte la norme S-100. Cependant, la réalisation de cette modélisation 3D pose des défis importants. Il s’agit de rassembler et d’intégrer des données géospatiales et hydrospatiales de haute qualité pour garantir une modélisation détaillée du port. Ces données sont souvent géoréférencées dans différents systèmes de coordonnées avec une grande hétérogénéité de résolution spatial et qualité.

AI-driven XRD spectra interpretation and classification

This project aims to develop an advanced system for interpreting X-ray diffraction (XRD) data and classifying it based on insights provided by Subject Matter Experts (SMEs). XRD is a critical analytical technique used across various industries, including materials science, geology, and geophysics, to determine the crystallographic structure of materials. However, the raw spectra generated from XRD analysis are often complex and require expert interpretation to derive meaningful conclusions.

Materials Formulation Generation Using A Novel Informatics Platform

Single-use plastic bans and EPR laws are forcing CPG brands to transition from petroleum plastics to sustainable materials, a process that is complex, lengthy and expensive. Materia is addressing this challenge with an AI/ML-driven materials informatics platform with an integrated marketplace, empowering companies to develop and launch eco-friendly products 65% faster and cheaper. This project will help Materia to expand its capabilities through the development of a data driven algorithm that can specifically assist customers from material selection to formulation, the first steps in product development.

Impact of environmental stimuli on electrical responses in plants

Research in our group has begun to show that plants generate and use electrical signals to control functions within their
structure. When external stimuli are applied to a plant, different electrical signals are generated. These electrical signals contain
information both about the stimuli but also how the plant reacts to this stimuli. This research project’s goal is to measure these
electrical signals under different stimuli, and attempt to interpret and understand how these signals are generated and how the
plant uses these signals. Our earlier research has developed equipment and computer monitoring systems for these plant
electrical signals. These signals are recorded with custom built electrodes and the signals are decoded to predict the type of
stimuli that was presented to the plant. Our research will assess the electrical signal with two different plant species and
compare the results under different environmental stimuli. This research will allow us to begin to understand how these
electrical signals can be used by researchers to understand the inner workings of plants.

Development of rapid and accurate genomic techniques for ballast water UV treatment

The United States Coast Guard (USCG) recently introduced stringent regulations for the treatment of ballast water. Ultra-violet (UV) light is a useful technology in a ballast water treatment system (BWTS), for inactivating phytoplankton which could be invasive and harmful to humans and the environment. UV damages DNA and prevents replication, but the vital stain methods mandated in the USCG protocol do not detect UV damage. Alternative culture-based measures of reproductive capacity are yet to be approved, time consuming, and have limitations (not all species may grow). Rapid and accurate assays to identify cells that are UV damaged beyond recovery are critical for the acceptance of UV-based BWTSs. We will use DNA damage and repair gene activity assays to develop a rapid, reliable and cost effective quantification method for UV algal elimination in ship ballast discharge. TROJAN Technologies will use this technology to validate UV sterilization for global ballast water treatment.

Ex Vivo Live Imaging of Hematopoietic Stem Cells in D. melanogaster

This project aims to investigate asymmetric cell division (ACD) in blood cell development using live imaging and Drosophila melanogaster (fruit fly) as a model system. Hematopoiesis, the process of blood cell formation, relies on tightly regulated mechanisms to balance stem cell self-renewal and differentiation. Disruptions in this balance can cause blood disorders such as leukemia. ACD, where a stem cell divides to produce one self-renewing and one differentiating daughter cell, is a key mechanism for maintaining this balance, but its role in mammalian hematopoiesis remains poorly understood due to technical challenges in live imaging. This project will combine advanced live imaging techniques with genetic tools for tracking ACD-associated proteins in the Drosophila lymph gland, a hematopoietic organ. By visualizing how cell polarity proteins like Par-6 dynamically influence ACD and blood cell fate in real-time, the study aims to provide insights into how environmental signals regulate blood cell development and identify potential therapeutic targets for blood disorders.

Study to increase production efficiency in a lumber recycling process

This project promotes the use of recycled material by diverting it from current waste streams, thus reducing the pressures on local landfills and positively contributing to a reduction in greenhouse gas emissions. However, processing lumber waste generated in construction and demolition projects remains challenging due to the variability in dimensions and wood species as well as the presence of contaminants (e.g., coatings and preservatives) and impurities (e.g., nails and screws). As such, the goal of the project is to collect extensive data on the manufacturing process to study material flow and quantify the efficiency of each processing step in order to identify areas of improvements. The intern will then design novel solutions to significantly increase process efficiency. These solutions will be tested at a small-scale before selecting the best ones that will be implemented. The partner organization will benefit from the knowledge gained from the thorough data analysis and the implementation of novel solutions that will improve its efficiency and support its mission.