Innovative Projects Realized

Automated Ichnofabric Analysis with Deep Learning for Marine Core Research

This project proposes a completely novel workflow to automate the detection and quantification of bioturbation (i.e., biological sediment mixing by infaunal organisms) in deep-ocean sediment cores using the proven capabilities of neural networks in complex image interpretation. The new technique will enable precise, objective, and efficient quantification and identification of bioturbation types caused by infaunal activity, overcoming current limitations that rely on expert interpretation and require highly specialized ichnological training. The student exchange will bring a talented PhD student from a leading UK university to Western University, creating a valuable new international collaboration. It will expose Dr. Shchepetkina at Western University to a cutting-edge partnership in Artificial Intelligence (AI) with a world expert (Dr. John) at a top UK institution. The student is a recipient of the prestigious HSS Principal’s Doctoral Research Studentship—a scholarship awarded only to top students—and will contribute their expertise to Western University’s ongoing research for four months. This collaboration benefits Western University by enhancing its capacity in AI-driven science and establishing direct ties with world-leading AI knowledge from the UK. For the UK institution, it provides a unique international experience for a top student and strengthens global academic cooperation to advance critical research.

3D-Printed Thermoelectric Metamaterials

Thermoelectric materials present a promising solution for sustainable energy generation, offering the potential to complement existing energy systems in everyday applications. However, the performance of conventional thermoelectric materials is largely constrained by the intrinsic properties of their bulk constituents. To overcome these limitations, reducing material weight while enhancing efficiency, adaptability, and multifunctionality is essential.
One emerging strategy involves engineering the micro- and meso-architectures of thermoelectric materials. By tailoring and optimizing their internal geometries, it becomes possible to significantly improve performance characteristics beyond what is achievable with bulk materials alone. Although the rational design of such complex micro- and macrostructures is increasingly feasible through computational methods, the fabrication of these architected materials—particularly those with intricate and precise geometries—remains a major technological challenge.
This project seeks to address this gap through a collaborative research effort between McGill University and the Pohang University of Science and Technology (POSTECH). The aim is to develop advanced manufacturing approaches and structural designs for next-generation thermoelectric metamaterials, enabling breakthroughs in both performance and practical deployment.

L2M – BIM-Enabled Multi-Criteria Decision-Making: Towards Efficient Building Element Selection

The project focuses on creating a new software tool that combines multi-criteria decision-making (MCDM) methods with BIM, a 3D digital modeling system used in construction. This tool will assist architects, engineers, and builders in selecting materials and elements by evaluating multiple criteria, such as cost, durability, and their environmental impact. By addressing challenges like too much data and fragmented decision-making, the tool aims to streamline workflows and reduce errors.
For the partner organization, the tool is expected to enhance project efficiency, lower costs, and improve the ability to meet sustainability goals. This could lead to more successful projects that are also better for the environment, aligning with market demands for greener construction practices.

L2M – Link Between Worlds

Link Between Worlds is a project that combines play therapy techniques and teaching creative expression to Indigenous peoples and communities that typically are not given a voice. The objective of Link Between Worlds, through an intensive/retreat format, is to teach and provide a safe space for indigenous people to grow and learn skills in storytelling/filmmaking, creating an outlet for image discovery, cultural retention, career ownership, entrepreneurship and healing through storytelling. Delivery in a traditional “with the land” setting encourages familiarity and group participation. Participants will acquire many tools to embark on a refreshed perspective on life.
The challenges we are facing are rooted in the differences between each indigenous community from a presentation/facilitation perspective. Additional challenges include determining which market would be our best primary customer, Governments/Bands, Institutions/Treatment centers or individuals. Lastly, scalability is another challenge we seek to overcome.
Launch will provide insight into our marketing strategy, aid in constructing our pilot offering, and assisting in determining our primary targets.

Surveillance permanente de l’état des machines opérant àvitesse et charge variables

Le changement de comportement dynamique des machines tournantes (ponts roulants, éoliennes, robots) en fonction de la vitesse et de la charge se confond facilement avec un changement d’état de l’équipement, ce qui déclenche souvent de fausses alarmes sur des machines saines. De plus, la plupart de ces machines opèrent à très basses vitesses, ce qui cause des problèmes sur la sélection de capteurs efficaces et sur les normes inexistantes dans ce genre d’application. Le projet proposé a pour objectif le développement d’une méthode de diagnostic d’endommagement de machines opérant en régime variable et la conception d’une chaîne de mesure permettant la surveillance en ligne de systèmes rotatifs. Une première phase sera allouée à l’étude de faisabilité, le choix de l’architecture, et la mise en place de la chaine d’acquisition. Une deuxième phase consistera à développer un système d’autodiagnostic en mettant en œuvre les techniques d’intelligence artificielles pour définir des seuils de sévérité à ne pas dépasser en tenant compte de la vitesse et la charge appliquées. Les travaux proposés permettront de détecter l’état de dégradation de la machine, d’obtenir un gain de productivité en diminuant les temps d’arrêt et d’avoir une diminution du risque d’accident lors de l’opération des machines.

Applied AI Solution Development

This project aims to help Rogers Communications bring real-world AI and Generative AI solutions to life across Business units like Customer Care, Network, HR, Rogers Business. A team of eight interns from the University of Waterloo will work with Roger’s Data & AI Strategy team to turn identified promising use cases into working solutions. Their focus will be on building small-scale models (called MVPs), testing them with users, tracking their performance, and preparing them for wider use. The project will speed up Roger’s ability to adopt AI in a responsible and scalable way, while also giving students hands-on experience in a real business setting. Ultimately, it helps Rogers improve service, efficiency and innovation, while training the next generation of AI talent.

TRLUP – Stretcher Aid

Our Stretcher Aid is a new approach to increasing ergonomics and overall care for both caregiver and patient. Our product is designed to create more usable working space for Nurses and Caregivers, allowing for more ergonomic choices during emergency situations. With the support of New Ventures BC, we will be able to utilize the resources available to advance project development while gaining the knowledge to secure IP and structure a successful business around it.

L2M – Neuro-integrated carbene coatings

Brain-Computer Interfaces (BCIs) are a revolutionary technology with the potential to significantly improve the lives of individuals with neurological disorders, but their long-term use is severely limited because the implants often fail within a short period. This project, a collaboration with Queen’s University, aims to solve this critical problem by developing and commercializing “Neuro-Integrated Carbene Coatings” (NICC), a groundbreaking new material designed to create an exceptionally stable and long-lasting bond between the BCI electrode and the brain tissue. By pioneering the use of N-heterocyclic carbene (NHC) chemistry, the project will create a coating that is both biocompatible and durable, minimizing the body’s immune response and preventing the material degradation that causes current devices to fail. The expected benefit to the partner organization is the validation and development of a clear commercialization strategy for this transformative coating technology, positioning it as a vital solution for the rapidly growing BCI market and ultimately enabling the creation of a new Canadian deep-tech venture.

L2M- AI Lab Assistant

This project initially targets drug discovery labs, with long-term plans to expand into broader biomedical research. As AI becomes integral to scientific work, we aim to build a custom AI assistant that goes beyond basic chat support, capable of running code, executing ML/DL pipelines, and assisting with lab-specific tasks.

L2M – Artificial Intelligence Integrated Medical Media Suite

The Artificial Intelligence Integrated Medical Media Suite (AIIMMS) is a smart, AI-powered crash cart designed to support emergency response teams during coding events. By integrating live video, audio, patient biometrics, and patient electronic health record data into a centralized interface, AIIMMS can help reduce the cognitive load and enhance clinical decision-making in real time. The system is powered by an AI model trained to interpret real-time video and audio data, provide guidance in determining a differential diagnosis, and assist in adhering to ACLS protocols. By streamlining the coding workflow with data-driven systems, AIIMMS aims to achieve a faster Return of Spontaeneous Circulation (ROSC) time to improve patient outcomes in hospitals such as SRI.

Revitalisation socio-territoriale en contexte nordique

Le projet de recherche se déroulera dans la municipalité de Baie-Johan-Beetz, une communauté nordique d’environ 80 habitant·e·s située sur la Côte-Nord du Québec. Cette localité fait face à plusieurs défis communs aux régions éloignées : vieillissement de la population, centralisation des services, rareté des logements et difficultés à attirer de nouveaux résident·e·s. Malgré des efforts importants pour revitaliser le territoire (marketing, développement résidentiel, projets communautaires), la municipalité est limitée par un manque de ressources humaines et une surcharge administrative. Le stage permettra d’appuyer la municipalité de façon concrète, en participant à ses activités quotidiennes tout en menant une analyse des initiatives de revitalisation mises en place. Cela inclut un travail sur les archives, les outils de communication, la sensibilisation citoyenne et l’évaluation des freins rencontrés dans les projets. Le stage offrira un temps de recul et une expertise externe difficile à mobiliser en temps normal. Il visera à renforcer la capacité d’action municipale et à produire des recommandations utiles, tout en valorisant les forces locales. Pour l’organisme partenaire, les bénéfices sont à la fois pratiques (soutien direct) et stratégiques (recul, analyse, transmission des savoirs). Pour la personne stagiaire, c’est une occasion d’approfondir ses compétences en aménagement du territoire, en revitalisation des milieux nordiques et en recherche ancrée dans le terrain.

L2M – Healthcare Systems Performance Optimization using Reinforcement Learning-Enhanced Functional Resonance Analysis Method

Healthcare systems operate as complex socio-technical environments, involving unpredictable interactions among patients, clinicians, technologies, administrators, and institutional policies. These systems are often under significant pressure to improve performance, reduce costs, and enhance patient safety—yet they frequently lack the tools to simulate the consequences of operational decisions before implementation. Traditional approaches like retrospective analysis or static models fail to capture dynamic system behavior and interdependencies, especially when working with limited or sensitive data.

This project addresses that gap by developing a simulation-based decision-support tool that integrates the Functional Resonance Analysis Method (FRAM) with Reinforcement Learning (RL). FRAM helps map functional relationships within healthcare processes, capturing variability in everyday work. RL, in turn, enables the system to learn from simulated experiences by rewarding effective decisions and avoiding poor ones—thereby identifying optimal strategies even in complex and low-data environments.

The aim is to provide hospital administrators, system planners, and policymakers with a user-friendly platform for exploring “what-if” scenarios without disrupting real-world operations. By simulating changes in patient flow, staffing, or resource allocation, the tool can uncover unintended consequences and support more resilient planning.

Through the Lab2Market Validate program, we will conduct structured customer discovery interviews, engage with healthcare stakeholders, and incorporate their feedback to refine the tool’s usability, interface design, and integration requirements. The ultimate goal is to bridge the gap between academic research and real-world application by building a product that is technically robust, practically usable, and commercially viable.

This innovation not only supports more informed healthcare decision-making but also contributes to Canada’s broader priorities around improving public service delivery, fostering applied AI innovation, and enhancing productivity in a resource-constrained health system.