Projets novateurs réalisés

Linear array CMUTs for medical imaging applications

We propose the construction of novel ultrasound transducer structures based on existing MEMS technology that has been in development through collaboration between Micralyne and Prof. Roger Zemp. We will be exploring linear array transducers intended for medical imaging, and individual transducers for automotive use for ultrasound range finding. We will undertake the design, modelling, fabrication, packaging, and testing of the devices. The end goal is to produce commercially-viable transducers that may be used as replacements for the current generation of piezoelectric-based transducers. Micralyne would benefit by having a commercial offering at the end of the project. The Zemp lab will demonstrate array imaging with a novel architecture, and the work done will serve as a platform for further development including the use of novel materials and new array imaging schemes.

Mapping the space of motion diffusion models to optimize performance

This research project focuses on optimizing the efficiency and performance of motion diffusion models for real-time applications in video games. Diffusion models have shown great potential in producing high-quality and diverse human motion animations, but are often limited by their computational demands. This project will explore different model architectures and optimization techniques to reduce their resource consumption, making them faster and more memory-efficient without sacrificing animation quality. The project will aid CD Projekt Red in deploying optimized motion diffusion models for games in production, affirming its position as a technical innovator in the gaming industry while providing material benefits through the development of an evaluation pipeline for future model assessments.

Quantitative Investing Intern

Vestcor, Atlantic Canada’s largest in-house investment manager with $21 billion in assets, specializes in quantitative investing and risk management to optimize portfolio performance. One of the key challenges Vestcor faces is the continuous need for innovation and improvement in security selection and risk modeling. As financial markets become increasingly complex and data-driven, Vestcor must refine and enhance its quantitative models, statistical approaches, and risk assessment techniques to maintain a competitive edge. The company seeks to integrate new data sources, machine learning techniques, and advanced financial modeling methods to improve portfolio management strategies. To remain at the forefront of investment innovation, the Quantitative Investing Team requires empirical research and development of new techniques to improve decision-making, optimize risk-adjusted returns, and ensure long-term financial sustainability for its clients.

Agentic AI for Automated Essay Scoring

This research project aims to develop an AI-powered essay grading system that is both cost-effective and highly accurate. The project will explore how a dual-agent AI system, one that optimizes the cost and another that performs prompt refinement, can improve automated essay scoring at scale. By using advanced techniques such as Retrieval-Augmented Generation (RAG) and error-based prompt refinement, the system will ensure more precise and consistent grading. The partner organization, a leading educational service provider, will benefit from operational improvements, faster feedback for students, and improved accuracy in assessments. Additionally, the system’s open-source, on-premise design ensures student data security. Overall, this project will not only enhance the partner organization’s competitiveness but also strengthen its reputation as a leader in AI-driven education. By improving grading efficiency and educational outcomes, the project will contribute to the broader goal of making AI a valuable tool in modern education.

Predicting Engine Failure from Vehicle Telematics

(1) Main activities of the partner
Geotab is a global leader in telematics specializing in fleet management solutions to enhance operational efficiency, safety, and sustainability. For this project Geotab will be providing their vast collection of data from over 80,000 customers. Additionally, Geotab will provide the intern with support and structure within their data science and maintenance/ safety team.

(2) Challenges
Diagnostic trouble codes (DTC) and the corresponding warning lights are often the first indicator of a severe mechanical problem with a vehicle. Geotab’s rich data set of ongoing vehicle metrics may allow for the detection of these issues before they become severe enough
to trigger a DTC. However historical breakdowns are recorded in a raw and unstructured timeseries dataset. Drawing insights from this will require extensive data cleaning and modeling to successfully predict severe maintenance issues before their occurrence.

(3) Social or economic benefits
A successful implementation of a predictive model will enable Geotab to empower their customers to achieve even more efficient fleet operations through:
? Enhanced Fleet Efficiency: Increased proactive maintenance will reduce vehicle downtime and repair costs for fleet operators.
? Cost Savings: Improved predictive analytics can help fleet managers optimize maintenance schedules, leading to lower operational expenses.
? Environmental Benefits: Reduction in emissions through better engine performance monitoring and operations.

Research and Implementation of LLM based Autonomous Agent Based on IoT Big Data Environment

Geotab will provide the foundational platform and infrastructure, data, and expertise for the project. This includes access to their IoT big data environment on Google Cloud Platform, containing telematics data from 4.5M+ connected vehicles globally. They will offer mentorship and support through their AI Platform team, share historical data and documentation for training the large language model agent, and enable the intern to utilize various tools and resources to conduct analysis and construct solutions.
Geotab possesses a wealth of telematics data gathered from over 4.5 million devices globally, which presents untapped potential for AI-driven improvements in safety, sustainability, and operational efficiency for its customers. However, manual identification of critical events—such as safety incidents, customer dissatisfaction signals, or computational inefficiencies—is time-consuming, reactive, and prone to delays. The reliance on human intervention for analysis compromises real-time responsiveness and scalability, with suboptimal resource usage and consumption.
This project addresses the challenge of developing an autonomous Large Language Model (LLM) agent to provide actionable insights to both Geotab developers and customers, enabling rapid responses and proactive problem-solving.
The project solution enhances Geotab’s product quality, improves driver safety, reduces computation cost, and strengthens customer relationships.

Optimizing Field Protocols for Assessing Pathogen Loads in Bumble Bees

Bumble bees are essential pollinators, but their populations are declining due to habitat loss, climate change, and pathogens like Crithidia and Vairiomorpha. These pathogens spread through feces on flowers and within colonies, reducing bee fitness and survival. While pathogen levels are well-documented in mainland southern Ontario, little is known about their prevalence on Pelee Island, a potentially important refuge for at-risk species. This project aims to assess whether Pelee Island bumble bees have lower pathogen levels, which could make the island a key site for conservation efforts. In partnership with Wildlife Preservation Canada (WPC), we will conduct surveys to measure pathogen prevalence in bumble bees across the island and compare infection rates to mainland populations. Using a non-destructive fecal sampling method developed by WPC, we will refine techniques for monitoring bumble bee health and explore behavioural assays to improve pathogen detection. The intern will also assist with WPC’s conservation breeding program to identify healthy bees for rearing efforts. This research will improve pathogen monitoring, inform pollinator conservation strategies, and determine whether Pelee Island serves as a low-pathogen refuge. Findings will support WPC’s breeding programs and broader efforts to protect imperiled bumble bee populations and maintain biodiversity.

Pollution control of gas mixtures: gas monitoring and detection of contaminants usingnovel THz technology Year Two

Electric power plants are the number one toxic air polluters in North America. The emitted pollutants are proven to cause serious health and environmental issues. The emission of Carbon dioxide and of other pollutants, such as nitrogen oxides, sulfur dioxide – major drivers of the human-accelerated global climate change- must be monitored insitu. Our goal for the present project is to explore the properties of Terahertz radiation for control of pollution in the atmosphere. In particular, we intend to develop a new waveguide-integrated gas monitor, based on Bragg grating sensors. Such devices, whose sensitivity will be increased through modulation via an external magnetic field, will be based on probing induced anisotropy. The integration of the proposed sensor into the existing line of products of our industrial partner, QPS Photronics, can potentially result in a versatile tool for industrial applications, which could give the company a leading edge over the competition.

Thermally Driven Contactless Power Transfer Using Thermophotovoltaic Receivers

The objective of the proposed research project is to build and demonstrate a fuel-powered contactless power transfer (CPT) system. This system is comprised of two units: an emitter and a receiver. The emitter, which can be heated using different fuels (including oil, gasoline, hydrogen, biodiesel) emits radiant energy over a distance to the receiver, which converts the radiant energy to electric power using photovoltaic cells. The emitter and receiver units can be mounted on different vehicles to achieve mobile CPT. This CPT system can be used in energy networks supporting a range of vehicles and infrastructure in remote and harsh environments such as arctic regions and outer space. This CPT system will exhibit significant advantages over existing wireless power transfer system. Since it is powered by fuel instead of batteries it can provide for much higher energy densities and reliability when operating in cold environments.

Vision-based precision landing for UAVs

This project aims to develop a robust vision-based precision landing system that enables drones to dock accurately in challenging environmental conditions including rain, fog, and darkness. The system leverages computer vision technology mounted on an ARA-408 drone to identify visual markers on a docking station, calculate trajectory, and execute precise landings when traditional GPS guidance may be compromised. This collaborative effort between ARA Robotique and Polytechnique Montreal represents an advancement in autonomous drone capabilities for monitoring applications, ensuring reliable operations in environments where conventional navigation systems might fail.

Debugging the Brain: Reading and Writing Human Cortex using Electroencephalography (EEG) and Transcranial Magnetic Stimulation (TMS)

The Temerty Centre for Therapeutic Brain Intervention aims to find new understandings of and approaches for hard-totreat mental illnesses across patients’ lifespans by delivering high quality clinical care and research using brain stimulation and psychedelic therapies. Personalized modulation of brain networks with Transcranial Magnetic Stimulation (TMS) is a promising treatment for neuropsychiatric brain disorders such a major depressive disorder. However, there is a need to
better optimize the treatment, to increase patient’s quality of life and reduce healthcare costs (Fitzgibbon et al., 2020). To do so requires the ability to reliably decode the brain activity evoked by TMS, as measured by Electroencephalography (EEG). However, it is challenging to analyze this EEG data because it has high dimensionality (an EEG recording from one patient contains thousands of data points for each of the 64 electrodes in an EEG cap) and noise (patient movements such as eye blinking can introduce artifacts in the signal (Louis et al., 2016)). EEG data analysis for TMS sessions is further complicated because, to extract relevant insights from a single trial data of EEG data, prior information on the expected signal features is required, yet currently not known (Hernandez-Pavon et al., 2023).

Implementation of Software Features for Electrochemical Impedance Spectroscopy Analysis in Industrial Electrochemical Assets

Pulsenics will collaborate closely in this project by partnering with the intern to enhance their software platform, specifically targeting real-time Electrochemical Impedance Spectroscopy (EIS) analysis. Pulsenics faces challenges with their current EIS software, which lacks the efficiency and diagnostic accuracy needed for effective real-time monitoring, resulting in increased downtime and less-than-optimal asset management. This research aims to develop a modular solution that addresses these shortcomings by improving diagnostic accuracy and reducing maintenance interruptions.
Pulsenics is an OEM specializing in EIS solutions for R&D, production QA/QC, and real-time monitoring of industrial-scale electrochemical systems. Their integrated hardware and software platforms support high-performance measurement, data analysis, and system control across a broad range of applications—including electrolyzers, fuel cells, batteries, electrochemical water treatment, and metallurgy. Pulsenics’ technology is used globally to enable innovation, scalability, and reliability in the transition to electrochemical-based systems.
As industries rapidly scale green technologies, there is a critical need to shift from R&D-centric workflows to scalable, production-ready operations. This transition demands faster iteration cycles to develop and validate new technologies, and robust, automated QA/QC systems that derisk sales while maintaining high throughput. This project will accelerate development, streamline QA/QC, and help deploy production-scale electrochemical systems with greater confidence and less manual intervention.