Projets novateurs réalisés

Calcium alginate microbeads loaded with lipid nanoparticles as precursors for lipid-loaded pellets

Adversarial Attacks on 3D Object Detectors

A Risk-Based Continuous Authentication Engine Using a Probabilistic Model around Behavioral Biometrics

Traditional static authentication systems have a fundamental deficiency; it assumes the presence of the validated user through the length of the session. Continuous authentication algorithms periodically validate the identity of a user during the entire session. It relies on information that can be automatically extracted from the user such as biometrics and behavior patterns. A probabilistic approach can naturally model the noise and latent variables present in the data. The probabilistic output of such models is a confidence value. Risk-based authentication makes use of this value to define task-specific requirements. The proposed research project has two components: an anomaly-based Intrusion Detection System (IDS), and a risk-based authentication system that uses biometrics and behavior patterns. If our research in this area proves to be successful, we can hopefully replace the use of password challenges as a primary authentication factor, in exchange for continuous algorithms that are more reliable and less of hindrance to the end-consumer

Development of high-efficiency semi-transparent organic solar cells with enhanced infrared absorption and tunable transparency

THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW

Intra-operative imagery processing for for computer-assisted interventions

Using wild potato species for blight resistance breeding research

Research and Development of Ultra-portable Modulus Structures

This Mitacs internship program is targeted to recruit a top mechanical engineering student to research and design a state-of-the-art braking system for the Greenheart’s high-speed ziplines. The intern will conduct literature review of different braking systems used in the zipline industry and develop robust numerical models to examine the performance of existing designs. Using the finding from the finite element study, the high stress area of the existing braking system will be identified. These findings will be used to design alternate braking system for Greenheart’s high-speed ziplines. The intern will work with Greenheart personnel to build a working prototype and verify the safety and efficiency of the braking system through experimental testing. Successful development of the braking system will significantly benefit Greenheart’s position as the leader in the eco-tourism company by allowing Greenheart to providing more versatile and safe transportation for its client to access the remote areas in Canada and worldwide.

L2M QC Spring 2025 | Personalized Daily Rhythm Optimizer (Technohealth): Using wearable sensor data to detect an individual’s biological clock and optimize daily schedules for peak mental performance, relaxation, and recovery.

Canada’s healthcare system is facing growing challenges, including rising costs, overworked providers, and limited access to preventive care. At the same time, mental health disorders and chronic diseases are increasing, often linked to disrupted sleep and daily activity patterns. Despite their impact, these disruptions are difficult to track because they rely on self-reports, occasional doctor visits, and expensive medical tests that are impractical for daily use. As a result, early warning signs are missed, leading to worsening health conditions and higher healthcare demands.
TechnoHealth aims to solve this problem by using wearable device data to improve health monitoring. While smartwatches and fitness trackers already collect valuable information, most systems struggle to turn this data into useful insights. TechnoHealth bridges this gap by integrating data from multiple devices, such as Fitbit and Empatica, and applying artificial intelligence (AI) to detect health disruptions before they become serious.
Our innovation has two key steps. First, TechnoHealth organizes and standardizes wearable data, ensuring consistent and reliable tracking over time. Second, it uses AI to provide personalized recommendations, helping individuals improve their sleep, activity, and overall well-being. Unlike traditional tracking apps that only display raw data, TechnoHealth translates this information into meaningful insights that support both users and healthcare professionals.
We have already tested our system with real data, demonstrating its ability to predict changes in sleep and activity patterns. A prototype mobile app has been developed, providing a foundation for further growth. Through Lab2Market, we aim to refine our solution, ensure compliance with privacy regulations, and explore business opportunities. TechnoHealth has the potential to make healthcare more proactive, reduce strain on the system, and help people lead healthier lives.

L2M QC Spring 2025 | Social Worker Safety and Reporting Application – SafeSocial

SafeSocial is a mobile and web application designed to improve the safety and efficiency of social workers during home visits. By providing real-time monitoring, emergency response, and AI-powered incident reporting, the app helps social workers feel more secure and supported in the field. Key features include a panic button, live location tracking, risk assessments, and voice/video recording. This project will benefit social work organizations by enhancing worker safety, reducing administrative burdens, and improving response times in critical situations.

Advanced Methods in Neuroimaging and Applications to Reward Processing

L2M – Automated Weight Monitoring for Free-Range Beef Cattle

The beef cattle industry faces significant challenges in cattle weight monitoring, particularly in free-range systems where traditional methods are labor-intensive, inaccurate, or infrequent. This results in delayed growth, increased feeding costs, and a larger environmental footprint, requiring the development of innovative and sustainable technologies, as well as collaborative efforts. To address this, we propose an automated, non-invasive weight monitoring system that combines vision-based sensors and machine learning to track cattle growth in real time without disrupting farm operations. By providing data analysis and insights, this solution will enable farmers to make data-driven decisions and optimize herd management to sustainably and efficiently improve livestock quality of life and health, optimize resource use, and boost productivity. Through the L2M Launch program, the proposed solution will be refined from a market perspective by tackling specific commercialization challenges and developing a comprehensive business model that reflects the economic and operational realities of the beef cattle industry to ensure product-market fit, while also promoting entrepreneurial skills and enabling research discoveries to move out of the laboratory and be commercialized, thereby accelerating and growing the translation of research excellence to impact the Canadian economy.

Behavioral Analysis Internship: Assessing Gerbil Personalities through Behavior and Vocalizations