Innovative Projects Realized

Long-Duration Testing of Concrete-Based Molten Salt Thermal Energy Storage Tanks Under Forecasted Electricity Supply Conditions

Molten salt-based thermal energy storage (TES) systems offer a promising way to store and manage heat efficiently, especially for industries that rely on stable high-temperature processes. However, these systems are still in development, and key challenges—such as heat loss, material durability, and long-term performance—must be addressed to ensure their reliability and cost-effectiveness.

While some studies have explored concrete-based tanks for molten salt storage, most research has focused on short-term performance. There is little understanding of how these systems behave over weeks or months, especially under fluctuating electricity inputs from renewable sources.

This project aims to fill that gap by testing TES tanks over long periods under real-world conditions. By examining their thermal stability, efficiency, and durability, this research will help develop optimized storage solutions, making molten salt TES more practical for industries like food processing and mining while supporting the transition to renewable energy.

Effects of flooding and rising temperature on C storage and release dynamics in alluvial forests

Advancing Land Classification with AI: Exploring Kolmogorov-Arnold Networks

Land classification is crucial for environmental monitoring, resource management, and urban planning. This research explores using Kolmogorov-Arnold Networks (KAN), a novel machine learning model, for multispectral land classification. Unlike traditional neural networks, KAN utilizes univariate functions as activation mechanisms, enhancing its ability to capture complex spatial and spectral patterns in satellite imagery. The study focuses on classifying land in the Edmonton-Calgary corridor using hyperspectral data, which contains rich spectral information but presents computational challenges. The Finnish Centre for Artificial Intelligence (FCAI) will provide expertise in optimizing KAN for high-dimensional datasets, reducing computational demands, and improving model interpretability. A key goal is to compare KAN’s performance with conventional models regarding accuracy, robustness, and efficiency. The study will also assess whether KAN’s high accuracy results from superior learning abilities or potential overfitting. This project contributes to Canada’s leadership in AI and environmental monitoring, offering a more efficient, data-driven approach to land classification. The findings will aid policymakers in making informed urban development, agriculture, and conservation decisions. Additionally, the collaboration between the University of Alberta and Aalto University strengthens global research ties in AI-driven remote sensing.

Set-up of a custom light-sheet microscope for electro-mechanical investigation of neuronal organoids

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.