Innovative Projects Realized

Imagerie THz multispectrale assistée par l’IA

L’INO (Institut National d’Optique), entreprise à but non lucratif spécialisée dans le développement de solutions optiques pour l’industrie manufacturière, souhaite bâtir une base de données structurée d’images THz annotées à partir d’échantillons de plastiques représentatifs de cas industriels. Les principales activités comprennent la fabrication d’échantillons de différentes épaisseurs (par impression 3D et à partir de matériaux bruts), l’intégration d’inclusions contrôlées, la réalisation de campagnes de mesure avec plusieurs configurations (fréquences, polarisation) sur ses équipements, ainsi que le développement d’outils d’annotation et d’analyse comparant des outils maison et commerciaux. Ces travaux permettront de relier directement les signatures spectrales et texturales aux types de plastiques et aux défauts.

Les avantages économiques et sociaux attendus pour INO sont multiples : d’une part, la base de données permettra à INO de prédire rapidement, lors des consultations avec de nouveaux clients, la faisabilité et la pertinence de solutions d’imagerie THz, évitant ainsi des expérimentations onéreuses et optimisant l’allocation des ressources. D’autre part, elle constituera un socle pour le développement de futurs outils de diagnostic assisté par l’intelligence artificielle, renforçant la compétitivité d’INO et soutenant l’innovation dans l’industrie du recyclage, de l’emballage et de la fabrication avancée.

Genetic control of Reproductive Longevity in Mouse and Validation of a genetic marker panel to predict Fertility and Longevity traits in Holstein Dairy Cattle

Reproductive Longevity (RL) is a complex biological trait under the control of many genes. In Cattle, RL is a key productivity factor, especially for dairy cows. The proposed research aims to identify RL-controlling genes in mammals using: 1) a unique model system, selectively-bred mouse lines that reproduce twice as long and have twice as many litters as matched control lines and 2) cattle (bulls) with High or Low genetic merit for Longevity. The project Partner, Performance Genomics Inc. (PGI), is applying whole genome mapping and sequencing technologies (outsourced) to generate complete genomic datasets for mice and cattle. This will result in a set of DNA markers that will be validated using DNA and data from 3,000 bulls. The internship project will apply bioinformatics tools and approaches to “mine” the genomics data with the goal of selecting and ranking candidates for genes and mutations responsible for RL in mouse and/or cattle. The end result for PGI will be commercial DNA Markers tests for RL for livestock breeding, initially for Holstein cattle.

Eddy-sea ice interaction in the Arctic Beaufort Gyre in two high-resolution ocean-sea ice models

The Beaufort Gyre (BG) is the largest freshwater reservoir in the Arctic Ocean. It is climatologically anticyclonic and governed by the Beaufort High. Its dynamics have a profound impact on the general circulation, and the possible release of freshwater has significant climate implications. The equilibrium state of the BG has been proposed to be governed by the combined role of surface wind forcing, eddy fluxes, and the ice-ocean governor. In the context of global warming, the sea ice in the BG has been transitioning toward a state of thinner and younger ice, making it more dynamic and susceptible to external forcing. Eddies are crucial and active players in the transport and mixing of heat, salt, and momentum. Our proposed work will employ large datasets obtained from two state-of-the-art km-scale ocean models to investigate eddy-sea ice interaction in the BG. This work will showcase how km-scale models can help understand eddy processes and the impacts of climate change.

Email and Marketing Assistant

Nature Bee is a Canadian-based company creating microplastic-free, sustainable cleaning products. As we scale, we are looking to strengthen our digital marketing efforts—particularly our email marketing, retention strategies, and performance analytics across channels.
This internship project will focus on developing a robust, evidence-based email marketing strategy using Klaviyo, alongside reviewing paid ads performance to improve full-funnel engagement. The intern will analyze Nature Bee’s customer and subscriber data to create refined audience segments based on purchase history, email engagement, demographic details, and customer lifecycle stage.
The intern will conduct a literature and competitor analysis of lifecycle marketing best practices for purpose-driven, direct-to-consumer brands, especially those targeting eco-conscious consumers. They will design and implement new Klaviyo flows such as welcome series, abandoned cart, post-purchase education, and customer win-back campaigns. A/B testing of subject lines, timing, creative content, and CTAs will be conducted to optimize performance.
In addition to email, the intern will collaborate with the marketing team to evaluate Meta and Google Ads platform data, identifying how paid campaigns influence email signups, conversions, and long-term retention. They will help build an integrated dashboard to report on key email and ad metrics such as open/click rates, revenue per campaign, CAC, and LTV.
Deliverables include a comprehensive email marketing playbook, clearly mapped automation workflows, campaign test results, performance dashboards, and recommendations for ongoing optimization. This work will directly support Nature Bee’s growth goals by driving customer engagement and revenue while maintaining the brand’s commitment to sustainability and transparent communication.
Beyond this work, they will be supporting our marketing and operations team with other creative work, production support to gain a deeper understanding of the work we do, support with marketing channels from our creative director and communicating with sales support as well!

A Novel Torque Measurement Technique Based onPiezoelectric Sensors

In this project, a novel torque measurement technique based on piezoelectric sensors will be proposed to overcome the constraints posed by traditional methods such as strain gauges, magnetic pickups etc. Specially designed disks which are connected to the sensor will be mounted on the shaft. The proposed method will be used to compare relative twist in the shaft based on the phase difference between the disks. The angle of twist is then correlated to the torque applied. The proposed technique can be used as a low cost solution for torque measurement or rotating components. Finally, it is expected to publish the novel piezoelectric sensor based torque measurement technique in peer reviewed articles.

Advancing Climate Finance and Social Entrepreneurship

Through this project, interns will support organizations and initiatives advancing climate finance and social entrepreneurship in the Victoria and British Columbia ecosystem.

Debugging ML via Feature-guided Analysis: Analyzing Neural Network Robustness

Neural Networks (NN) use a set of individual units (neurons) connected together to learn a specific behavior from a dataset. For example, NN excel in classification tasks where given a dataset labelled with presence or absence of a feature in each entry, they are able to detect the feature presence on new inputs. This technology has been applied in many fields, including automotive, aerospace, medical and others.
A significant drawback of NNs is that their behavior is unknown, since it only depends on the training data and it is not understandable to humans. This significantly limits their applicability, especially in safety-critical fields. For this reason, NN interpretability is a growing field of research. Feature-Guided Analysis (FGA) is a technique that extracts rules from NNs and can help explain how the values assumed by individual neurons affect the outcome of the network.
This project aims at replicating the results of this technique on a new image-based dataset and improve upon the limitations of the existing technique. We further aim at employing this technique to analyze the robustness of the network, providing engineers with a description of which portion of the NN are more susceptible to perturbations on the inputs.

Exposing the Invisible – Designing with the Uncertainty of Wind

The objective of this project is to connect architects and wind engineers early on within a project so that affects associated with wind such as pedestrian comfort and building strength may be maintained from the start of a project. Rather than making post-construction modifications to a building through the costly use of screens, covers or even redesign, favorable wind conditions could be achieved through the collaboration between architects and wind engineers during the initial stages of design. This would reduce the dangers of increasing wind speeds on ground level, the costs to redesign or add in components and finally save time on construction. Instead of sealing ourselves inside buildings, we could begin to understand wind flows and expand our ideas of what architectural form, technologies and experiences could be created. The idea is to not only promote the goals of safe environments from RWDI but to also spread the word and clarify the importance of wind to a larger audience so that wind can play a larger role in the development of our cities.

Quantifying the Safety and Efficiency of Dance Styles Using Wearable Sensors at University College Cork and Tyndall Institute

This project, based at the Tyndall Institute at University College Cork in Ireland, is creating one of the first open-access, lab-quality biomechanics datasets focused on dance. It will record movement from different dance styles using motion capture, wearable sensors, and muscle activity measurements to better understand the physical demands of dance techniques and the risks of injury. The project will also develop standardized methods for processing and interpreting the data, making it easier to apply in training, rehabilitation, and machine learning. By sharing these resources openly, the project supports innovation in sensing technology, artificial intelligence, and human performance research.

Querying the immigrant: data classification and technical construction of the risky entries

The project is part of a thesis that investigates logic of classification embedded in advanced data analytics and automated decision-making tools (and, now “AI”), implemented to determine Canada’s temporary resident visa applicants, which involves sorting applicants for risk, inadmissibility, ineligibility, and illegality.

Developing Advanced Topologies for High-Power Motor Drives

Energy saving is one of the important issues in today world. In order to improve the performance of the industrial motor drives for high-power applications, higher voltage power converters are recommended. Compared with low-power converters, high-power systems have their distinct characteristics and challenges, and usually require converter configurations capable of processing energy conversion at higher power and voltage levels. The technical requirements and challenges for MV systems differ in many aspects from those of the low-voltage AC converters, which have been mostly resolved. In this project I would like to perform research into promising high-power converter topologies and new control algorithms that are an improvement over existing technology in terms of power quality, cost, efficiency, and reliability. This helps Rockwell Automation Canada to develop new technologies for the next generation of the motor drive systems.

Inventing the Future of AI Applications: Applied Research in Machine Learning at AXL

AXL Labs is the technical arm of AXL, a Toronto-based venture studio that creates and launches companies focused on human-centric artificial intelligence (AI). Their main goal is to leverage human-computer interaction (HCI) and AI in designing and deploying end-to-end solutions for industry and academic applications. Organizations that partner with AXL typically have business problems where they don’t fully understand the breadth of the opportunity that a solution could provide. AXL conducts an opportunity analysis to determine high-impact business areas to develop a full-fledged solution that may alleviate these business problems. As the rapid development of AI technologies continues, organizations must determine how to best leverage and benefit from these models.
The internship is designed to tackle this challenge by building novel interactive systems that utilize advanced machine learning techniques and large language models (LLMs). This problem is particularly relevant to AXL as we aim to innovate in the AI sector, creating cutting-edge AI systems and building new spin-out companies that address market needs. In particular, the proposed project, designing a human-in-the-loop AI ingester for intaking startup ideas, such as pitch decks, founder interviews, and application forms, will aim to reduce the time taken for venture capital and investors to evaluate potential startup ideas, pair founders with potential products, and result in an accelerated feedback loop that can shorten the time it takes for a startup company to reach the broader market. We believe it is possible to create a modular prototype that can ingests the types of unstructured and semi-structured data, as described above, in a multi-modal system within the time proposed.