Innovative Projects Realized

Temporal and spatially consistent inpainting with deep diffusion models

Most current brain imaging software is designed to work with images that have a consistent anatomy. However, this can be a problem when there are changes in the brain, like the appearance or disappearance of lesions, between two scans taken at different times. While we could develop complex new software for these situations, many researchers prefer to use existing, well-known tools, especially for studies over time. One suggested solution is to use a technique called image inpainting. In image inpainting, we fill in certain parts of an image based on a special pattern, making these parts look like they naturally belong there. This is really useful in brain scans, for example, when we need to add in images of lesions from multiple sclerosis (MS) in a way that looks real and fits with the rest of the brain image. Current inpainting methods usually practice on specific patterns, which means they might not work well on new or different types of patterns. Plus, these methods often struggle with handling lesions of various sizes and locations because they’re used to working with the same types of patterns, which limits how well they can work on different or new ones.

Building Mindset and Partnerships for Innovation in Canada: Business Strategy Internships with the Cansbridge Fellowship

This project enables interns to enable Market Innovation in Canada, related to their field of study or industry of interest. This will contribute significantly to the Cansbridge Fellowship’s mission of empowering entrepreneurially-minded students and promoting innovation in Canada. Under the guidance of the academic supervisor, the intern will focus on identifying innovative organizations for potential strategic partnerships with Canada. The intern’s multidisciplinary market research project will explore diverse technological and business opportunities, with a primary goal of aligning these opportunities with Canadian policy objectives and commercial needs. The academic supervisor will provide valuable insights into strategy and strategic partnerships, while the Cansbridge Fellowship, as a key partner organization, will offer mentorship and access to an extensive professional network. This collaborative program aims not only to equip interns with a wealth of knowledge but also to advance the partner organization’s mission of fostering collaboration and attracting forward-thinking Canadian youth. The outcomes of the market research will be made accessible to all interested stakeholders, ensuring that the research contributes to Canada’s broader innovation goals and strategic partnerships.

Archiving Groups and Athletes – Dylan Froh

Provide some background on the partner organization and their challenges or opportunities. How will this project help the partner organization address those challenges? Feel free to provide links to articles, reports or other useful information.

SkillShark Software is a SaaS model company leading the industry in making youth athlete evaluations easy. Current sport organizations do evaluations on pen and paper and spend countless hours re-entering the data onto a spreadsheet and are even then unable to provide report cards to athletes and parents. SkillShark has signed contracts with the largest youth sport orgs in the world (USSSA) as well as MLB
This project involves data life cycle. There is information which our customers (sport orgs and sport academies) want to remove from their primary view for multiple reasons. E.g. The athlete could be no longer attending their program but may return some day in which case they will want to retain historical data.

Optimal Coverage and Path Planning of Indoor Service Robots

The proposed project will study some essential tasks regarding motion planning of autonomous indoor service robots, focusing particularly on reliable coverage-planning of arbitrary and irregular-shaped indoor regions. The tools to be used in devising solutions for these problems include geometric and graph theoretical optimal path planning algorithms, various sensor data fusion techniques, and artificial intelligence and machine learning approaches. The goal is to produce methodologies and algorithms as solutions to these robot motion planning problems and to apply these solutions to provide reliable autonomous motion of Avidbots robots cleaning semi-structured indoor areas, with precise on-line monitoring, maximal area and quality of the cleaning, guaranteed collision avoidance, without requiring frequent calibration and fine-tuning.

Everly Product Iteration and Customer Retention

With this project, we aim to understand better what we can do to improve our product and customer experience to drive higher customer loyalty.

Phase 1 of this project will be to survey existing and churned customers to understand what they like, what they dislike, and what they would improve about our product. We will use tools such as Iterate (Consumer Insights Manager), and Hotjar (Behavior analytics platform) to collect customer feedback.
Phase 2 of this project will be to improve our product and website experience based on customer feedback.
Phase 3 of this project will be to test our product with existing clients and see if their feedback has improved based on product innovation. This phase will require sending samples to the consumer’s home and getting new feedback through iterate.

R&D Software Developer

The purpose of this project is to leverage Open AI fine-tuned models to enhance the speed in which consulting firms can respond to government issued RFPs. The benefit to the partner organization is enhanced speed and ability to match requirements with consultants.

CAN intrusion dataset for IDS development and digital twin simulation

In-vehicle networks of modern automobiles, particularly Controller Area Networks (CAN), are vulnerable to cyberattacks which can cause dangerous accidents. There are many CAN intrusion detection systems (IDS) that use different techniques and features. While there are several CAN datasets available from real vehicles and CAN testbeds, we identify a lack of datasets containing signals decoded from raw CAN messages, which hinders the development and evaluation of signal-based CAN IDS and prevents their comparison with other types of CAN IDS. We aim to address this gap by using open-source CAN databases to create a decoded signal dataset from raw CAN data and identify the physical values represented by the signals. Such a dataset can be used to create digital twin simulations that allow the evaluation of CAN IDS in a realistic and safe test environment and the generation of advanced attack scenarios that are lacking in current datasets. This collaborative project shall facilitate the sharing of knowledge, expertise, and insights into industry trends and best practices, as well as resources such as specialised tools and facilities, between the participating institutions. It will also enable participating researchers to expand their networks, leading to further opportunities and contributions to the area of cybersecurity.

Virtual Reality Design of a Mineral Processing Plant

This project is a collaboration between Queen’s University and BBA Engineering Consultants. With a shortage of mining and mineral processing engineers across the country, BBA is looking for way to attract more students to study mining engineering and for ways to expose their EITs from other engineering disciplines to topics in mining and mineral processing. This project will address these challenges by expanding the functionality of a Queen’s University developed Virtual Reality Concentrator that can be used as:
1. An innovative education tool at Queen’s University that will help attract high school and first year engineering students to the field of mining and mineral processing engineers, and
2. An internal training tool to give EITs at BBA exposure to mineral processing operating environments, particularly if there engineering degrees was in an other area (chemical engineering, mechanical engineering, civil engineering, etc.)

Mobile PO and Requisition Approval

Purchase Orders and Requisitions must all flow through an approval process based on an individual’s Delegation of Authority Guideline Grade (DOAG). When an approval is needed a user must be logged into the internal network, then logged into the ERP System (JD Edwards) and then search for the PO or Requisition and approve it. The goal of this project is to implement a solution that will improve efficiency by allowing individuals to use a mobile app to approve the PO or Requisition from anywhere.

La laïcité de l’État comme lien civil : conditions et limites

Mon projet de recherche vise, d’une part, à définir la place du religieux dans la genèse du lien social (philosophie fondamentale), d’autre part, à fournir un ensemble de recommandations pratiques dont l’objet essentiel est la laïcité de l’État (philosophie pratique). Ce séjour de recherche au Brésil aura pour but, sous la supervision de M. Bignotto, spécialiste reconnu de l’histoire des idées politiques, la rédaction du premier chapitre de ma thèse dans lequel j’analyserai différentes conceptions philosophiques des rapports entre religion et société, analyse dont l’enjeu pratique est de dégager un modèle cohérent de laïcité de l’État adapté aux enjeux multiculturels du Canada contemporain. Un effort important de traduction des concepts philosophiques en recommandations politiques sera fait à l’issue de cette recherche fondamentale en histoire des idées.

Purification of Single Wall Carbon Nanotubes produced by thermal plasma

Raymor Industries, a Canadian high-tech company, is at the forefront of producing advanced materials that are vital for the next-generation technologies of the Clean Tech sector. The main materials they produce are single-walled carbon nanotubes (SWCNTs) and graphene, which can be used in sustainable electronics, energy storage, and medicine. However, to fully realize their potential, they need to be purified and separated from impurities. Raymor’s subsidiary, NanoIntegris Technologies, is a world-leading supplier of high purity, semiconducting, and metallic SWCNTs, but they need to optimize their purification process to maintain their competitive edge. Through this collaborative project with Prof. Richard Martel’s laboratory, an internationally recognized leader in the field of carbon nanotube electronics, the optimal purification protocol that enables the production of high-quality CNTs and graphene via the thermal plasma process will be established. The completion of this project will provide the best possible materials that can help transform the Clean Tech sector and create a more sustainable future.

Development of computational methods for heart surgery planning.

3D modeling is crucial for effective left ventricular assist device (LVAD) implantation by providing surgeons with precise, personalized visualizations of the patient’s heart anatomy. The proposed technology will allows for detailed preoperative planning, optimizing the placement of the LVAD within the left ventricle. The accuracy and individualized approach afforded by 3D modeling will contribute to improved surgical outcomes.