Innovative Projects Realized

Quantum Federated Learning in Distributed Systems: Challenges and Future Directions

This project reviews quantum federated learning (QFL) for non-IID and heterogeneous distributed systems. Practical federated learning systems often involve clients with different data distributions, device capabilities, and communication conditions, which can lead to unstable aggregation and degraded global performance. QFL provides a promising direction by combining federated learning with quantum neural networks and parameterized quantum circuits.

The project will organize recent QFL studies from the perspectives of aggregation strategies, quantum circuit architectures, data encoding, communication cost, and device heterogeneity. It will also discuss future research directions for architecture-aware QFL, including the potential role of quantum neural architecture search (QNAS) for adapting quantum circuit structures to different clients, data distributions, and resource constraints.

Over the Air Quantum Federated Learning

This project investigates the fundamental theoretical boundaries of deploying Quantum Federated Learning over next-generation wireless networks. The scaling of distributed quantum intelligence is currently bottlenecked by the short coherence times of quantum hardware. While analog Over-the-Air (OtA) aggregation solves this latency issue by physically superimposing radio waves for instant computation, it creates a severe mathematical conflict: OtA operates in flat, Euclidean space, whereas quantum circuit parameters reside on curved manifolds governed by complex Lie algebras.

This research will mathematically bound the non-linear structural distortion caused by raw analog channel noise and design novel, noise-resilient quantum ansätze to survive it. By merging Korea University’s expertise in Quantum Machine Learning and differential geometry with Memorial University of Newfoundland’s leading expertise in physical-layer wireless communications, this project will deliver a joint communication-computation framework. Ultimately, it provides the theoretical blueprint required to achieve zero-latency, industrial-scale quantum edge networks.

International Comparison and Standardization of Implant Outlier Detection Methods in Total Knee Arthroplasty Registries

Joint replacement registries are essential for ensuring the safety and effectiveness of medical implants used in knee replacement surgery. By tracking implant outcomes over time, these registries help identify designs that fail more often than expected so they can be reviewed or removed from clinical use. However, different countries currently use different statistical methods to identify poorly performing, or “outlier,” implants. This lack of consistency limits international comparison and shared learning.
This project is an international research collaboration between the University of Waterloo and Leiden University Medical Center in the Netherlands. The research will compare how national joint replacement registries, including those in Canada and the Netherlands, analyze and monitor implant performance. Working with experts from the Dutch Arthroplasty Register, the project will examine how different analytical choices, such as risk adjustment and comparison strategies, affect which implants are flagged as potential concerns.
The objective is to develop a standardized approach to implant performance monitoring that could be applied across countries. Improving consistency in registry methods will support better decision-making by clinicians and regulators and ultimately enhance patient safety worldwide.

A Market Analysis of Growth Opportunities for Trusti in the In Vitro Diagnostics Sector

The intern will support trusti’s development and commercialization of rapid STI diagnostic solutions by contributing to market analysis, partnership development, and product advancement initiatives. Responsibilities include supporting regulatory and clinical trial preparation, evaluating market access opportunities, and assisting with commercialization and fundraising efforts aligned with key company milestones, including international expansion and product portfolio growth. Through this work, the intern will gain hands-on experience in health technology commercialization while contributing to the growth of a Canadian biotech company improving access to diagnostics and strengthening Canada’s bio-economy and health innovation workforce.

RadiCare Digital Infrastructure Project

RadiCare Ventures is a Calgary social enterprise that delivers property maintenance and public space cleaning services while creating stable jobs for people facing barriers to employment. Building on the software platform an intern developed last summer, this project will expand RadiCare’s internal technology into a reliable end to end system that tracks every job from start to finish, gives each client a clear self serve view of their service, and uses artificial intelligence to support staff with reporting and incident review. The intern will also train the team and document the system so RadiCare can run and grow it independently. The result is a small but mission driven Canadian organization spending less time on manual administration and more time creating impact and jobs in the communities it serves.

Business Strategy and Learning Innovation for Safety Buzz Campus

This project will support the development of a business strategy and learning innovation plan for Safety Buzz Campus. The work will focus on strengthening the organization’s digital training offerings through the design and development of Moodle-based safety courses, while also examining opportunities for growth, improved learner engagement, and scalable delivery. The intern will contribute to course development, pedagogical planning, and business strategy activities that help Safety Buzz Campus expand its online safety education platform and better serve learners, employers, and industry partners.

Machine Learning-Based Assessment of Masonry Degradation in Cold and Hot Climates

Heritage masonry buildings are deteriorating at an accelerating rate due to aging, weathering, and environmental exposure. Early and accurate detection of surface defects such as cracks, mortar loss, and spalling is essential to prevent progressive structural damage and enable timely, cost-effective conservation. However, current practice relies predominantly on manual visual inspection, which is subjective, labor-intensive, hazardous, and incapable of producing the quantitative defect data needed for evidence-based maintenance planning. This project develops an automated computer vision inspection system for heritage masonry buildings using deep learning to detect, classify, and quantify surface defects. A dual-climate annotated image dataset spanning heritage sites in Saskatchewan, Canada and Kuwait will be compiled and used to train and validate instance segmentation models. The research will also produce a Masonry Condition Index (MCI) translating model outputs into actionable condition scores for maintenance prioritization. The project establishes a research collaboration between the University of Saskatchewan, Canada and the Australian University, Kuwait, focused on AI-driven heritage infrastructure assessment and the training of a highly qualified person. Outcomes will support more efficient conservation of Canada’s built heritage and contribute to the growing field of automated infrastructure inspection nationally and internationally.

Graph Neural Networks for Drug Discovery at Simmunome Inc.

This project will help Simmunome Inc. better evaluate and explain its machine learning models for biomedical discovery. Simmunome uses biological network data, such as relationships between proteins, genes, pathways, and disease targets, to support decisions about which biological targets may be worth investigating further. The intern will build a structured testing process to compare Simmunome’s current graph-based model with simpler models, standard graph models, newer state-of-the-art methods, and control models where the graph structure is changed or removed. This will help determine when graph-based modelling truly improves predictions. The intern will also develop methods to explain model predictions by identifying the proteins, connections, pathways, or interaction patterns that most influence a result. The expected benefit is a clearer and more reliable evaluation toolkit that helps Simmunome improve its models, understand when predictions can be trusted, and communicate results more clearly to scientific users, clients, or collaborators.

Business Process Improvement and Innovation

This project will help improve how RadiCare Ventures manages its internal operations as it continues to grow. RadiCare is a social enterprise that provides professional services while creating job opportunities for people facing barriers to employment. The intern will work on creating clear step-by-step workflows, setting up a system to track staff and client contracts, and building a simple, consistent training program for employees. These changes will help reduce time spent on manual tasks, keep important deadlines organized, and make day-to-day work more efficient. By making processes more consistent, RadiCare will have a stronger foundation to grow its services without losing quality. Overall, this will allow the team to spend less time dealing with administrative issues and more time focusing on supporting the community and delivering its services.

Use of generative AI to accelerate the utility of Oracle NetSuite platform

Through Mitacs Accelerate project, SwifTEST plans to hire an artificial intelligence expert to work with them on conducting research and development activities as well as developing an artificial intelligence component of their software. The end goal of the project is to finally develop a no code approach which can offer customers the ability to create test cases using natural language and/or offer suggestions/auto creation of test cases.

Agentic AI Pipeline for Phishing Detection, Investigation, and Response

Phishing remains one of the most common and high-impact threats affecting organizations using Microsoft 365, often serving as an entry point for credential theft, malware delivery, and business email compromise. Security Operations Center (SOC) teams must manually triage large volumes of phishing-related alerts by extracting indicators of compromise, validating them through threat intelligence sources, correlating contextual evidence, and producing incident reports. This process is repetitive, time-consuming, and can lead to inconsistent classification and delayed response.

This project will develop an Email Investigator Agent that automates key phishing triage activities, including alert ingestion from Microsoft 365 Defender, indicator extraction and normalization, multi-source threat intelligence enrichment, and LLM-assisted classification. The system will generate structured SOC-ready incident reports with evidence-based severity scoring, classification rationale, and recommended response actions, while distinguishing phishing attempts from spam and benign email traffic.

Designed as a decision-support tool, the solution will keep analysts in control while reducing manual workload, improving consistency, and enabling more scalable phishing detection and response operations.

Modular Garden System Sales and Marketing- Mitacs BSI

One Health Medical Technologies (OHMT), a Saskatoon-based biomedical engineering firm, has developed a high-potential Modular Gardening System. While the product is technically sound, the organization currently lacks the dedicated commercial infrastructure to transition this innovation from the research-and-development phase into a self-sustaining venture. This project seeks to bridge that gap by establishing a scalable commercial foundation for the modular garden and future consumer-facing products. The primary objective is the design and implementation of a comprehensive market entry strategy, initially targeting Saskatchewan before expanding to neighboring provinces. To achieve this, the intern will focus on four key areas: Market Identification: Vetting local businesses and garden centers for B2B partnership opportunities. Strategy Development: Creating a lean marketing plan that balances digital presence with physical outreach, accounting for seasonal growing cycles. Content Creation: Producing a suite of digital assets and short-form videos to demonstrate the system’s value proposition. Direct Engagement: Conducting cold calls and “walk-ins” to secure the first wave of commercial distributors. This internship provides significant benefits to all stakeholders. OHMT will receive a repeatable commercialization playbook and an established network of retail partners, driving increased revenue and domestic innovation. The intern will gain hands-on entrepreneurial experience, applying academic business theories to a startup environment while developing specialized skills in B2B negotiation and digital strategy. Finally, the project supports Canadian food security by promoting sustainable, accessible gardening technology within the domestic market