Consulting
AI Agent Integration
Build a governed AI platform that enables intelligent agents to support complex business work and informed decision-making.
Consulting
City of Kingston Urban Planning Model
Built in collaboration with the City of Kingston, this project treats property valuations as strong indicators of an area's economic activity and provides a multi-model spatial econometric system to support urban planning.
Consulting
Cognitive Chain RAG
Built in collaboration with AI4Support, a London-based company focused on transforming how enterprises access and trust their knowledge, Cognitive Chain RAG is a Retrieval-Augmented Generation system that reasons in steps rather than stopping after a single search.
Consulting
Conversational Intelligence for Advanced Process Control
Explore a conversational AI framework that explains complex Advanced Process Control behaviour to engineers and operators in mineral processing.
Consulting
DCP Federated Learning
Build a proof-of-concept federated learning package on DCP so hospitals can train a shared machine-learning model without sharing private data.
Consulting
MiCRA
Built in collaboration with Project X Ltd., a Toronto-based AI and data consulting firm, MiCRA is a multi-modal content-repurposing agent that ingests long-form company content such as call transcripts, papers, and videos.
Consulting
PostopCare
Built in collaboration with PostopCare, a Canadian AI healthcare startup, this project replaces printed post-operative handouts with digitized instructions patients access via QR code. Already proven in a clinical setting, the platform lets clinicians upload their own documents to automatically generate a new webpage and QR code.
Consulting
QMIND x OpenJustice
QMIND x OpenJustice enhances the Queen's Conflict Analysis Lab's OpenJustice tool by integrating a robust Model Context Protocol (MCP) server.
Consulting
SmartCV
Built in collaboration with Technical Management Group Ltd. (TMG), SmartCV is an automated pipeline that converts heterogeneous resumes into standardized, company-specific CV formats.
Consulting
TrustLayer
Develop a responsible AI evaluation system that assesses AI-generated outputs and actions before they enter real-world workflows.
Research
A Deep Learning Approach to Cardiac Image Segmentation
Using modified U-Net architectures, this project builds accurate, efficient segmentation models that perform well on small, complex datasets, aiming to automate a task cardiologists and radiologists currently perform manually.
Research
ARES (Adaptive Reinforcement Ensemble Strategy)
ARES is an adaptive ensemble strategy that trains three deep reinforcement learning agents (Proximal Policy Optimization, Advantage Actor-Critic, and Twin Delayed Deep Deterministic Policy Gradient) on a diversified universe of nine ETFs spanning U.S. and international equities, fixed income, commodities, and real estate.
Research
Ascensi: Adaptive Maze Agent
Ascensi is an intelligent maze-generation agent in Unity that dynamically creates solvable mazes matched to a chosen difficulty level.
Research
Beyond AUROC: Clinical Readiness of ED Chest-Pain AI
Evaluate what evidence is needed before chest-pain AI models can be trusted in real emergency-department decisions.
Research
Beyond Bill C-27
Beyond Bill C-27 examines the proposed Artificial Intelligence and Data Act (AIDA) and its weaknesses through legislative analysis, case studies, and comparison with international models.
Research
CanopyMap
Use computer vision to measure plant growth in indoor farms and help automate growth-optimization decisions.
Research
De-biasing Robotic Actions
De-biasing Robotic Actions trains standard classifiers (Logistic Regression and Balanced Random Forest) on the MLG-ULB Credit Card Fraud dataset and demonstrates baseline violations of EU AI Act fairness thresholds.
Research
DeepfakeGuard
DeepfakeGuard is an open-source Python library that unifies three complementary deepfake detection modalities behind a single API: a DINOv3 Vision Transformer detector, a LipFD audio-visual detector, and a training-free D3 motion detector.
Research
ECHO (Everyday Context-aware History & Outcomes)
ECHO is a system that collects, parses, categorizes, and indexes a user's everyday work.
Research
Framework for Mitigating Dataset Inequities in AI Models for Alzheimer's Disease Diagnosis
This project surveys the current landscape of AI in Alzheimer's diagnosis through a narrative review while developing a prototype model using MRI image classification, with experimental results from a fine-tuned ResNet-34 architecture.
Research
Interpreting Brainwaves with Self-Supervised Learning
This project presents a general-purpose foundation model for electroencephalography (EEG) data built with self-supervised learning.
Research
LLM-Enhanced Decision Making Agents for Cloud Autoscaling
Explore whether large language models can improve dynamic cloud resource management through context-aware autoscaling decisions.
Research
LLMs and Mental Health Vulnerability through Prompts
To evaluate how LLMs respond to vulnerable users, this project administered 340 synthetic prompts to ChatGPT-4, ChatGPT-5, DeepSeek, and Gemini and analyzed the outputs through thematic analysis.
Research
Mechanistic Interpretability of Test-Time Reasoning in Large Language Models
Build an interpretability toolkit to investigate the internal circuits behind uncertainty, branching, premise commitment, and error recovery in reasoning models.
Research
NFL Predictor
NFL Predictor is a machine learning pipeline that leverages historical NFL data to predict key player and game performance props.
Research
ScamBench AI Recruitment Phishing
Study how AI-generated recruiter profiles and deepfakes influence trust and security decisions during multi-step remote job scams.
Research
TriAID
TriAID is an image-plus-LLM triage platform that ingests DICOM studies and automatically prioritizes them for radiologist review.
Research
Uncertainty-Aware Deep Learning for Parkinsonian Motor Symptom Severity Estimation from Monocular Video
Use monocular video and uncertainty-aware deep learning to estimate Parkinsonian motor symptom severity while communicating when the model is unsure.
