Leveraging Agentic AI to Detect and Mitigate Shilling Attacks for Enhanced Robustness in Recommendation Systems

This research project explores how agentic AI—autonomous AI agents with the ability to perceive, reason, and act—can be designed and deployed within recommendation systems to proactively identify and counteract shilling attacks. These attacks involve malicious users injecting fake reviews or ratings to manipulate recommendations. The project aims to develop an adaptive, multi-agent, Agentic AI-driven model […]

Read More
Designing high precision pointing systems for balloon-borne telescopes

Stratospheric balloons operate above more than 99% of the Earth’s atmosphere, allowing astronomers to observe colours of light that would otherwise be blocked or blurred by the atmosphere at only a tiny fraction of the cost of an equivalent space telescope. However, it is very challenging to ensure that to telescopes are pointing the right […]

Read More
Understanding and Improving the Reasoning Capabilities in Vision-Language Models

Vision-language models (VLMs) are considered augmentations of text-only large language models (LLMs) with additional access to the visual world. However, it is known that VLMs typically perform worse than text-only LLMs on reasoning tasks that involve only text (e.g., math word problems), raising the question of whether the benefits of visual augmentation justify the loss […]

Read More
Ventus Analytique Inc. BSI Proposal – Wind Data

Ventus Analytiques Inc. is a Canadian technology company specializing in offshore data systems and analytics, with a focus on marine environmental monitoring and renewable energy. As the company scales its operations and prepares for international deployments, there is a growing need for a cohesive cloud infrastructure and data operations strategy that can support a global […]

Read More
Map Data Analysis for Lawn Service Optimization

This research investigates the fusion of multi-source geospatial data to overcome key scaling limitations in automated property assessment. The primary research problem addresses object occlusion in satellite imagery, where features can obscure ground-level surfaces and prevent accurate area measurement. We propose and evaluate a novel machine learning approach that geometrically fuses satellite imagery with ground-level […]

Read More
Financializing Justice? The Politics of Climate Finance in Colombia’s Energy Transition

This project explores how countries are managing the shift from fossil fuels to clean energy, with a focus on just energy transitions that aim to provide an equitable transition for workers and local communities. The research focuses on Colombia’s national state-led just transition plan. By conducting on-the-ground fieldwork, the project will examine whether the financial […]

Read More
Optimization and Expansion of Eventlinx

TicketWindow Inc. is a Canadian ticketing company providing digital event management solutions to promoters, venues, and organizations. Its new platform, EventLinx, is a comprehensive, cloud-based event management ecosystem that includes a promoter portal, patron website, mobile point-of-sale (POS) application, and administrative backend. The system is deployed via edge computing infrastructure using Cloudflare Workers and Pages, […]

Read More
AI for Airplane Engine Inspection

This project aims to develop an AI-powered visual inspection system using image data from P&WC’s existing Computer Vision Inspection System (CVIS) to enhance aircraft engine assembly issue detection. By leveraging deep learning techniques, the proposed solution will address current limitations in accuracy and consistency, targeting a 100% visual detection rate for anomalies such as: part […]

Read More
Oxygen vs. Metabolites: investigating Mechanistic Drivers of Skeletal-Muscle Hypertrophy in Low-Load Hypoxic Resistance Training

Many athletes and patients use blood-flow-restriction (BFR) cuffs to make light-weight exercise feel like heavy training, but no one is sure why this type of exercise causes improvements similar to traditional exercise. Is it because the cuff blocks oxygen from entering the muscle, or because it traps byproducts (metabolites) that signal the muscle to grow? […]

Read More
Business Strategy Internship @ The forever Group

The Forever Group (TFG) is a 30-year-old Canadian owned and operated consumer-packaged-goods company that currently generates $2.5 million–$3 million in annual revenue across North America, the UK, Japan, and other export markets. To achieve its strategic goal of reaching $5 million–$10 million in the next three to five years, TFG must overcome the operational friction […]

Read More