Stable Manipulation with Offline Model-based Reinforcement Learning

In this project, we would like to study the problem of object manipulation in a real-world scenario. We assume three major settings in the environment – the object is non-rigid, oniy offline dataset is available and the input is high-dimensional images which are hard to be handled by classical control models. Recent successes in deep […]

Read More
What athletic therapists need to know about pain and pain medication: an evidenced based approach

The Canadian Athletic Therapy association (CATA) is the governing board for athletic therapist, health care professionals who rehabilitate athletes who are injured or in pain. Over-the-counter and prescription medications are often used by athletes as a pain management strategy, although they can have negative impacts on their health if misused. Since Athletic therapists follow athletes […]

Read More
Hypatia-Learn: State of the Art Mathematics Learning and Tutoring System

The project revolves around reading and understanding students solution to various mathematical problems. We wish to analyse the work done by students and the solution to these problems and provide math checking capabilities to various types of problems. Furthermore, this project looks to construct a virtual tutor that can analyse students work and provide feedback […]

Read More
A Predictive Cluster-based Machine Learning Pricing Model

Dynamic pricing models create price by assessing total cost, demand, and timing to customize the price to the moment. The models enable both buyers and sellers to settle a price that is very custom to their specific needs. Bison Transport Inc. has a network model that monitors profit and a pricing engine that monitors margin. […]

Read More
Multi-Object Tracking in Production Environments

Multi-object tracking has many uses cases in autonomous driving, robotics and security. Tracking is important as it allows us reason about the dynamic world and make actionable decisions based-off predicted object trajectories. As an example, in autonomous driving, not only the location of objects is important but also their predicted future trajectories are needed in […]

Read More
Cloud platform for machine learning

Surgical Safety Technologies aims to provide healthcare professionals with the opportunity to perform research in areas of surgical performance and education and implement evidence-based solutions to improve patient safety. Search on video content would an ideal functionality to assist with healthcare professionals’ research. This project uses computer vision model to rank the relevance of the […]

Read More
Assessment of neuromuscular, cardiorespiratory, and cognitive performance in running and hopping tasks using wearable sensors

The objectives of this research project are (a) to record neuromuscular, cardiorespiratory, and cognitive related data using wearable sensors during running and hopping as two basic activities of many sports; and (b) convert the data to medically meaningful indicators of athletic performance and risk of injury using signal processing and machine learning algorithms. The project […]

Read More
Predicting population level effects of microplastics ingestion on the behaviour of fishes

High numbers of microplastics are currently present in freshwater lakes, rivers and ponds. Fish are known to mistake microplastic particles for food, then behave differently after eating them. As changes in behaviour are often the first line of defense against human-induced rapid environmental changes, monitoring these behavioural changes can tell us how pollutants, like microplastics, […]

Read More
An end-to-end IoT framework for reliable remote and contactless measurement of biometric data

Veyetals online smartphone-based application that can be downloaded through the Apple Store or the Google Play Store. It uses Remote Photoplethysmography (rPPG) technique to extract Blood Volume Pulse (BVP) signal from a face video captured using smart phone camera, and then applies multiple computational algorithms to measure heart rate, heart rate variability, oxygen saturation, and […]

Read More
Dosage of admixture for 3D printing based on optimization

Many chemicals can be used for the mix design of concrete 3D printing. With a traditional experimental approach, the number of experiments to conduct is exponential. The objective of this study is to develop a cement-based material suitable for 3D concrete printing applications by utilizing optimization and predictive algorithms. The question to answer is if […]

Read More
Energy and exergy analysis of refrigeration systems for refrigerated cabinets

Major efforts have been undertaken to reduce ozone depletion substances (ODS) used in refrigeration systems such as hydrofluorocarbons (HFC). Carbon dioxide (CO2) is recognized as safe, economic and environmentally sustainable. Commercial transcritical CO2 (R744) refrigeration systems have emerged as leading technologies in food retails, especially in cold climate countries. Major research and development challenge is […]

Read More