Sparse Representations for Embodied AI

Understanding scenes representing real world environments is a challenging problem at the intersection of Computer Vision research and Deep Learning and a necessary pre-requisite for Embodied AI. Embodied AI is an emerging field within Machine Learning that focuses on the challenges that need to be addressed for successful deployment of edge devices such as drones […]

Read More
Durability of EV’s Battery Pack Joints

To address the global concerns regarding climate changes and increase of earth temperature, carbon dioxide emission has to be removed/reduced. A major source of Co2 emission is transportation vehicles, which account for close to 30% of Canada’s greenhouse gas emissions. An active method to reduce this significant contribution to global warming is electrification of transportation […]

Read More
Detection and Classification of Pavement Defects Using Computer Vision

The objective of the project is to automate the detection of pavement defects. Defects can be of different types: cracks, deformations, potholes and others. These defects are cataloged and detailed in standards established by the Quebec Ministry of Transport in Quebec and various authorities in other regions of the world. At present, the inspection of […]

Read More
Development of a 3D Laser Scanning System for Generating Prototypes of Buildings and Large Scale Structures

Virtual Prototypes provide a fast and efficient way to visualize objects or products during their design phase. In architecture, engineering and various construction projects 3D models are used throughout process, from design, through construction, and into the facility management phase. An accurate 3D scan could represent a built region in a virtual world. The 3D […]

Read More
An active video game for rehabilitation therapy of children with musculoskeletal disorders

Children with musculoskeletal disorders, such as Cerebral Palsy (CP), must follow regular, intensive rehabilitation to improve their movement patterns and walking ability. Often, these protocols are perceived negatively by children, who would rather play and have fun. The use of active video game based training programs could help reduce participant attrition while improving engagement and […]

Read More
Automated Tunnel Inspector

High-resolution visual and spatial models are transforming traditional methods of inspecting heavy civil infrastructure. These models overcome the inaccuracy and uncertainty of traditional inspection methods and enable infrastructure owners to assess deterioration and prepare plans for repair. Despite photogrammetry being the fastest method of collecting data for these models, it is slower than a traditional […]

Read More
Modeling of flow in heat exchangers optimised for additive manufacturing

The proposed research aims to 3D print a series of heat exchangers in plastic and metal to optimize the pressure drop and heat transfer. An initial prototype will produce experimental data to validate a numerical model, which can then be used to rapidly evaluate future heat exchanger designs. Optimizing the pressure drop and heat transfer […]

Read More
A Prospective Model for Predicting Driver Workload, and Safety Related Distraction, using Heterogeneous Data and Machine Learning

There is an increasing amount of potentially distracting information being made available to drivers. However, applications (e.g., for navigation, work, entertainment, etc.) need to be aware of driver workload so that they don’t create unsafe distraction. This work is important because distracted driving is a major risk factor for road accidents and the threat of […]

Read More
Development and validation of SafeSleep, a smart, accessible, and convenient textile-based technology for remote monitoring of sleep apnea in high-risk population at home

Sleep apnea, which affects 10% of adults, is a disorder that causes breathing to repeatedly stop during sleep, leading to reduced blood oxygen and fragmented sleep. It increases the risk of HF by four times, of hypertension or stroke by three times, and doubles the risk of car accidents. Health care utilization is doubled in […]

Read More
Integrating Reservoir System Information for Cyclic Solvent Injection Process to Support Post-CHOPS Field Development

Heavy oil (high viscosity oil) is trapped underground. Cold heavy oil production with sand (CHOPS) is an enabling technology to extract heavy oil through wormholes forming around wellbore. There are thousands of CHOPS wells in Saskatchewan and Alberta with low primary oil recovery. Cyclic solvent injection (CSI) enhanced oil recovery process stands out as one […]

Read More
Development of an On-body Sensor Network Usinga combination of INS and USID System and itsapplication to ExoLegs™

Bionik Laboratories Inc. has developed ExoLegs™, a battery powered, motor driven, robotic pair of legs intended for use in rehabilitation and mobility enhancement of individuals with paraplegia. ExoLegs represents a technology that improves rehabilitation and recovery of paraplegics and reduces secondary health issues that result from confinement to wheelchairs for extended periods. The proposed research […]

Read More