Change point detection algorithms to assess pilot’s reactions to malfunctions

In this project the intern will work with time series data containing different parameters from a flight simulator. The intern will take these data and assess different learning as well as change point detection algorithms that can identify and segment pilot reactions to malfunctions and assign these reactions a proficiency metric. One of the possible approaches would be to assess the use of change point detection algorithms using a data driven approach. This will allow the partner organization to understand important segments of the flight data where large changes have taken place.

Application of Topology Optimization for Efficient Composite and Additively Manufactured Structures

Additive manufacturing offers new opportunities for designing high performance composite structures. However, sophisticated numerical approaches are required to tackle the complex task of designing structures which take full advantage of additive manufacturing capabilities. The proposed research project aims to apply topology optimization, a numerical approach capable of determining the best shape of a structure, to develop a design process producing optimal composite sandwich structures which include a 3D printed core.

Semi-supervised and unsupervised method to increased database labels in the case of classes imbalances

The project aims to improve the amount of labelled samples in a semi-automatic or automatic manner using AI to impove a CNN performance. We will test various state-of-the-art AI methods, in the context of forest inventory, and select the most effective ones.

The benefits will be significant because labelling is an important but tedious task, in many cases, when working with natural forests, some tree species will not occur as often as others (hence creating a shortage in some classes), also there can be co-species to many other species and they are difficult to identify clearly.

Food Catering Ontology to Enhance UEAT's Recommendation System

Integration of an ontology for the representation of restaurants, menus and dishes for the catering industry and construction of a recommendation model using this ontology.

Enhancing interpretability of gaze-tracking convolutional neural networks

Innodem Neurosciences is developing a visible light gaze-tracking algorithms that can be sued to predic a user's gaze position on the screen of a mobile device without the need for any third-party hardware. This algorithm leverages various image processing techniques, and relies on the use of convolutional neural networks and computer vision. Enhancing the quality of this gaze prediction network will be the primary goal of the resident scientist over the course of this project.

Fall and Head Impact Acceleration Monitoring of Short Track Speed Skaters

Short track speed skating is a fast-paced sport where athletes routinely reach speed above 50 km/h. It is one of the leading Canadian sports for medal count at the Olympic games. Unfortunately, given the fast-paced and pack-style skating, athletes often fall on the ice, which may lead to concussion. There is no clear data on the incidence of falls in short track speed skating, nor is there a clear understanding of the mechanism of head impact.

Therefore, this project will track the incidence of falls and measure head impacts that may lead to concussion using ‘smart’ mouth guards.

A Novel Bone Anabolic Treatment in Mouse Models of Pediatric Bone Fragility Disorders

Children that break their bones repeatedly often have genetic conditions that either affect bones directly or indirectly. The drugs that are currently used to decrease the number of fractures in children are only partially effective. Mesentech Inc. has developed a new drug that has shown a strong effect on bone formation in rats. In this project, we will test the effect of this drug in mouse models of a condition that affects bone directly (osteogenesis imperfecta) and a condition that affects bone indirectly (Duchenne Musclar Dystrophy).

Multi-chip Integration of Lasers and Silicon Photonics

In the era of big data, internet of things and cloud computing, the ever-increasing demand for bandwidth density causes a bottleneck in inter and intra-datacenter communication systems. Optical integrated circuits based on the silicon-on-insulator platform is a well-known solution to overcome the bottleneck in data rate transmission. It is an interesting platform as it can be fabricated through existing CMOS technologies and the high index-contrast between core and cladding helps realize compact, and low loss structures.

Multifunctional Life Cycle Assessment (LCA) of the HubTrack helical transmission system for its application in transportation sector

With the latest measurements and experimental tests, we have strong evidence that the HubTrack is energy efficient and ecologically sound for a multifunctional transportation solution. Currently, the latest HubTrack operational system has reached the stage of pre-commercialization with an industrial standard compliant model based on monorail standards.