Deep Learning based Real-time Object Recognition and Tracking for Immersive Training and Maintenance Applications

The immersive software market, which includes virtual, augmented and mixed reality, is expected to see tremendous global growth over the next five years as players from all sectors race to identify and capture market opportunities of the technology.
This project investigates into the business and technical aspects of immersive training and maintenance applications by taking various case studies.

Anatomy Detection of Cats and Dogs using Localization

The proposed work is an application of artificial intelligence and medical imaging. When positioning a dog to have an X-ray image taken of its paw, a neural network trained in canine anatomy can be configured to inform radiologists if the patient’s paw is improperly placed or even drive motorized hardware to automatically center the patient’s anatomy with respect to the imaging hardware. Diagnostic X-ray images like DICOMs contain header information about the subject including species, anatomy imaged, and the orientation of the image.

Quantum Resistant High Speed Blockchain Project

Secure, open, distributed computing platforms are able to provide trustable peer-to-peer transactions without the need for trusted intermediaries. However, as quantum-computers gain power and capability, the cryptographic systems they are built on are threatened. This project will provide the system described here with quantumresistant cryptographic protocols to ensure both system security and user privacy, and build a formal mathematical model to verify the safety and liveness of the system.

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.

Research and Data Analysis of Aycoutay Wellness Device user scans

The Aycoutay Health Screening Device is based on well-established EEG technology. It is a modern, computerized EDA based health monitoring/screening device that performs a comprehensive analysis of the bio-electrical activity of each organ and gland, as well as the critical interrelationship between them, using algorithms that translate this electrical data into diagnostic information. It is designed for wellness consumers and provides a primary diagnostic estimation or an opinion about state of internal organ systems.

Attacking Transaction Relay in Cryptocurrencies based on Dandelion++

Blockchains are a new technology that are finding applications across several domains. Participant privacy in a blockchain is a major concern for this technology, and this project focuses on studying privacy attacks and defenses in several kinds of publicly deployed blockchains. Specifically, the project will focus on how a participant’s location in the network can be determined and how a participant’s transaction can be uncovered in the context of blockchain networks that provide privacy guarantees.

Measurement and Modeling of Pandemic Effects on Door-to-Door Bottle Recycling

SkipTheDepot is a door-to-door bottle collection service based in Calgary which allows users in Calgary and Edmonton areas to request bottle recycling pickups, and the COVID 19 pandemic has caused demand for these services to increase. In order to meet rising demand, it is important to develop a clear understanding of how the service is used currently, how the service may be used in the future, and how usage affects the overall performance of the collection system.

Identification of high-frequency periodic acoustic fish tags with deep learning

Innovasea produces fish tags and receivers to track the presence and motion of fish and marine mammals while underwater. Fish tracking (acoustic telemetry) is used by researchers worldwide to determine the abundance and habits of marine life, make decisions about fishing seasons and allowed catches, and help protect marine mammals. Innovasea has developed a novel high-frequency tag technology that is suitable for very small fish and generates more precise trajectories.