Anomaly detection from system logs through deep learning

During the last decade, we observe in organizations a surge of numbers of cyber-attacks originating internally. In this project, we aim to develop deep learning models to detect suspicious activity (such as malicious events, system failure or attacks) from log data generated by the Desjardins ecosystem.

Read More
Digital Twin for Civil Engineering Design Workflow

McElhanney provides Engineering and Surveying services across Canada. They want to leverage the AI feature extraction work conducted in 2021 – 22 (Mitacs Accelerate IT23104) whereby the University of Alberta interns helped to extract physical municipal assets (fire hydrants, street lights, manholes, curbs, etc.) from detailed terrestrial laser scanning (TLS) data, i.e., LiDAR point-clouds. This […]

Read More
Lab2Market West: Advancing echocardiography scanning through multiview fusion using robotics and machine learning

Echocardiography is widely used for scanning cardiac patients to assess the health of their hearts. Despite its wide use, echocardiography suffers from a few limitations, including the limited field-of-view and longer scanning times. We propose a product using a collaborative robot arm to overcome these limitations. Our project allows scanning the heart from different locations […]

Read More
AI-enabled food waste differentiation for at-home compost nutrients estimation

The main goal of this project is to digitalize food waste at home for a sustainable future using at-home composters. We will develop dedicated machine learning algorithms to detect, segment, and classify various food waste generated in the kitchen, making it possible for everyone to immediately estimate the quality and nutrients of the generated compost […]

Read More
Project Title – ezPT Technologies Ltd

Our company is developing an AI-powered clinical documentation platform. In the proposed project, the intern will assist us in building robust and scalable cloud-based web applications for operations carried out in Outpatient Physical Therapy clinics. They will support the design and security of our cloud infrastructure to comply with HIPAA and other privacy regulations and […]

Read More
Automated Data Labeller

All data-driven solutions today start with the ingestion (input) of data. Typically that data is messy and unlabelled. However, downstream consumers of data benefit from well-labelled data. Data labelling (assigning categories, data types, privacy and sensitivity tags, source characteristics, etc.) is usually an error-prone, time-consuming, manual effort. There are no readily available off-the-shelf tools that […]

Read More
Transformational Specification of Out-of-Thin-Air Memory Models

Much of the performance in today’s computing devices such as mobiles, desktops, supercomputers, etc. can be attributed to concurrency – the ability to perform more than one task simultaneously. In addition, performance of software that run on such devices greatly benefit from the compiler (software that translates our code to be run by hardware) that […]

Read More
Domain incremental learning in forgery detection

Digital image forgery has become a worldwide pandemic, with many forms of forgery (e.g., insurance fraud, fake news, identity theft) negatively affecting our life. This effect could be attributed to the accessible costs of mobile phones and digital cameras, which has led to an exponential proliferation of digital images, and the availability of many image […]

Read More
Transformation of healthcare data management using blockchain technology

The healthcare industry is focusing on utilizing emerging technologies to make healthcare systems secure, interoperable, and efficient. Blockchain technology offers promising features, such as immutability, security, traceability and decentralization, appropriate for clinical healthcare interoperability and data sharing. This project is part of Lab2Market program, which provides a commercial opportunity to utilize blockchain technology, a new […]

Read More