Improving Monitoring and Decision-making with Uncertain Sensor Data

Terrestrial contaminated sites – such as abandoned oilfields, chemical spill sites, or former industrial zones – are a major environmental problem in Canada and around the world. Environmental Material Science has created new environmental monitoring equipment that generates high-resolution spatially and temporally explicit data on environmental quality. The data must be visualized and then used to make decisions regarding if site remediation needs to occur, or if occurring, if site remediation should stop.

Modelling the Non-Condensable Gas (NCG) in SAGD infill wells– Part 1

In the last decade optimization is expanded in many applications from food production to sophisticated applications such as engine fuel efficiency. In the proposed package, it is tried to apply optimization techniques along with physics based analytical and semi-analytical methodologies to create a compelling framework which can help thermal-process based oil industry to reduce their GHG and also better evaluate their CAPEX. Many SAGD projects are overspent on their facilities due to under prediction or overprediction of their oil production expectations.

Opportunities for and impacts of community-scale biomass and waste heat district energy systems in Canada

Solid biomass, of which Canada has plenty, is the lowest cost, and greatest employment generating, renewable heat source available but to date but is not often considered as a low carbon heating option for deployment on a large scale in Canadian cities. For solid biomass to reach a high market share, a key enabling infrastructure is required: district energy systems (DES). While there are existing DES in Canada, they provide less than 2% of all building heat in the country.

Prototyping and Industrial Testing of Novel Non-Consumable Thermocouples/Sensor Holders in Molten Steel

Secondary metallurgy is the most value adding step in the steelmaking process. As more sophisticated steel grades are developed, better process control is required to adjust and monitor properties of molten steel in secondary metallurgy. Improved process control also serves to increase productivity and profitability of steel mills. In steelmaking, process control is achieved through feedback from sensors. Unfortunately, existing state-of-the-art sensors for molten steel are consumable, unreliable, and provide limited measurements.

Unsupervised Learning Based Approach for Insider Threat Analysis

Insider threat is one of the most damaging security threats to the safety of data, systems, and intellectual property of institutions. Typical threats caused by malicious insiders are trade secrets / intellectual property theft, disclosure of classified information, theft of personal information and system sabotage. Malicious actions of insider threats are performed by authorized personnel of organizations, which may be familiar with the organizational structure, valued properties, and security layers.

Explorations into the mechanism and potential of the antiviral activity of BOLD-100 as a treatment for COVID-19

BOLD-100 is a promising new drug that initial studies have shown has potent activity against the SARS-CoV-2 (the cause of COVID-19) in cell culture experiments. Before being able to start clinical studies with BOLD-100, additional research into the mechanism of action is required, plus testing the safety and efficacy of BOLD-100 in animal models of COVID-19. The purpose of this project is to utilize a range of cell culture and animal models to test BOLD-100 against COVID-19 to better understand the drug.

Multi-institute domain adaptation by adversarial constrained medical time series representation learning

Hospitals strive to perform cutting edge medical treatment, treat all patients fairly, and reduce operating costs, while also enabling caregivers to spend more time interacting with patients. Artificial intelligence and machine learning promise these things. However, medical data provides unique challenges for machine learning. Currently, if a hospital wants to include an algorithm for automated decision making, they must either secure approval to collect additional patient data or change their care practices to replicate those at other institutions.

Development and Application of Marine Mammal Density Estimation Methods for Directional and Omnidirectional Hydrophones

Estimates of the population density of marine mammals in an area and the change in population over space and time are critical inputs for managing the interactions of human activity and mammal populations. Visual surveys from boats, shore stations, and aircraft have served as the basis for most population estimates currently used by managers. However, these survey methods are generally only performed in good weather conditions and require many trained observers. These factors make visual surveys expensive and reduce the temporal and spatial coverage of population estimates.

bridgeVUE – leveraging emerging technologies for safer and more efficient marine navigation.

Navigation at sea is a complex and comprehensive task. Combined with the challenges of navigating in heavy traffic, and avoiding dangers in low light and low visibility, it becomes considerably more difficult. This project, bridgeVUE, leverages an emerging technology to enhance marine navigation by contextualizing radar data over an individual’s field of vision, in real time.

Development of Conversational Agents and Applications in Playful Environments

In this project I will be making a talking, artificial intelligence prototype that provides meaningful, playful exchanges in different interactive settings. By taking advantage of the latest advances in machine learning and creating a model founded on knowledge from social and cognitive sciences, I will build a series of digital avatars to test how they interact with users. This research-creation project connects to other disciplines like Human Computer Interactions (HCI).