The objective is to develop a real-time fraud detection algorithm for a large E-commerce company based on construction of a robust reference model from normal multivariate data. To accomplish this, we propose to leverage machine learning techniques, such as reinforcement learning, in combination with stochastic modeling techniques such as Hidden Markov Models, to provide both […]

Two Hat Security is a company that develops next generation moderation tools for social networking apps. Since images are of the most important data shared by social networking apps, an important problem for the company is to identify images that are unsafe or inappropriate. In particular, images containing certain objects (e.g. knife, gun, bikini, etc.) […]

The proposed research project will conduct feasibility studies on the purification and conditioning of industrial, hemicellulose derived C5 sugars from a number of potentially commercial liquor fractions, derived from lignocellulosic biomass. In the first two Mitacs projects, enzyme hydrolysis showed considerable benefits over traditional acid hydrolysis for S2G’s bio-glycol production. However, relatively high enzyme loadings […]

Increasingly prevalent patient violence within the dementia population is a challenge to long term care providers. Violent incidents can lead to serious musculoskeletal and neurological health complications. I propose to use video surveillance and a novel brain monitoring system in a care facility-based elderly population, to monitor violent episodes and brain vitality after incidents. This […]

The great number and variety of factors influencing the survival of migrating salmon smolts in the early marine environment makes it difficult to understand the causes of recent declines in smolt survival and salmon population productivity. We will combine novel methodologies (biotelemetry and biomarkers) simultaneously to examine a variety of factors influencing the migratory behaviour […]

Peanut is one of the leading foods that can cause food allergies. An extremely low amount of peanut protein is sufficient to cause mild reactions in people who are sensitive to peanut. Over 90% of allergic reaction cases derived from peanut digestion are related to Ara h 1, a glycoprotein that comprises about 15% of […]

Nucap developed a new bonding technology (GRIP Metal™) that has been primarily used to connect backing plates with braking pads used in automotive disk braking systems. Nucap wishes to explore the technology towards different applications. In this proposal, fibre metal laminates used in the aerospace industry, in particular, GLARE (glass laminate aluminum reinforced epoxy) will […]

This project is aimed at using machine learning algorithms and techniques to enhance the current state of the art of missing tooth detection in mining monitoring systems. Unlike heuristic approaches that follow strictly static program instructions, machine learning techniques operate by building a model from example inputs in order to make data-driven predictions or decisions. […]

Pesticide detection in water has become a high priority worldwide, from protecting the population from environmental contamination due to agricultural pesticides, and bio-threats from terrorist activities. An exhaustive characterization of water pollutants requires laboratory-based analyses which are inherently slow and expensive. Thus, regarding the above mentioned pesticide contaminations, developing a real-time and in-situ detection technique […]

New emerging Virtual Reality (VR) technologies and mobile devices are changing the way that we are interacting with computing technology. The partner organization has a multimedia product that is used to train technicians to perform various maintenance tasks or introduce them to the interconnected components of a machine. The goal of this project is to […]

Experiences in early childhood are fundamental determinants of lifelong well-being. In this project, we will give voice to Aboriginal families and caregivers on what they believe is important to the well being of their young children. A methodology adopted from social psychology, called ‘echo’ enables the values and beliefs of the population of interest to […]

ET-LBC technology (Evapotranspiration-Landfill Biocovers) is the capital intensive emerging modern landfill technology. The acceptance of this technology by landfill regulators and operators, and its possible future participation in carbon credit trading depends on its performance. In order asses the performance of the ET-LBC technology using mathematical models, the anaerobic degradation parameters such as the methane […]