Real-time Bidding Using Contextual Targeting

Ads keep the internet free. But, to keep them from becoming spam and degrading the user’s online experience, they need to be relevant to them. The traditional way the industry does this is by collecting a lot of information about every user and creating profiles that can be used to target users based on their […]

Read More
Autonomous Navigation for Small UAV in Indoor GPS-denied Environments

With the evolution of unmanned aerial vehicles (UAVs) in recent years, more and more researchers are setting their sights on the application research of the indoor environment. Indoor applications include industrial facility inspection, warehouse inventory management, health sector, search, and rescue, among others. However, the use of UAVs in these applications requires continuous high-accuracy positioning […]

Read More
Automated code fix suggestions based on source code syntax tree analysis

AMD manages a very large code base that supports multiple graphics products, operating systems, and customers with multiple releases per year. With a high rate of innovation and corresponding code changes it is a daunting task to ensure a given change works correctly on all applicable configurations for every release. It is therefore imperative to […]

Read More
Identifying Risk Factors for Hazardous Driving and Accident Propensity

Road safety affects everyone, Geotab has several years of driving and environmental data from over 2 million connected vehicles providing the opportunity to make customers safer, as well as our communities and cities. This project will leverage data and existing methods to build a model that can identify causal risk factors for hazardous driving and […]

Read More
Statistical and Ethical Implications of Pimavanserin Drug Trials Published with Unexplained or Missing Datasets on Parkinson’s Disease

This project looks to examine the safety of the medication Pimavanserin, marketed under the brand name Nuplazid. Pimavanserin is prescribed to manage Parkinson’s Disease Psychosis, a common side effect of Parkinson Disease medications. This medication has already received regulatory approval in the United Stated by the Food and Drug Administration under a special program called […]

Read More
Knowledge Modeling and Product Development for Canadian Indoor Hydroponic Farming

Urban population is facing unprecedented growth resulting in the need for additional agricultural resources. Traditional farming practices seem vulnerable to cater to urbanities’ needs, placing an additional burden on the food and agriculture system. Furthermore, the unsettling environmental impact of traditional farming practices has aroused the metropolitan population to search for alternatives, such as indoor […]

Read More
Conception intégrée et fabrication d’une électrode composite flexible sèche d’électroencéphalographie et d’un système de support à pression variable pour utilisation mobile de longue durée in-situ

Durant les dernières années, de nouvelles méthodes d’analyse par ordinateur impliquant l’intelligence artificielle ont permis de grandement améliorer notre capacité à interpréter les signaux obtenus par électroencéphalographie pour des applications allant de la santé à la défense en passant par les sports et l’amélioration du bien-être mentale. Toutefois, les avancées dans ce domaine sont aujourd’hui […]

Read More
Visual Semantic SLAM using Bottlenose Camera System

Simultaneous Localization and Mapping (SLAM) is useful in multiple applications such as autonomous driving, augmented reality, and surveillance. Visual SLAM is a popular and widely used SLAM technique due to simplicity of the sensor network. Semantics and machine learning are used widely in recent research to achieve better robust real time SLAM performance. Hardware acceleration […]

Read More
Multi-modal machine learning for business-critical insights in video conversations

The team is building a machine learning platform and solution to extract meeting insights from online meetings. Meeting insights denote moments from these meetings that may impact the company’s future product features, revenue, and customer satisfaction. This platform is driven by the market created by the widespread adoption of online virtual meetings as the main […]

Read More
Towards Development of a Decision Making Tool for Owners, Designers and Municipalities: Surveying Current Domestic Water Conservation Technologies and Tools for Single Family Residential Dwellings

The proposed project will survey “best-in-class” decentralized water conservation technologies and approaches such as rainwater harvesting systems and greywater recycling systems for use in single family residential dwellings in Canada. The proposed project will also survey all tools and resources provided by water conservation authorities such as CMHC to homeowners, building designers and municipalities. The […]

Read More
Automatic Machine Learning for Recommender Systems

Crossings Minds provides machine learning-based recommendation systems that allow companies to integrate their data and easily obtain on-demand personalized recommendations for their users. Currently, onboarding a new customer requires significant work on the behalf of Crossing Minds engineers to create and polish a machine learning model for that specific customer. The research project will explore […]

Read More
Modular Magnetorheological Actuators Controls

Since its foundation in 2013, Exonetik has been developing and manufacturing magnetorheological (MR) actuator systems that enable novel functionalities to satisfy unmet customer needs. Exonetik’s patented actuators offer a unique combination of torque-density, high bandwidth, superior back-drivability, low-cost and aerospace-level reliability. To reach its ambitious goals, Exonetik has built several strategic relationships with major OEMs […]

Read More