Scale-up of a Green Plasticizer

Plasticizers are used to increase the flexibility and workability of relatively rigid polymers such as poly(vinyl chloride) (PVC). For decades, di-2-ethylhexyl phthalate (DEHP and sometimes termed as dioctyl phthalate (DOP)) was the most common plasticizer used in PVC formulations. However, DEHP has been shown to have negative health effects, such as being an endocrine disruptor. Recently, DEHP has been banned for use in children’s toys and phthalate alternatives are rapidly being offered.

Text Recognition Software Development for Legal Services

The rapid advancement in the areas of machine learning and artificial intelligence has led to many breakthroughs in industries. As an online medium legal intermediary platform, Right Legal aims to connect clients and lawyers by providing them with a secure, convenient, and efficient platform. In order to accomplish this, we take into account of (1) the resourceful text information generated from the platform (e.g., the request and feedback from clients), (2) the lawyers’ profiles, and (3) the service quality offered by the lawyers.

Integrated Microlens Technology for Light Steering Projectors

MTT Innovation Inc. is a Canadian company that is based out of Vancouver, British Columbia. MTT develops technologies for next-generation projectors in home entertainment systems and theatres. The developed projectors are engineered to provide especially high quality images, with enhanced brightness and dynamic range, and an emerging product of MTT that targets these goals is their light steering projector. Such a projector is being developed through the proposed project as a partnership between MTT and researchers at the University of British Columbia's Okanagan campus.

Device-free indoor activity detection and localization using Wifi signals

Creating smart indoor environments that detect and understand human daily life activities is attracting significant amount of attention, due to their huge potential impact on context-aware technologies. Aerial Technologies, our partner organization, is developing products that provide device-free indoor localization and activity recognition Wi-Fi signals generated by off-the-shelf Wi-Fi enabled devices. This project will use state of the art machine learning and time-series analysis algorithms to improve the detection and classification capabilities of these systems.

Improved Human Movement Tracking and Prediction in High-Occlusion Multi-user Virtual Reality Environments

Virtual reality has the ability to change the way people work and play together, but almost all VR technology to date is designed for single users in separate, dedicated spaces. The problem with having multiple people in the same shared room (while in a shared VR experience together) is that they become much more difficult for the sensors to accurately track because sensors become visually blocked more often. This research proposal is focused on using intelligent algorithms to help improve tracking accuracy in these situations, while keeping hardware costs as low as possible.

LAFORCE: Log Analytics For Operational Intelligence

The goal of this project is to explore the use of log analytics and machine/deep learning techniques to improve Ubisoft operational intelligence. Logs contain a wealth of information, but often hindered by the lack of best practices, tools, and processes. Despite the importance of logging, the area has not evolved much over the years. At Ubisoft, logs are used extensively for various system diagnosis tasks. The analysis of logs, however, is usually performed manually, limiting the full potential of the information contained in logs.

Hardware Support and Heterogeneous Compilation for P4

Today’s data-center network services cover a broad spectrum that evolve rapidly which means that regularly new services need to be deployed in production networks in a timely manner. Using network programmability, a network programmer can write a precise specification of what the network behaviour should be, and this specification is translated by a compiler and executed on the hardware. The goal of the project is to allow this programmability to include automatically leveraging hardware to improve performance.

Mathematical Foundations of Hybrid Quantum Technologies and Quantum Leap Africa

We are on the doorstep of a quantum revolution in modern science, perhaps most significantly in the development of new types of information and communication technologies, and Canada has positioned itself as a world leader in these efforts. This proposal includes an expansion of research into quantum information and communication by the University of Guelph’s David Kribs, in collaboration with the African Institute for Mathematical Sciences (AIMS), which has identified quantum information as an area of fundamental importance to its network.

Machine learning methods for signal classification in anti-drone technology

Drone technology has recently gained wide-scale acceptance in multiple military and commercial applications, including security surveillance and medicine delivery. In 2017 alone, the market revenue from drones is estimated to be around $6 billion. With this, there is also an emerging need for sophisticated anti-drone technology to detect rogue drones entering secure territories, such as military bases and prisons.

Vehicle Occupancy Detection using Thermal Camera and LIDAR

In this project, a vehicle occupancy detection system will be developed for automatic monitoring of HOV (High Occupancy Vehicle) and HOT (High Occupancy Toll) lanes. The system makes use of machine vision along with artificial intelligent algorithms, developed based on deep learning, to detect number of passengers in a vehicle in real-time. The developed technology will enable the industry partner to commercialize this solution in Canada and globally for efficient and enforceable monitoring of HOV and HOT lanes.