Investigate machine learning algorithms to develop anomaly detection methods

The industry partner, Metafor is developing a new class of IT system management solution. As part of this project, Metafor is building a product feature that monitors computer and network activities and looks for signs of anomalies. This is an important problem as anomalies are usually associated with abnormal user or system behaviors that can potentially result in problems such as system breakdown.

Measuring and quantifying mobile user quality of experience

The objective of this research is to develop an on-device, quality of experience (QoE) measurement suite, for Android based mobile devices. As mobile devices become the predominant method with which the world accesses the internet, it becomes increasingly important to understand the complex interaction between applications, mobile OS’s, the networks they run on, and the behaviours of a user base at large. Doing so with mobile devices raises a set of issues that aren’t present with traditional PC’s, and as such haven’t been explored thoroughly.

Assessing of affects on application-level mobile device quality of experience measures

With the growth of mobile device platforms such as smartphones and tablets, users now primarily experience the wireless networks they uses, whether cellular or WiFi based, through the context of the apps that they use. Hence, a heavy Skype user may perceive a given network to be of substantially different quality than would be perceived by a heavy text-messaging user. This reality has lead to a growing interest in quality-of-experience (QoE) measures as a compliment to more traditional network-level quality-of-service (QoS) measures.

Aperture antennas as mobile satellite terminals

Antennas are essential part of communication links. This project is investigating antennas for communication between a mobile terminal on earth to a satellite. The mobile terminal could be a flying craft or a vehicle in motion. These antennas should be able to transmit and receive data simultaneously in different channels. Besides, they should be capable of scanning the space to find the target satellite. Single channel antennas or antennas with mechanical tracking have been tested for this purpose and are available in market.

Sensorless control of brushless DC motors at low speeds

Accelerated Systems is a leader in the design and implementation of control systems for electric vehicles; especially vehicles driven by permanent-magnet brushless DC (BLDC) motors.  One of the key technological challenges in the use of BLDC motors is that traditional control, especially at low speeds, requires external sensors to determine the rotor position.  These external sensors then become an added cost and maintenance challenge.  In this project, we will investigate novel control strategies that infer the rotor position from measurements of motor voltages and currents only.  A succes

Machine learning for user behaviour prediciton in mobile games

With the growth of the social networks and mobile gaming devices in recent years, the social gaming became an important part of the game industry. These social games provide huge amount of data about the users’ behaviors, an important issue for the gaming companies is to analyze this data and model the choices and behavior of the users and based on this model they try to improve their product and predict the behaviors of their users. The expected benefit to the partner organization is the research and adaption of new techniques for modeling user behaviour for social gaming.

Computer-aided spinal disease diagnostic system

This proposed research aims at developing a fully automated computerized system for multiple spinal disease diagnosis. It improves the efficiency of the current clinically workflow. The development of the research is based on the state-of-the-art computer vision and image processing techniques. To the best of our knowledge, our group is the first group focusing on this direction. Once success, it will not only improve the clinician’s accuracy, inter and intraobservability, but also promote the technical advancement in the computer vision and image processing.

Terahertz surface plasmon near-field sensor for material sensing applications

In this project, we plan to address the specific problem that TeTechS Inc is facing at this stage of its product development project, which is collecting a complete set of measurement data for an array of organic materials with different levels of purity and demonstrate the capability of its proprietary terahertz sensing techniques to qualify and quantify purity and integrity of organic LED (OLED) materials with the level of precision required in OLED deposition and material purification processes.

Industry Internships on Smart Applications and Virtual Infrastructures

This Mitacs Accelerate program will support a internships for graduate students in the areas of services and applications using next generation communications, Internet, and cloud computing. The interns will be placed in Canadian telecom and networking providers and vendors and will undertake research projects defined jointly with these partners. The program will prepare graduates to work and industry and will foster collaboration between universities and industry.

Strategic safety stock allocation in an assembly supply chain network

The supply chain structure of an engine assembly line consists of several complex flows and processes to satisfy the requirements for on time delivery of these products. The difficulty in managing such systems is due to the fact that more than 1000 parts should be available on time in a synchronized manner to start the assembly procedures and deliver the products on time. Due to the supplier lead time variability, quality inspection related delays and other sources of uncertainty, the adherence to a production plan is almost impossible.