CommuterVis: Visually Understanding Commuter Behaviour in Canada

Too many people drive cars for commuting to work. If people used more active and sustainable transportation options this would reduce the impact on the environment and likely increase people’s physical activity and well-being. Our project partner Sustainable Alberta Association (SAA) is a not for profit organization that organize a Canadian annual wide competition called […]

Read More
Modelling of Surgical Workflows

Minimally invasive interventions are becoming increasingly common as they improve patient outcomes such as recovery time and infection risk; however, these procedures can be difficult for operators to learn. To improve surgical training efficacy, computer-assisted training, which must provide feedback in the form of instruction and skill evaluation, can be used. The training system must […]

Read More
Improving bend gesture accuracy using simulated tactile properties

Bend gestures on flexible devices allow users to provide subtle and continuous input to a computing device by bending a corner or a side of the device in question. The depth of bend can be used to control, for example, the speed at which the user scrolls through a document. This kind of input could […]

Read More
Modéliser les données multi-relationnelles comme des séquences / Modeling multi-relational data as sequences

The objective of the project is to automatically learn missing information in knowledge bases (KBs), which are becoming essential tools to deal with big data, since they provide means to organize, manage and retrieve all this knowledge. These databases are huge directed multi-relational graphs, whose nodes correspond to entities connected by edges representing a certain […]

Read More
Segmentation des masses en mammographie.

Le cancer du sein est l’une des premières causes de mortalité chez les femmes dans le monde. Le dépistage précoce par le biais de la mammographie reste est le seul moyen reconnu pour la réduction du taux de mortalité de cette pathologie. Toutefois, la qualité des mammographies rend pénible l’identification des masses mammaires. Dans le […]

Read More
Educational Math Games For Developing Countries

Hundreds of millions of children in developing countries are unable to complete primary education. Mobile devices such as tablets are increasingly inexpensive and becoming accessible in large numbers in such developing countries. We propose developing educational software for such tablets to help children acquire arithmetic skills. To do this, we will develop new ways of […]

Read More
PACTA: Automated text mining and analysis of business contracts

PACTA is a cutting edge SaaS contract management and analysis product designed for SMBs that proactively manages and tracks business contracts and obligations, thereby minimizing business risk and saving up to 9% of the bottom line. The objective for the full-time 8-month internship, in partnership with Dr. Lingras at SMU and Mitacs is to identify […]

Read More
Asynchronous vs. Synchronous Rumor Spreading

Our intended research will be focused on rumor spreading protocols, also known as randomized broadcasting. In the randomized rumor spreading problem, the goal is to broadcast a message that is initiated at one node to all nodes in a given network, by means of nodes choosing uniformly at random a neighbor and exchanging the message […]

Read More
Deep Learning for Action Recognition, Localization and Parsing

The goal of this project is to develop algorithms that allow machines to understand and describe actions in video. For example, we would like computers to be able to classify videos according to the actions taking place inside them , and annotate the videos according to where and when the actions take place. To tackle […]

Read More
Multivariate polynomial interpolation: efficient algorithms and applications

This research project aims at providing efficient methods to solve a mathematical problem which has practical applications in digital communication and online storage. In the domain of communications, these methods perform the decoding stage of some error-correcting codes, which are used to ensure reliable data transmission over an unreliable or noisy communication channel such as […]

Read More
Human Performance of Finger Identification for Multitouch Input

The project first aims at developing a robust and low latency hardware system for identifying which fingers are in contact with a surface. The second objective is to implement and refine finger identification interaction techniques that would improve the interaction with touch surfaces (smart phone, tablets, tabletops). These techniques will be evaluated to state of […]

Read More