The purpose of this project is to investigate self-adaptive forecasting and anomaly prediction algorithms based on deep neural networks (DNNs). DNNs present a compelling technology due to their wide-spread availability through open-source projects (e.g. TensorFlow, MXNet). However, usability of DNNs in scenarios outside of image, speech or text pattern recognition is mostly unproven. This project […]

Deep neural network (DNN) is a class of machine learning algorithms which is inspired by biological neural networks. DNNs are themselves general function approximations, which is the reason they can be applied to almost any machine learning problem. Their applications can be found in visual object recognition in computer vision, translating texts in unsupervised learning, […]

Networks are moving towards being adaptive. This means that automation will be used to replace processes which are today highly manual. This project proposes a development of knowledge in the area of algorithms required to enable adaptive networks. The project will train two PhD students to understand optical networks and devise optimization algorithms in the […]

The project is about removing noise from video signals, for example, those taken by a professional cinema camera. In this project, we propose to develop a commercially capable noise reduction framework based on one of our patents to noise reduction. A commercial noise reduction is required to automatically recognize the type of noise piesent in […]

The project entails the creation of a program that will capture data from building sensors. It will analyze that data and predict future trends based on the data collected over a period of time. It will also graph data from sensors over a period of time. Currently both are done manually, take a significant amount […]

In this project, we will explore novel modeling methods to predict oil prices, based on a combination of machine learning methods with dynamic multiresolution analysis. The objective is to develop a software to better forecast oil prices. Oil is the world’s leading fuel, and its prices have a big impact on the global environment, the […]

Software-defined networking (SDN) technology is an approach to cloud computing that facilitates network management and enables programmatically efficient network configuration in order to improve network performance and monitoring. SDN suggests centralizing network intelligence in one network component by disassociating the forwarding process of network packets (data plane) from the routing process (control plane). The control […]

In Canada, approximately 40,000 out of hospital cardiac arrests (OHCAs) occur annually. Survival rates are under 15%, and the only treatment is immediate use of an Automated External Defibrillator (AED), coupled with CPR. This project will focus on finding solutions to identified problems associated with locating and using an AED. Some of these solutions will […]

This project is aimed to develop a next-generation network providing unprecedented quality of cellular service to Canadians and small and medium businesses, stimulating innovations and improving the quality of life of our people. Relying on the ENCQOR infrastructure, which is the first 5G network in Canada supported by three governments (Quebec, Ontario, and Canada), the […]

To meet the network latency requirements in intelligent driving (e.g., city-wide smart parking, vehicle infotainment, and collision avoidance), more and more computing functionalities are moved from the centralized clouds to the network edges (e.g., mobile base stations, or roadside infrastructure). By doing this, the response time to drivers or in-vehicle passengers could be improved. Nevertheless, […]

Despite significant recent progress on generative models, controlled generation of images depicting multiple and complex object layouts is still a difficult problem. Among the core challenges are the diversity of appearance a given object may possess and, as a result, exponential set of images consistent with a specified layout. In this project, we propose to […]

La Tomographie d’émission par positrons (TEP) est une modalité d’imagerie médicale qui permet d’observer des processus biologique in vivo. L’imagerie TEP trouve de nombreuses applications en neurosciences, notamment pour la détection et le suivi des maladies neurodégénératives. Pour des images précises, le sujet doit demeurer immobile pendant l’acquisition des données qui peut typiquement durer plusieurs […]