New meters, sensors and other field data collection devices are providing a plethora of real time system operational data for building, industrial plants and production systems. At the same time, building owners, industrial plant owners and campus based operations are being challenged with managing their energy use both through conservation and demand management processes. In […]

Human safety represents an ensential key feature in future samrt cities, which can be improved by mission critical vehicles that can operate in remote locations where rescue teams cannot reach due to various factors such as unavailable roads, floods, or fires. For example, unmanned aerial vehicles (UAVs) or simply drones, that work together in a […]

Hydro-Québec has data acquisition systems for a multitude of sensors, some of which have been installed since almost 20 years in its electrical generation equipment (turbine-generator units – TGU). The collected data is primarily used to ensure that the information is adequate in the event of an equipment breakdown or for specific behavioral studies. Data […]

Smartphones are not only incredibly powerful computing devices, but also sophisticated sensor platforms. Leveraging sensed user context, such as location, to provide targeted advertising has been discussed as a potential application of ubiquitous sensing in the literature, and is beginning to appear in industrial applications. In this proposal we describe the innovations necessary to realize […]

There is a strong demand for effective means to detect and record trespass activities onto farm properties, which cost the agriculture industry many hundreds of millions of dollars each year. The goal of the project is to design and develop a trespasser detection system based on the presence of a human being carrying a cell […]

Software developers have been quick to capitalize on the growing number of children using smartphones, publishing enough educational titles to warrant their own category on the Apple App Store. However, establishing the efficacy and usability of these mobile educational games can be difficult and expensive. Heuristics are commonly used during the evaluation of user interface […]

Deep learning is nowadays one of the most popular areas in computer science which has shown extraordinary performance and enjoyed wide use in a variety of fields. This research project is aiming at exploring the application of deep learning algorithms in two fields: autonomous driving with 5G networks, and facility maintenance with CT scanning. In […]

Les agents conversationnels (chatbot) sont de plus en plus populaires. On n’a qu’à penser à Google Assistant, Alexa ou Siri. Ces agents utilisent l’apprentissage profond afin de classifier les phrases des utilisateurs et d’en extraire les informations pertinentes. Les modèles derrière ses technologies sont d’habitude entraînés sur des corpus (des bases de données contenant du […]

pre-agreed price. The problem of what an option is worth is usually solved using costly numerical simulation methods. We will apply Deep Learning methods to solve the Option Pricing Problem. This cutting edge technique has the advantage that, once trained, the model can simulate many scenarios at a low computational cost. Unfortunately, training is costly […]

Data is rapidly growing in most of the applications and fields. Thus, data is becoming big data as it meets the 5V model of big data: volume, velocity, variety, veracity, and value. As a result, dimensionality reduction and feature selection become mandatory to overcome ML models’ performance and explainability issues. This project looks at feature […]

We are building a machine learning algorithm to be able to better understand the unstructured clinical notes. This will help the medical coder and auditor to quickly navigate the clinical notes and locate the text that corresponding to the codes. Reduce the chance of missing labels and mis-labeling in the coding review process.

The general objective of this research project is to develop a new natural and empathic chatbot by integrating the transformer and intent-based systems. The goal is to implement a system for expressive 3D interactive characters that can move between the structure of an intent-based system with specific Question and Answer pairs and the more open-ended […]