Automated Land Use and Land Cover (LULC) Classification for Hydrological Modelling and Physically-Based Inflow Forecasting

The problem considered in this work is how to produce highly accurate and consistent land-use/land-cover (LULC) maps significantly faster than current semi?automated methods for use by Manitoba Hydro. The goal is to improve the ability to produce maps quickly and efficiently as priority needs arise. This project will use an approach for automated LULC mapping […]

Read More
Active Learning for Fish School Recognition in Echograms in the Bay of Fundy

OERA use hydroacoustic echosounder surveys to evaluate the impact on marine life of tidal turbines in the Bay of Fundy. OERA use Echoview software to read in the raw sensor data (e.g. voltages) and convert it to a visual representation. Echoview contains some algorithms to detect the bottom of the ocean. However, the Fundy data […]

Read More
Wide-baseline Novel Scene Synthesis from a Single Image

Novel view synthesis is the process of generating new images from an unseen perspective, given at least one image of a scene. There may be more than one probable novel view associated with each unseen perspective, an assumption made by existing methods. This simplifying assumption prevents these methods from being applied to more difficult novel […]

Read More
Improving the Reliability of AI Systems from a Software Engineering Perspective

Artificial Intelligence techniques have been widely applied to solve real-world challenges, from autonomous driving cars, to detecting diseases. With the popularity of 5G wireless network, more and more AI systems are being developed to provide convenient services to everyone. It is important to ensure the reliability and quality of AI systems from every phase in […]

Read More
Traitement du langage et Résumé automatique de documents

Un résumé est un texte qui décrit de façon synthétique la forme, le contenu, et la thèse principale d’un ensemble de document. Une société comme la Fédération des caisses Desjardins reçoit énormément d’informations provenant de ses membres et clients, notamment via les sondages de satisfaction. Grâce à différentes méthodes de traitement automatique du langage nous […]

Read More
Technologies innovantes pour une intelligence urbaine au service des citoyens

Le présent programme de R-D a pour objectif de développer des solutions novatrices – innovations technologiques et sociales – au sein d’un environnement interdisciplinaire (sciences urbaines) et plurisectoriel (université – entreprises – villes). Les projets se réaliseront dans le cadre d’un nouveau programme de maitrise sur mesure en intelligence urbaine chapeauté par la Faculté des […]

Read More
Intelligent Non-Person Agent to Play a Game

Creating a non-person character (NPC) to play a game is becoming increasingly important. NPCs can be used in quality assurance to test a game before sending the game for certification. Being able to test a game in a way that mimics a human player would allow the test to be more accurate and would help […]

Read More
A Machine Learning based approach for Portfolio Allocation

The goal of this project is to create new algorithms and state-of-the-art methods for resource allocation in a financial context. This model can be applied to other domains, such as fleet and personnel management, scheduling of computer programs, manufacturing production control or controlling a mobile telecommunication network. Alpine Macro provides market insights, investment strategy and […]

Read More
Parallelization of an Industrial Optimization Application

Acculogic develops state-of-the-art testers for short-batch electronic circuit boards (ECBs). The order in which the required tests are performed affects the amount of shuttle and probe movements required between the tests, and this affects the overall efficiency of the test procedure. Unique characteristics of the problem (e.g. the ability to move one set of probes […]

Read More
Investigating multi-task learning in semantic parsing

Current research in semantic parsing suffers from lack of annotated data, which is hard to acquire. In this project, we aim at tackling the problem of converting natural language utterances to SQL language (Text-to-SQL) on complex databases in a low-resource environment. More specifically, we focus on the research of how multi-task learning (MTL) can help […]

Read More
An Automatic Tool for Developing Transactive Energy Smart-Contracts: Development, Validation and Integration with the IEMS Blockchain Platform

Energy consumers and prosumers are currently dealing with each other via utility companies, which is a slow, costly and indirect mechanism. With the aim of moving toward a free market, the goal of this project is to provide a suitable platform for automatic development and evolution of smart contracts in distributed transactive energy markets. This […]

Read More