Innovative Projects Realized

Identifying Questions for Game-Based Learning through Deep Learning

Game-based learning tools often make use of questions to measure and encourage learning, but generating questions can be challenging, especially at the scale that companies like Axonify are required to do. In this project, the intern will design, implement, and evaluate a system that can apply machine-learning on a corpus of text (e.g., a textbook) to automatically generate questions that can be used in game-based learning tools. This system will allow Axonify to scale their products to larger corpora of source material, larger sets of questions, and ultimately have a much larger market as a result.

Numerical modeling and optimization of the coagulation-flocculation process for seawater pre-treatment

The result of this project can be used by engineers to design a multivariable control system that will optimize the dosing of chemicals in seawater pretreatment. Besides, the plant operators and technicians will be able to perform ‘what if’ scenarios based on computer modeling results to ensure that the outlet water quality is not decreased. The model will also provide an understanding of the effective parameters that determine the optimum coagulant/ flocculant dosage required for an effective water treatment process. This project is a part of a bigger project which is desalination of sea water, which can positively affect the Canadian community in case of water quality and availability. The results of the modeling can be directly used in that main project at Pani-energy.

Graphics Processing Unit Solutions for Power Systems Computer Aided Design: Advanced Development with the University of Winnipeg

Graphics Processing Units (GPUs) are usually employed to quickly render images on everyday computer screens, and do so quickly and efficiently for relatively little cost compared to the use of Central Processing Units (CPUs) that make up the “brain” of the computer. Modern GPUs are able to do hundreds or thousands of simultaneous calculations; rewriting conventional computer problems in the language of GPUs offers the po-tential to dramatically decrease the computation time for complex problems such as Electromagnetic Trans-mission (EMT) simulations. EMTs are used to model large electrical systems — such as city power grids — and are fundamental to power engineering software. This project will focus on how to integrate the power of GPUs into established software for EMTs, with the aim of providing power engineers around the globe with a cutting-edge tool to help design ever greater electrical systems.

Représentation dynamique de l’empreinte carbone de l’hydroélectricité au Québec

La production d’électricité à faible empreinte carbone est un levier majeur dans la lutte contre les changements climatiques. L’hydroélectricité, qui représente 99% de l’électricité produite au Québec, possède une faible empreinte carbone comparativement à l’électricité provenant de ressources fossiles, soit un avantage majeur pour la province. Les émissions de CO2 et de CH4 provenant de la dégradation de la biomasse dans les réservoirs ont une grande influence sur l’empreinte carbone de l’hydroélectricité. Il est primordial de bien quantifier ces émissions afin d’être en mesure de prendre des décisions éclairées dans le contexte actuel de transition énergétique. Or, les émissions des réservoirs varient fortement dans temps, étant beaucoup plus élevés dans les 10 à 15 années suivant la création des réservoirs. L’objectif de ce projet est de développer une représentation dynamique de l’empreinte carbone de l’hydroélectricité au Québec afin d’avoir un portrait plus juste de l’impact climatique de l’électricité produite actuellement dans la province, ainsi que dans les années à venir.

Étude du comportement hydrodynamique, et diphasique d’un classificateur à lit fluidisé – Phase 2

Le projet a pour but d’analyser le comportement d’un fluide diphasique, mélange de bauxite et d’eau, dans un classificateur à fond plat soumis à l’effet de plusieurs paramètres.
Une étude expérimentale utilisant un classificateur à échelle réduite permet d’effectuer les mesures de fraction solide (pourcentage de solide dans l’échantillon) aux sorties du classificateur, ainsi que d’observer le comportement du fluide diphasique et particulièrement du lit fluidisé présent dans le bas du classificateur.
Une étude numérique consiste à développer un modèle CFD (computer fluid dynamics) qui représente l’écoulement d’un fluide diphasique (solide-liquide) composé d’une plage granulométrique (répartition des particules selon leur taille) variée afin d’en observer le comportement et de calculer les paramètres de sortie.
En incorporant les résultats expérimentaux au modèle CFD, l’étude de comportement de la bauxite dans les équipements de séparation solide-liquide à fond plat permettra d’optimiser leur conception et leur fonctionnement en usine.

Insight into killer whale habitat quality

British Columbia’s (BC) resident killer whales are listed under the Species At Risk Act as ‘threatened’ and ‘endangered’ for the northern and southern residents, respectively. Contaminants have been recognized as one of the main threats affecting the survival and recovery of these populations. This project will look at the levels of contaminants of concern in sediment samples collected from killer whale habitat. Sediment has been used around the world to evaluate pollutant inputs and distribution in aquatic environments as it can be both a contaminant ‘sink’ and a ‘source’ for adjacent food webs. As part of Ocean Wise’s PollutionTracker program, sediment samples have been collected at over 50 sites along the BC coast. This project is a great opportunity for Ocean Wise to compile and use the data that has been collected since 2015 and provide invaluable information on the source, transport and fate of contaminants of priority concern for the endangered southern resident killer whales.

Landfill Odour Management Strategies

Golder Associates Inc. is the Technical Lead Consultant on the Environmental Assessment for the expansion of the W12A landfill of the City of London. One key aspect of this project is landfill design alternatives and the impact on air quality and, specifically, odour issues. The proposed project aims at providing critically valuable information regarding local air and odour monitoring at the W12A landfill site, regional air and odour monitoring in the South London area, as well as an assessment of the industry best practices not currently employed that may be applicable. Experimental and modelling work, combining data gathered with appropriate sampling and monitoring technologies, dispersion modelling and meteorological data will allow to better understand the air quality and odour issues surrounding the landfill and to recommend the most effective odour management strategies by either enhancing or implementing new operational activities or employing additional engineering controls and/or monitoring devices/programs.

The interplay between mental health, mental illness, sport culture, and athletic performance in Olympic and Paralympic sport

Mental health is increasingly being recognized as a key component of elite athletes’ overall functioning and sport performance. Globally, research on antecedents (e.g., sport culture) and consequences (e.g., athletic performance) of mental health and illness in elite athlete populations is growing. However, little is known about the relationship between mental health, mental illness, sport culture, and athletic performance in the Canadian high-performance sport context. The purpose of this research project is to better understand the interplay between these variables in Canadian Olympic and Paralympic athletes using a longitudinal mixed-methods design. The results and deliverables associated with this project will help the partner organization, Own The Podium, develop evidence-based and culturally appropriate resources, policies, and programming to support Olympic and Paralympic athletes in their training and competition environments.

Séparation magnétique appliquée à l’extraction de la magnétite dans les résidus de bauxite calcinés

Le but de cette étude est de réaliser une séparation magnétique de la magnétite (oxyde de fer) contenue dans le résidu de bauxite calciné, dans le but de le valoriser. L’étude se déroule en plusieurs volets : la caractérisation du résidu de bauxite, phase expérimentale de séparation et le développement d’un modèle mathématique. La caractérisation permet de connaitre entre autres la distribution granulométrique et les espèces chimiques. La phase expérimentale permet d’identifier les paramètres d’influence de la séparation. Le modèle mathématique permettra de réaliser des simulations. Le montage expérimental est un séparateur à échelle réduite avec lequel se feront les mesures de trajectoires, de vitesses, de concentration à la sortie. Les mesures de trajectoires et de vitesse se font par imagerie, et les concentrations à la sortie par gravimétrie. Au terme du projet, le banc d’essai (montage expérimental et modèle mathématique) servira la conception à pleine échelle de dispositifs industriels de séparation.

Novel MRI Technical Developments for Noninvasive Measurements of Arterial Stiffness

L’importance de la foresterie dans l’économie nécessite de réaliser des études

permettant de comprendre et résoudre les impacts que cela produit, pouvant affecter

la durabilité des zones productrices. L’orniérage est l’un de ces impacts qui sont

connus mais pas toujours contrôlés. Certaines zones connaissent des disparités

importantes pouvant conduire à une modification du milieu à courts et longs termes. A

l’aide de photos satellites et de mesure locales, nous allons travailler à différentes

échelles et étudier la dynamique de résilience des sols et végétaux suivant les

conditions du milieu. Dans le cas des zones déjà modifiées nous isolerons les seuils à

partir desquels le milieu a basculé vers un autre état d’équilibre.

Industrial Safety Management using Control Theory and Machine Learning

Optimizing plant processes is of prime importance now more than ever. With stricter infrastructures being placed on safety, environmental effect, and corporate social responsibility, more complex systems that optimize these factors are needed. These complex systems with advanced algorithms are intended to further streamline the existing process while mitigating issues leading to a safer workplace, and environment, while creating cost savings potentially in the millions. Two of the biggest problems that are hindering this growth are process optimization and management of alarm systems. This proposal aims to incorporate a methodology that combines traditional safety analysis techniques with recent data-driven techniques such as machine learning and reinforcement learning to minimize and manage the alarm system and suggest operational set points to increase throughput while optimizing safety. The proposed research will use data from the plant process at NTWIST Inc will be used to obtain optimal policies that minimize cost associated with the unsafe operation.

Dynamics of T-cell recruitment and polarization in inflammatory skin diseases

Psoriasis is an auto-immune disease in which the T-cells (type of blood cells involved in fighting infection) mistakenly attacks the cells within the body leading to formation read scaly patches or plaques on the skin. Plaque Psoriasis that occurs in 80-90% of the patients is associated with anxiety and depression that negatively affects patients social and economical situation. The current treatment options for psoriasis are expensive and require a long-term commitment from the patients to prevent disease relapse. There are no options for complete cure. The current understanding of the disease is that the pathogenic T-cells are only residing in skin and therefore, most of the treatment options available are skin directed. Recent studies and clinical observation suggest otherwise. We propose a study to identify these pathogenic T-cells in blood that will likely explain the cause for relapse of the disease and limitations of current treatment protocol.