Projets novateurs réalisés

Machine learning for robust and reliable measurements

In this project, we will employ deep learning techniques to enhance the accuracy, interpretability, and robustness of indirect measurements. Particularly, we focus on problems of i) interpretation and analysis of metagenomic data obtained from agricultural soil samples, characterized by high-dimensional feature spaces with a relatively small number of soil samples (for an overview, see [1]-[4]), and ii) improvement of the non-invasive measurement approach developed for estimating animal weight based on 3D images in the farming industry, involving a huge amount of data used for volumetric representations (for a brief review, see [5]-[8]).

Both problems involve evaluating or detecting an unknown quantity from the observations indirectly related to the measured/detected quantity, and our goal is to apply low-rank models (which are increasingly relevant in data science) to both problems, given their ability to capture the essence of complex data while reducing the dimensionality. So, we are mainly interested in two major benefits they offer. One is related to overfitting reduction (the limited dimensionality confers a greater capacity for generalization, making them less prone to overfitting), and the second is related to the adaptation capacity, which is particularly important in real-time data processing.

Halton Kindergarten Parent Survey: Exploring Key Findings and Developing Knowledge Translation Resources

The intern will lead the development of three research briefs based on findings from the 2023 Kindergarten Parent Survey, a unique research instrument designed by a collaborative of Halton researchers. The survey provides a snapshot of the wellbeing of Halton kindergarten preschool children and their families on multiple domains, including healthy development, physical activity, nutrition, childcare, community experiences, parenting experiences, and community wellbeing. The intern will explore changes to wellbeing among preschool children and their caregivers using data from the 2023, 2018 and 2015 cycles of the KPS. Children who experienced the pandemic during their early years are represented in the 2023 KPS cohort, and may have unique needs, indicating a need for targeted information sharing among professionals serving children and families. The internship benefits the partner organization by fulfilling our strategic direction to provide knowledge translation that fulfills the information needs of child/youth serving agencies in Halton.

Compact dc Transmission

The project will investigate a novel HVdc transmission arrangement referred to as a “symmetrical monopole”. This configuration has the ability to continue operation even when one of the transmission line conductors is faulted. This property allows for the use of new compact dc transmission lines which occupy only a fraction of the right-of-way of other transmission options, thereby minimizing the negative impact on the environment. The research will investigate the appropriate control and protection aspects of such a transmission scheme. It is expected to generate new expertise in compact dc lines, which would significantly increase the competitiveness of the partner organization, Electranix Corporation Inc., who is a leading Canadian Consulting Firm in the HVdc Area

Machine Learning developer interns working within cross-functional teams to develop and commercialize AI-powered solutions in the Public Services sector (1)

AltaML builds artificial intelligence (AI)-enabled solutions to business problems. We work with organisations, bringing together their data and domain expertise with our AI expertise, to develop AI solutions that are deployed in their operations. We also commercialize AI-enabled products business via industry-specific ventures, yielding scalability from our investment in the first solution. Competition for tech talent is fierce, and our talent strategy includes a talent accelerator program, designed to rapidly equip highly qualified individuals with hands-on work experience in applied AI while providing partners with continuous and cost-effective development of AI solutions. AltaML’s AI Lab for Government, also known as GovLab, is a talent accelerator for public service professionals, post-secondary students and recent graduates. GovLab.ai’s mission is to set a global example of how to transform the public sector through applied AI, and is designed to encourage the growth of technical and business AI skill sets that are in high demand across Alberta and around the world. The project comprises internships in a variety of technical and business roles within our organization and within our GovLab program. Within the organization, roles include associate machine learning developer, business development associate, communications associate and finance associate.

First Languages AI Reality ASR Pilot

The research projects will range from practical curricula development using Indigenous linguistic strategies to advanced machine learning experimentation. The goal of the intern research projects will be to advance ML science for the benefit of Indigenous communities.

Optimization of DMT Levulinic Acid Co-Product Production

“THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW”

Femmes du Nord. Une histoire des Jamésiennes

De la colonisation du nord de l’Abitibi pendant la crise des années 1930, à la fondation de camps de prospecteurs dans un des derniers Klondike, jusqu’à la création de villes de compagnies modèles, l’histoire de la Baie-James est à l’image de son territoire : diversifié. L’histoire de cette région-ressource aussi grande que l’Allemagne a principalement été étudiée sous l’angle des industries qui ont forgées son développement. Cette manière d’étudier le territoire passe toutefois sous silence la place des femmes dans le développement de ses communautés. Femmes du Nord est le premier projet de recherche à s’intéresser à l’histoire des Jamésiennes et à reconstituer la place de celles-ci dans le développement de nos communautés nordiques.

Effects of Photochemical Aging on Wildfire Smoke and Traffic-Related Air Pollution Exposures on Human Lungs: Translational Science Through Collaboration and Partnership

Air pollution is composed of gases and Particulate Matter. Wood Smoke (WS) and Traffic-Related Air Pollution (TRAP) are the two most common sources of air pollution. Air pollutants arising from WS and TRAP differ chemically. Additionally, they undergo chemical changes due to atmospheric processes, such as photochemical aging. The role of the chemical composition of air pollutants in governing mechanisms (oxidative stress and inflammation) that may translate into inflammatory lung diseases, such as COPD, asthma, etc., is not understood well. We will investigate how exposure of human lung cells to fresh and photochemically aged TRAP, WS, and TRAP+WS affects the respiratory system. This will help improve our understanding of the underlying mechanisms, which can be translated into therapy and policy initiatives. The study will contribute to the Legacy for Airway Health’s goal to improve the respiratory health of Canadians through improved knowledge mobilization, which could be translated accordingly into improved air quality standards, cost-benefit analyses for policy and funding changes, air quality health index development, etc.

Eastern Whip-poor-will landscape use and migratory tracking

The primary goals of our project are to fill critical knowledge gaps directly identified in the Federal Recovery Strategy for the Eastern Whip-poor-will regarding habitat use, prey availability, migratory paths and strategies, and overwintering sites in Southern Ontario, and to inform landowners about the presence of Eastern Whip-poor-will on their properties to support on-the-ground stewardship initiatives.

Machine Learning based Combustion Control for Zero Carbon fuels

The Canadian Net-Zero Emissions Accountability Act targets net-zero greenhouse gas (GHG) emissions by 2050 with similar commitments around the globe. In the short-term, emissions from heavy-duty internal combustion engines (ICEs) that dominate the power generation in freight transportation industry can either be reduced or eliminated with zero-carbon fuels such as Hydrogen / Ammonia. One solution is the implementation of advanced combustion and optimal control strategies for the best performance and lifespan of the ICE. Model predictive control (MPC) is one of the most promising control strategies for handling these highly constrained nonlinear systems. The research will focus on integrating machine learning (ML) for the model and controller to discover state of the art control methods to optimize energy conversion in
mobile applications. The student will have the opportunity to gain experience in machine learning, MPC and experimental engine testing during their stay at the University of Alberta.

Schéma conceptuel et conception d’environnements immersifs appliqués en contexte de loisir pour l’inclusion des personnes autistes

Ce projet vise à améliorer la participation sociale des enfants autistes et de leur famille en utilisant des activités de loisir immersives basées sur la réalité virtuelle (RV), en particulier dans un environnement de type CAVE. Actuellement, les enfants autistes rencontrent des obstacles à la participation sociale en raison de divers facteurs, tels que des environnements inconfortables et des malentendus liés à leurs caractéristiques personnelles. Le projet propose d’utiliser la RV pour créer des activités inclusives qui tiennent compte des besoins et des forces des personnes autistes, favorisant ainsi leur participation sociale et leur bien-être. Le projet a trois objectifs principaux. Tout d’abord, élaborer un schéma conceptuel novateur en classifiant les activités de loisir préférées des enfants autistes, en mettant l’accent sur le type de jeu, les compétences développées et le niveau d’interaction. Ensuite, développer un scénario de jeu spécialement conçu pour encourager des interactions fortes entre les utilisateurs, adapté aux divers intérêts et niveaux de fonctionnement des enfants autistes. Enfin, expérimenter le jeu dans des organismes partenaires. Le projet contribue à la formation du stagiaire et s’inscrit dans une initiative plus large visant à renforcer l’inclusion sociale des enfants autistes au Canada en utilisant la RV.

Decoding Political Messaging to Working-Class Voters In Canada

This research project, “Decoding Political Messaging to Working-Class Voters In Canada,” is interested in understanding how the three major Canadian political talk to working-class voters. We will be looking at what the Liberals, Conservatives, and New Democrats say about important topics like jobs, climate change, and healthcare. By exploring and analyzing their party platforms from 2003 to 2021, we want to understand the similarities, differences, and significance of what and how they are communication to working-class Canadians. This study is valuable because it can offer practical recommendations for communicators, policymakers, and leaders to do a better job of reaching everyday Canadians. The partner organization, Resonant Strategic, will gain useful information and tips on connecting with working-class citizens, making their messages clear, and tackling issues that matter to everyone in Canada.