Projets novateurs réalisés

Centre for Operations Excellence Industry Projects 2018

The Centre for Opertations Excellence Industry Projects 2018 consists of seven sub-projects sponsored by five different industry partners. Each sub-project represents an important challenge for its sponsor. These sub-projects include Correlating Anomaly detection for Boeing Vancouver(Boeing 1), Correlating NOTAMs with airport disruption for Boeing Vancouver (Boeing 2), Using Wifi data to measure process times at YVR (YVR), Using text analytics to predict return to work for Worksafe BC (WSBC), Modelling the claim approval process for Worksafe BC (WSBC), Optimizing truck assignment during disruptions for Teck Resources (Teck), and Modelling tire failure rates for Kal Tire (Kal Tire).

Career Stage, Age, and Gender on Employees’ Ethical Challenges: a Canadian Perspective

Corporate employees face a range of ethical pressures and challenges; in some cases, employees fail at these challenges, and the result is often bad for employees, for employers, and for the Canadian public. Ethics education in post-secondary settings and corporate ethics training may help, but needs to be designed in a way that takes account of the specific kinds of challenges and pressures employees actually face. First-hand testimony suggests young people (in their 20s) face special challenges and special risks because of their junior status in the workplace. Likewise, testimony suggests that women face different challenges than men. This research aims to gather evidence about these patterns in order to create better tools for ethics education and training. This research is expected to help CleaVview Strategic Partners understand how to improve their products and services, and to help their clients improve upon their own ethics programs and ethics communication strategies.

HEAL-Me: Home-based eHealth (Exercise and Nutrition) in Cirrhosis

For patients with end-stage disease, like cirrhosis, their only treatment option is life-saving organ transplantation. The wait for an organ can take many years over which the patient’s condition continues to deteriorate as there is no other treatment. However, maintaining physical activity and a good nutritional intake is necessary to remain on the wait and have successful health outcomes post-transplantation. For many patients, this situation is challenging to balance.
Driven by our patient experiences and limitations of pre-transplant care, we are using e-health to create an accessible, home-based, interactive app. With attention to the nuances of gender and diversity in the Canadian population, our two-year research will identify motivational behavior predictors. These will be incorporated into a hybrid app/web-based platform, HEAL-Me, intended for patients with and without hepatic encephalopathy.

Quelle place pour les unités d’habitation accessoires dans la transition socioécologique urbaine au Québec ?

Depuis quelques années, on constate un engouement marqué pour le logement intergénérationnel et multifamilial au Québec. Plusieurs rêvent par exemple de se construire une mini-maison en fonds de cours ou d’ajouter un logement à leur habitation. En plus de bénéficier aux particuliers, en canalisant la croissance urbaine vers les quartiers existants, ces habitations contribuent à limiter l’étalement urbain, à optimiser les infrastructures existantes, à générer des nouveaux revenus pour les ménages et les municipalités et, éventuellement, à favoriser une transition vers des villes et banlieues plus durables. Toutefois, si l’insertion de ces nouvelles unités d’habitation accessoires (UHA) n’est pas réfléchie en fonction des enjeux de demain, elles risquent de générer des problèmes pour les municipalités québécoises. TO BE CONT’D

Cartographie des énergies renouvelables et leur chaîne de valeur sur le territoire québécois

Le stage a pour objectif de mettre à jour et de bonifier la liste des sites de production d’énergies renouvelables (incluant coordonnées GPS et caractéristiques techniques) sur le territoire québécois. Il visera également à identifier et géolocaliser les fournisseurs de biens et services de chacune des filières technologiques (hydro, éolien, solaire, bioénergies) afin d’identifier l’impact économique de chaque source d’énergie verte dans les différentes régions du Québec

Development of deep learning pipeline for automatic segmentation and classification of cardiac magnetic resonance images

Heart disease is the main reason of death worldwide. One way to understand better and detect heart diseases without need for biopsy via surgery is by using medical imaging such as magnetic resonance imaging (MRI). Cardiac magnetic resonance is a specific kind of MRI which allows great visualization of inner parts of the heart and can be used for measuring the size of the heart and its chambers, which can be very useful for understanding blood flow and other potential markers of disease. One problem with modern technologies for measuring parts of the heart is that they are often unreliable because of the data complexity. In this project, we use advanced artificial intelligence techniques to solve that problem. Our techniques are going to be used to obtain better representations of the internal chambers of the heart which can be useful for assessing several kinds of heart diseases.

Bringing Personalized Recommendation to the Legal Domain

Machine Learning has just started to be applied to the Legal Domain. ROSS Intelligence makes it possible for legal professionals to work faster and more effectively. Advanced Recommender Systems have not been previously applied in the Legal Domain. Yet state of the art models such as ones using Deep Collaborative Filtering have proven to be very effective on very sparse datasets. This project will evaluate the effectiveness of state-of-the-art Recommender System techniques applied to the legal domain in the hopes of improving the precision and recall of the current Q&A system.

Coupled human-salmon-bear systems of coastal British Columbia

The Raincoast Conservation Foundation pursues conservation initiatives in coastal British Columbia through science, outreach, and sustainable economies, such as ecotourism or community-driven fisheries management informed by local knowledge and ecology. The success of wildlife viewing ecotourism greatly depends on knowing areas and time periods predictably used by target species. The goal of the proposed research is to inform initiatives of Raincoast and its ecotourism partners (e.g. Spirit Bear Lodge, Wuikinuxv First Nation, Nimmo Bay Resort) by research on commercially-valuable wildlife. We will monitor places and times where grizzly bears eat salmon; identifying critical habitat. This information will let ecotourism operators focus their efforts and expenses on predictably high bear-use locations, which in turn supports conservation-based economies. This information can also inform the Wuikinuxv Nation of how their local fisheries, and the proposed re-opening of commercial fisheries, may affect bears’ access to salmon and in turn, potential ecotourism opportunities.TO BE CONT’D

Réalité virtuelle,

Le déploiement d’environnements de réalité virtuelle permettant l’immersion physique

des participants repose sur un ensemble intégré de technologies. Ces systèmes sont

généralement très coûteux, peu flexibles et mal adapté au travail des chercheurs en

communication ou à celui d’artistes qui désireraient développer des expériences

immersives physiques

Ces systèmes appelés CAVE 1 nécessite notamment l’emploi de systèmes de projection

vidéo intelligents permettant la reconstruction d’environnements synthétiques interactifs,

de systèmes “tracking” visuel ou gestuel permettant à un interacteur d’affecter des

composantes de ces environnements ainsi que de systèmes audio permettant la

l’attribution de sons à certains éléments de ces environnements.

Ce projet de recherche vise à employer des technologies développées par VYV dans le

domaine de la projection intelligente pour le monde du spectacle dans un contexte de

recherche en communications. Cette application transversale des savoirs entre le

monde du spectacle technologique et de la recherche en communication permettra le

Analyse du cycle de vie de la clientèle de Énergir

L’objectif de ce stage de recherche est de déterminer le cycle de vie de la clientèle de Énergir. Ces clients sont de type résidentiel ou industriel. Pour caractériser le comportement de sa clientèle, des outils statistiques issues de la littérature scientifique seront utilisées. Le projet permettra à l’entreprise de mieux cibler sa clientèle et en augmenter sa rétention. La stagiaire fera une étude approfondie des données internes de l’entreprise et travaillera également sur la mise au point de modèles prédictifs concernant les différentes décisions que le client pourrait prendre.

Generating realistic customer purchase baskets using Generative Adversarial Networks (GAN)

This project uses the purchase history data from loyalty member cards at the basket level (i.e., all items bought by a customer during a particular trip) for customers under the loyalty program of a chain drug store to develop a model that can generate a realistic future “customer shopping list” (i.e., customer baskets) using the novel machine learning technique of Generative Adversarial Networks (GAN). Specifically, the goal of this project is to use the above data to build a simulator that would predict for a given customer, multiple possible future baskets of items during his/her next four trips (one trip per week) conditioned on the previous weeks’ baskets. This project has significant potential applications to allow retailers to better predict demand and revenue potential at individual customer level including better supply chain and inventory management as well as more personalized promotion planning.

A New High-Speed Warehousing Cable Robot: Prototyping, Evaluation and Commercialization

As consumer preferences shift from shopping at brick and mortar stores to on-line shopping, there is an increased need for warehouses to use automated systems that fill orders quickly and accurately. This research project will design a warehouse robot that is adaptable to different platform systems and shelving configurations, providing a lighter, faster, and more cost-effective warehousing system. Key competitive advantages to our partner, Dematic, include (1) orders filled 30% faster than current systems, (2) the flexibility to adjust the robot for different weight/capacity requirements, (3) a smaller footprint with higher storage density, and (4) lower capital, running and maintenance costs.