Innovative Projects Realized

Rapid Digital Twin and Ontology Builder for Buildings

Schneider Electric (SE) is developing their EcoStruxure Building Operations (EBO) system as a next generation Building Management System (BMS) that will combine data collected from the building into a Smart Digital Model (“Digital Twin”) that will be able to answer building users’ questions. This project will develop the tools necessary to develop such a Digital Twin, including defining its capabilities, identifying the information required to achieve the required functionality (including data formats and organizational structure), and developing a working prototype for a reference building. To maximize the benefit to SE, who would like to deploy this across a broad range of buildings, this approach must be replicable, scalable, and appropriately documented.

Correcting specular reflections for computer vision in collaborative robotics

Unlike traditional industrial robots, collaborative robots are meant to be used alongside workers. They can also be taught their task by the workers themselves instead of robotic engineers. This means that these robot have to be inherently safe and be able to properly perceive their environments when performing tasks such as picking parts from a conveyor belt. Because these robots can be taught in a wide variety of environments with people moving in and out, this also means that the operating conditions, especially lighting, can be quite dynamic. This produces unwanted artifacts such as reflections and highlights in images used to perceive the environment, and traditional processing systems to perform poorly. This project aims at developing an algorithm based on deep learning to correct such artifacts and allow these robots to work properly in non-ideal lighting conditions, enabling the workers to focus on the task instead of the robot’s needs

Microfluidics Study of Three-Phase Non-Equilibrium Phase Behavior

CO2 management have been an important research theme to minimize the GHG impact on Canadian environment. Enhanced oil recovery by injecting CO2 underground is a very efficient way to minimize the CO2 environmental effect. Meanwhile, after primary and secondary production, either CHOP or CHOPS well present a high water cut in the produced liquid stream. This high water cut has a significant effect on choosing the proper post-CHO techniques. Therefore, in order to understand how the presence of various aqueous phase interacts with CO2 injection in heavy oil reservoir, non-equilibrium phase behavior study will be conducted on three-phase system under multiple reservoir operating schemes within the equipment allowable range of 0.1MPa—20MPa and 20?— 180?. Multiphase flow system mainly includes CO2 and heavy oil, with the addition of other aqueous solutions, such as brine, polymer, surfactant, alkaline solution etc. A profound understanding of solvent-heavy oil-aqueous solution three-phase non-equilibrium phase behavior will be achieved.

Automatically Assessing Frailty from Medical Notes

Frailty is an especially problematic expression of population ageing. It is a condition characterised by loss of biological reserves across multiple organ systems and vulnerability to physiological decompensation after a stressor event. Older people with frailty are at increased risk of adverse outcomes including disability, hospitalisation, nursing home admission and mortality. This project addresses the issue of predicting frailty in patients by automatically processing medical notes taken by health professionals when consulting those patients. The result of this research could provide valuable information for physicians and other health professionals for individual patient care, as well as epidemiologic indicators on the overall population. The problem will be addressed by evaluating three different, but maybe complementary, approaches: Natural Language Based (NLP) processing, frailty index prediction using deep learning and summarization techniques. Besides, we intend to study in this project two side aspects of the application of technology to the health domain: the explainability of automatically generated predictions and knowledge discovery.

Évaluation de la conscience de la situation des pilotes de navires du Saint-Laurent et des Grands Lacs

L’analyse des accidents de navires indique que 80% des accidents ont pour origine un problème de facteurs humains et que la mauvaise conscience de la situation de la part du pilote est le facteur causal principal à l’origine de ces accidents (C. C. Baker & McCafferty, 2005; Barnett, 2005). La conscience de la situation est de savoir ce qui se passe dans et autour du navire, comprendre ce que cette information signifie par rapport aux buts de la mission et comment elle évoluera dans le temps. Développer cette meilleure compréhension de la conscience de la situation du pilote dans ses tâches de navigation permettra d’améliorer le bilan de sûreté du transport maritime.
Dans ce projet, nous modélisons les variables clés de la conscience de la situation des pilotes de navire pour des scénarios critiques et dynamiques (croisement, dépassement, ancrage) à partir d’une analyse des buts cognitifs du pilote. Ensuite, nous concevons un outil d’évaluation de la conscience du pilote basé sur l’approche SAGAT pour les scénarios étudiés. Cet outil est utilisé pour évaluer la maîtrise des éléments de conscience de la situation des pilotes en formation. C

Use of Terrestrial Laser Scanner to access plant structure and tree volume at Gardens by the Bay – Singapore

The forestry sector is one of the important pillars in the Canadian contributing to 1,6% for the country`s GDP. Access forest structure and quantifying leaf and wood elements is essential to understand productivity and environmental contribution of trees and forested areas. Light Detection And Range (LiDAR) produces a 3-Dimension point cloud with high spatial resolution, therefore, Terrestrial Laser Scanners (TLS) arises as an important tool to measure efficiently forestry metrics fast and at a low cost. There are several TLS sensors that have different spatial resolution, field of view, range and laser wavelength. Diverse methods have been used to access different forest parameters. The presence of wind, dust and humidity on the atmosphere are limitation for accurately measure forest metrics. We will be using two TLS systems to generate high spatial resolution digital models and calculate tree volume and biomass in a controlled environment at Singapore Gardens by the Bay (GB). The possibility of scanning in a complete controlled area brings the possibility of testing different approaches and methodologies, on a diverse group of trees from temperate to tropical ecosystems, which could be used on natural areas increasing the performance and accuracy of the measurements.

Research Visit – Environment and Development Economics

While at Berkeley, I would mostly be working on my sole-authored paper. This paper links trade and the environment in Brazil. Using the major trade liberalization episode in the early 1990s as a plausible source of exogenous variation, my paper investigates two hypotheses. First, increased international competition in manufactured goods negatively impacted the least productive industries. This so-called “deindustrialization” of Brazil may have reduced its pollution emissions, especially if these less productive industries happened to be the most polluting. However, to the extent that Brazil responded to market opening by becoming a pollution haven, pollution emissions may have increased.

This research visit will allow me to collaborate with world leading experts on the issues of the environment, climate change and the measurement of their consequences. The project involves not only an analysis part but also the creation of a dataset using data science (remote sensing) in order to build the kind of pollution emission measurements developed countries have but developing economics lack. Give Reed Walker’s research agenda,(associate professor at Berkeley who hosts me), is the ideal person to collaborate with, as he worked on both of these issues.

Population Health Assessment Bridge for Ontario (PHABIO)

“The purpose of this project is to develop a web-based reporting system to provide central analytics for key public health indicators in Ontario. This project will enhance the capacity of health units to fulfill the foundational standard of the Ontario Public Health Standards. The project will also provide an opportunity to engage and establish partnerships in the area of indicator development and health status information while building on Public Health Ontario’s own data and information strategy and data acquisition strategy. It is anticipated that this work will become part of Public Health Ontario’s core business and be an ongoing initiative.”

Engaging More Men in Mentoring

A key factor in fostering the resilience of children and youth is the presence of at least one caring adult who holds high but reasonable expectations of them. In some instances, this relationship is formally facilitated by an organization in the form of mentorship. Despite the documented positive effects men have in the lives of children, the majority of mentors are women. Many organizations report having significant difficulty recruiting and retaining male mentors despite a growing demand. To date, virtually no research has been conducted in Canada to explore this issue. In this project, we will carefully examine the research that has been conducted in the United States and abroad and have systematic discussions with organizations in Alberta who are engaged in mentoring. The overarching goal of this project is to provide Canadian based guidance and resources to mentoring agencies to support them in recruiting more male mentors.

Probiotic lactic acid bacteria-derived secretome impact on intestinal epithelial and antigen-presenting cells: determining effects on immunometabolic and epigenetic reprogramming in the context of cell interactions

While intestinal bacteria are increasingly understood to be important for maintaining health, many questions remain about how probiotic bacteria act to influence the immune system. We have previously found that one of these bacteria, Lactobacillus rhamnosus R0011, produces mediators able to influence communication between intestinal epithelial cells and antigen-presenting cells, cell types important for our immune defences. The objectives of this research project are to determine whether additional probiotic bacteria also produce these types of mediators, and to examine how these mediators act on intestinal epithelial cells and antigen-presenting cells using approaches that facilitate cell interactions and allow for production of mucin, a component of the mucous layer in the gut. By investigating the impact of these bacteria and their secreted mediators in this context, we can also determine the impact on antigen presenting cell metabolic activity, now recognized as an important way in which behavior of these cells is controlled. Determining the ways in which the products of these bacteria influence activities of and interactions between intestinal epithelial cells and antigen-presenting cells will give in-depth information about the impact on our immune defences and in turn, insight into their impact on health, information of use

Processus d’amélioration continue dans les mines – optimisation de la gestion des stériles miniers

Durant les années où les prix des métaux ont permis une hausse des revenus pour les minières, ces dernières ont constaté que cette hausse ne s’est pas traduite par des profits substantiels pour les investisseurs. Ce constat a amené les minières à réfléchir à leur mode opérationnel et à développer un processus d’amélioration continue inspiré de celui utilisé dans le domaine manufacturier. Ce développement consiste à adapter les pratiques actuellement utilisées en grande partie dans le domaine manufacturier et surtout à développer des indicateurs de performance propres à l’industrie minière. Ce projet s’intègre dans cette philosophie et permet d’avoir une vision plus complète de la chaîne des valeurs du processus minier en intégrant la géologie et les gestions des stériles miniers. Ce projet, piloté par groupe MISA, impliquent une compagnie minière productrice d’or.

The effect of peer-to-peer video modeling (VM) on socialization and physical literacy in individuals with autism spectrum disorder (ASD)

According to literature, individuals with Autism Spectrum Disorder (ASD) can imitate movements since they have learned many social, vocational, speech, and academic skills. However, motor skill deficiency has been mentioned as one of the contributing factors to social isolation, reducing opportunities for people with ASD to be connected to society and peers. Improving motor skills increases their confidence to participate in social interactions. This research project has two aims: (1) to teach fundamental motor skills through video- modeling with tablet technology and (2) to encourage socialization where participants with ASD interact and discuss their performances with peers with ASD through peer-to-peer learning using a structured format. The Asperger Autism Friendship Society (AAFS) provides support to a large Autism population in Calgary. This project will provide support for a research-based program that will increase the validity of various kinds of interventions, attract more clients to be a part of intervention programs, and increase the social skills and physical literacy of persons with ASD.