Innovative Projects Realized

An automated system to identify and extract key structural components in academic written texts or genres

To streamline knowledge acquisition, indexing, dissemination, and synthesis—especially important to the future of libraries—a fundamental understanding of knowledge storage and communication is required. In a textual body of knowledge, relevant qualities include layout and structure; headings, chapters, sections, and paragraphs; figures, tables, lists, captions, and illustrations; authorship information and references; and, most importantly, the relationship between these semantic components. We propose research to develop a series of software model pipelines capable of producing a JSON file of an input document’s relevant semantic qualities. This inter-disciplinary project combines computer vision, natural language processing (NLP), and computational linguistics to research optical character recognition, document classification, document object detection and segmentation, document layout recognition and classification, and semantic labelling. Deep learning, statistical machine learning, and traditional computer vision-based methods for these topics will be researched and evaluated.

The real world of environmental pollutants: New approaches to identifying priority contaminants in the Endangered Southern Resident Killer Whale food web

The Southern Resident Killer Whales (SRKW, Orcinus orca) population is assessed at 73 individuals, and significant threats include high levels of endocrine disrupting contaminants, alongside other anthropogenic threats. Studies have painted a partial picture of the contaminants of concern in the SRKW food web. For example, preliminary studies of chinook salmon suggest that some resident populations are more contaminated than others which may be contributing to the high PCB burden in SRKW. This underscores the value of generating new information on contaminant concentrations and profiles in dominant prey species and / or stocks of this endangered whale population. This study presents a science-based evaluation of the contaminants found in their diet (food web) and habitat, the development, adaptation and/or application of new tools to prioritise (rank) the pollutants of concern, and the delivery of refined guidance to support of the wider conservation agenda for this (and other) at risk species

Preliminary investigation into the use of biocomposites for a solar panel support truss system

Global hurricanes create a unique clean energy production opportunity – namely to build electricity resiliency into solar energy infrastructure for weather ravaged areas of the world. Terrasol is an industry leader in the design and construction of truss systems to support such solar panel systems for energy generation. In particular, the company’s flagship system is designed to be Category 5 Hurricane resilient and have a 20-year life expectancy. This MITACS research explores different bio-derived fibres and bio-resin material options for design and manufacture of the solar systems. Unlike current solar products in the hurricane belt that are often destroyed during violent storms, the new, environmentally-friendly, lightweight composite solar canopy is aimed to withstand hurricane winds and remain electrically sound after being completely submersed during storm surge floods.

Detection of Listeria by nanoparticle-based technology coupled with a novel fluorescence device

Listeria monocytogenes is a common food-borne pathogen that is the causative agent of listeriosis, a severe and potentially fatal condition. Current methods for detection of L. monocytogenes in food samples require multiple days due to lengthy amplification steps to aid in microbe detection. Due to the recent emergence of nanoparticle technology, however, new options are emerging for removing and concentrating microbes from complex samples and providing extremely sensitive detection. This project aims to make use of nanoparticle technology in combination with a customized fluorescence reader, to provide a rapid (<8 hours), cost-effective method to detect L. monocytogenes that can be applied in a routine manner to samples from food sources. Specifically, L. monocytogenes will be targeted with....TOBECONTINUED

Refonder l’intervention de la puissance publique dans un contexte de transformation des industries culturelles et des médias : assurer la souveraineté culturelle et économique du Canada

Cette recherche s’intéresse à la compréhension des dynamiques de transitions numériques de divers secteurs de la vie économique et plus particulièrement à la transition numérique dans les industries culturelles (incluant les médias). Nous nous intéressons également aux processus d’élaboration des politiques en matière de soutien aux industries culturelles et des médias qui sont fortement affectées par la montée en puissance des grands acteurs du numériques dans ces secteurs d’activités. Le projet consiste à travailler avec notre partenaire (Syndicat canadien de la fonction publique-Québec, SCFP-Québec), membre de la Coalition Culture et Média (CCM) qui regroupe les industries culturelles dans une volonté d’assurer la transition numérique et de participer au processus de révision des lois et des politiques de la radiodiffusion et des télécommunications au Canada. La méthodologie consiste à faire un suivi analytique et stratégique des développements en matière de modification des cadres réglementaires (notamment les lois sur la radiodiffusion, sur les télécommunications et le droit d’auteur) et de permettre à notre partenaire de mieux comprendre et se positionner dans les changements en cours.

Photocatalytic Oxidation of Volatile Organic Compounds in Air

A new type of device that uses a combination of UV light, oxygen, flowing water, and titanium dioxide (a com-mon white pigment) is capable of removing volatile toxins from the air. This device will be investigated using a range of techniques that provide molecular insights into this process, and those insights will help in the rede-sign of the device to make it as effective as possible, in terms of energy efficiency, longevity, reusability, range of compounds removed, and speed of their removal. The partner organization will use these insights to develop a better, more efficient and marketable design.

Evaluation of Clustering Methods on Game Play Data

The goal of the project is to evaluate several clustering algorithms on players’ styles data in the context of Video
Lottery Terminals (VLTs). The previous work has shown that by segmenting anonymous player data by
sessions, and then clustering the sessions using the simple k-means algorithm, we can get a descriptive
statistic on player styles, including problem gambling behavior, recreational player styles, and similar. An open
question is whether the preprocessing techniques were optimal for this purpose and whether the k-means
algorithm is the most appropriate algorithm. In this project, of a number of clustering algorithms, such as
partition-based (e.g., k-means), hierarchical-based (e.g., hierarchical k-means), density-based (e.g.,
DBSCAN), model-based (e.g., statistical model based such as EM), and grid-based (e.g., STING) algorithms
will be evaluated and their performance on game play data will be analyzed.

Targeting Semaphorin 3C in Castrate Resistant Prostate Cancer

Prostate cancer is the most common malignancy in men and a major cause of cancer deaths. Androgen deprivation therapy (ADT) is the first-line therapy for metastatic prostate cancer but invariable the cancer regrows despite the androgen deprivation – this regrowth is termed castrate resistant prostate cancer. We have discovered that expression of a specific gene (Semaphorin 3C) is associated with the emergence of castrate resistant prostate cancer. The Ong laboratory has developed an inhibitor to the Semaphorin 3C pathway, and the purpose of the current study is to determine what genetic alterations in the tumour cells can result in the emergence of resistance to inhibition of Semophorin 3C signaling.

Capacity Building for Good Governance and Economic Development in First Nations in British Columbia

The Ahp-cii-uk Community Society and the Beedie School of Business are submitting a

research cluster proposal to the MITACS Accelerate Program with the purpose to continue

research conducted by the Ahp-cii-uk Leadership Initiative in the three Nuu-chah-nulth

First Nations of Ahousaht, Ehattesaht and Tseshaht. The proposed research cluster will

provide interns with an opportunity to apply lessons learned in these three communities to

well defined needs expressed by other First Nations, with the financial support of

businesses with an interest in encouraging First Nations Economic Development. Ahp-cii uk

will benefit from being able to demonstrate the utility of its process, a holistic approach

to working with First Nations on economic development projects, in a way that is

adequately documented and linked to the aspirations of the relevant communities

Investigation and design of large supercapacitor banks for grid energy storage system

Supercapacitors provide high power density, extra-long cycle life, and wide operating temperature ranges and are poised to grow rapidly in the energy storage market. They offer good complementary features to the batteries and can be used to implement fast cycling speed grid energy storage systems given the cost being driven down. With its own charging and manufacuturing technologies developed, the industry partner is set to move forward to design and implement large supercapacitor banks for distribution grid use. This research proposal is intended to identify and design optimal solutions for the targeted large supercapacitor bank, including its internal cell arrangements, balancing schemes, and investigate the behavior and performance of the designed systems.

A data-driven framework for integrating visual inspection into injection moulding pipeline

Recent advances in machine vision has led to new opportunities for automating that entire manufacturing pipeline. Consider, for example, the situation where an unattended computer vision system inspects the widget and decides whether or not to discard it. Even this little amount of automation can save many hundreds of person-hours on a typical factory floor. While for simple designs, we now have automated inspection methods relying upon lasers, 3D scanning or other imaging modalities that can decide if a widget has any defect. For complex designs, this ability remains elusive. More importantly, however, automated inspection schemes can only decide if a widget deviates from its intended design, say available in the form of a CAD drawing, it cannot decide what changes should be made down the manufacturing pipeline to prevent similar defects in the future. This project aims to explore machine learning techniques that integrate automated inspection with manufacturing process. Specifically, we will focus on injection moulding process in this project. We will develop new theory and methods for characterizing the injection moulding process in terms of quantities measured via an automated inspection system.

Preventing school dropout through community worker interventions modeling

The project is part of a desire to address the school dropout issue, particularly in multi-ethnic and disadvantaged communities. Despite the implementation of several universal interventions in Quebec, the drop-out rate remains high in numerous areas. In the Eastern Townships area, a partnership between the Sherbrooke Regional School Board and the Université de Sherbrooke in the form of a research chair has been established to study the issue since 2007. As a result, a new program (i.e., Accès 5) was initiated in partnership with a community organism, the Maison Jeunes-Est (MJE) that allowed community workers, school personnel and researchers to work together towards a common goal: better social and educational outcomes for youth. The ultimate goal of the program is to change the culture of education in the targeted community. Although the evaluation of Accès 5 demonstrated great promise for helping youth reach better outcomes, there were limitations. First, there was very little data gathered pertaining to specific undertaken actions/interventions, due to the high variability in intervention style. Second, the program is deployed in one setting, due to the limitations of the used tools. Finally, no tool enables interconnecting such variability of data sources.