Development of simulation-based training modules for the SGI graduated licencing program

Proper education and training are necessary to ensure young drivers have the appropriate knowledge and skills to drive safely. The current Saskatchewan Government Insurance (SGI) graduated licensing program has education components and some in-car practice sessions, however, data shows that many young drivers are still involved in accidents due to a lack of experience driving in difficult or challenging situations.

Automatic Generation of Career Advice Articles is a well-known employment-related search engine for job listings worldwide and is the number one job site in Canada. In addition to job listings, Indeed provides other job seeker content like career advice articles about jobs and required skills for different professions. Indeed hires freelance human writers to produce these articles. However, human writers are slow, expensive, and can produce content that varies drastically in quality.

Model Calibration and Optimization of Oil Sands Tailings Electrokinetic Dewatering

Alberta oil sands mining operations have produced about 1 billion m3 of fluid fine tailings (FFT) stored in large "ponds" up to 10 km long and 4 km wide. FFT is a stable colloidal suspension that is forecasted to take decades to dewater if left undisturbed. The EKS-DT process, developed by ElectroKinetic Solutions, has the potential to be a cost-effective technology for dewatering FFT; understanding how the FFT properties respond to the EKS-DT process is a critical step in commercializing the technology. The EKS Model is a computer simulation program designed for this purpose.

Semantic Search and Visualisation using Machine Learning and Natural Language Processing

This project tackles the issue of knowledge incompleteness and lack of domain coverage in resume and job posting matching caused by the exploitation of domain-general resources. A variety of co-operative semantic/ontological resources will be used to filter out irrelevant resumes. A two-way (candidate to job and job to candidate) semantic-based automatic suitability ranking is proposed. The suitability is determined by the semantic distance of resumes and job postings, evaluated by their word embeddings.

Digitizing the End-of-Life Final Document Service

During COVID-19, unexpected death has become more commonplace, and many are finding themselves in the unfortunate position of dealing with their loved ones’ estates while continuing to worry about their own health and well-being. In a time where we are asked to stay indoors to protect ourselves and help ‘flatten the curve’, grieving family members are expected to deal with dozens – or even hundreds – of administrative tasks related to the estate of their deceased loved one.

Optimizing the use of recycled treated fines in eco-efficient concrete mixtures

Concrete is a major construction material used worldwide responsible for the production of roughly 7% of total global carbon dioxide emissions. The extent of its environmental impact relates to the energy embodied in extraction and transportation of concrete aggregates with a direct link to the amount of Portland cement (PC) used to bind the raw materials. Recent advances in design protocols, packing models, and geopolymers are increasingly being used to minimize concrete’s carbon footprint and to produce PC free mixes.

Wise Practices in Indigenous Entrepreneurship Education

In partnership with Tribal Resource Investment Corporation (TRICORP), the University of Victoria (UVic) Gustavson School of Business co-created and designed the Aboriginal Canadian Entrepreneurs (ACE) program. The ACE program provides entrepreneurial training, mentorship and coaching for members of First Nations communities, governments and financial institutions in their home communities.

Asset Information Modelling for Non-Urban Environments (AIM-NUE)

In 2016, in partnership with The Ontario East Economic Development Commission (OEED), we started exploring the potential of AIM to represent and manage multi-dimensional graphic and semantic assets related to a geospatially large (40,000+km2), non-urban environment in Eastern Ontario. The area under study is comprised primarily of what Statistics Canada identifies as “rural and small town” (RST) census subdivisions with varying degrees of metropolitan influence.

A Multi-Case Study to Advancing Accounting, Financial Reporting, and Performance Management Strategies

The role of accountants, especially in today’s fast changing data-driven world, is continually evolving. Responding to the technological advancements as well as to the increasing amounts and complexity of data available, accountants need to develop skills that go beyond their traditional training. Businesses and their accounting departments need to be able to not only collect information through billing, reporting, and operations, but also need to be able to evaluate and analyze the information received from internal and external sources.

Speaker Diarization for Audio Transcription

This research is concerned with speaker diarization for the purpose of facilitating automated speech transcription. This problem has multiple depths depending on the prior knowledge provided to the system. The type and amount of information about the number and characteristics of the speakers can differentiate this problem in a range from a 1-to-N matching, where the voice is compared against different templates, to a clustering problem, where no prior knowledge is available.