Projets novateurs réalisés

A causal discovery approach based on synthetic data and its application in contaminant transport modelling and card fraud detection

This project will apply causal discovery methods to two model-generated datasets. One is a dataset describing the transport of emerging contaminant metformin in the groundwater; the other is a card fraud transaction dataset. The method will examine the dataset’s underlying structure (data skeleton). Multiple new methods will be evaluated and tested on the datasets. The synthetic datasets are designed to reflect the real-world scenario to the maximum extent. The study results can help gain new knowledge on the contaminant transport process and the credit card fraud problem, test the performance of the causal recovery methods in different domains and guide the design of the causal discovery framework in multiple scenarios.

Understanding diverse COVID-19 outcomes at the cellular and molecular level

Approximately 40% of COVID-19 survivors experience the Post-Acute Sequelae of COVID-19 (LONG-COVID-19) or Long COVID. It is currently not possible to predict who will become long-haulers and continue to experience symptoms that last for weeks or even months. The goal of this project is to better understand the molecular underpinnings of diverse patient outcomes in COVID-19 and develop molecular diagnostics that can identify specific patient groups for targeted management, improving patient care and allocation of scarce resources to those who need them most. Our research team has unique access to IMPACC study, a unique resource that includes comprehensive molecular profiling at many time points during infection, as well as in long-term follow-up, on a large group of COVID-19 patients. Crucially, the size of this cohort allows for capture of disease variability driven by emerging variants, as well as the effect of vaccines in diminishing disease. The molecular signatures we develop will be validated using ongoing Canadian research cohorts.

Voice Activity Detection in Real-Time Speech Processing using Deep Learning

The COVID-19 has changed dramatically the educational environments in all countries over the world. Due to the pandemic, online education has played an important role over the past two years while in-person classroom teaching had to be prevented. Under the present pandemic circumstance, although a quite number of courses at many universities had being held remotely, transferring all the educational activities online would bring many issues to both trainers and trainees. One of the key issues is about the lack of an integrated advanced online learning platform with which instructors can prepare course material conveniently and efficiently. Also, the present form of online teaching is mainly based on the slides prepared before hand, which makes learners tired and bored. On the other hand, some educators offer e-courses by providing pre-recorded videos. However, these videos either present slides or make use of a traditional classroom board setup, which is not efficient either, since the instructors lack of intuitive and inspiring means of delivering the material. In this project, we aim to develop a novel intelligent speech processing system based on artificial intelligence (AI) to facilitate remote teaching.

Understanding how to Decolonize as an Indigenous-led Organization in a Western Funded World

In partnership with the Mi’kmaw Native Friendship Centre (MNFC) researchers from Dalhousie are interested in investigating what decolonization means to an Indigenous led organization that resides in a Western funded world. MNFC is interested in learning how to navigate what does it mean to be decolonized and how to engage with partners going forward. The project involves a literature review and interviews with people inside and outside of MNFC with the end goal of creating a decolonization framework that MNFC can implement. MNFC will benefit from this project because they will be able to apply this framework in their organization to set principles and boundaries to ensure they have decision making authority when working with Western organizations.

Gold mineralization at the Engineer Mine, northern British Columbia: Its causes and consequences for local and regional gold exploration

At the Engineer Property in northern British Columbia, gold-bearing epithermal (shallow heat) quartz-carbonate veins feature electrum (gold-silver alloy) and roscoelite (a vanadium mica), an association which has not been well studied in similar gold deposits. The igneous heat source for the veins has not been proven, but is believed to be the Eocene Sloko Group volcanism and the nearest igneous body is thought to be related to this volcanism. However, minimal age dating has been done in the area. Gold is also present in a regional shear zone called Shear Zone “A”, but its relationship to the epithermal veins is uncertain. The main objective of this study is to develop a deposit model for the high-grade gold mineralization. This deposit model should address the following questions: (1) At what temperature and pressure did the veins form? (2) What is the mineralogy and geochemistry of the veins? What does this tell us about the source of the gold? (3) What are the structural and spatial relationships between the geologic features of the area? (4) What is the chronology of the formation or emplacement of the geologic features?

Business Strategy Internship with Healthy Cow and ProPreg

Healthy Cow is an agriculture biotechnology company with a primary focus on the dairy industry, although its research is applicable to all livestock. All of Healthy Cow’s research is based on healthy metabolome and microbiome.Healthy Cow has worked over the last five years to advance research out of the University of Alberta. The first technology and product is called ProPreg. This intra-vaginally designed technology is formulated to maintain a healthy microbiome. With the launch of this innovative product soon approaching, this project will be essential in developing marketing, sales and the necessary high level strategic planning needed for the launch of ProPreg. The role of the intern is important in providing business development activities and the development of sales and marketing materials.

Multi-Channel User Acquisition Marketing System – ShopHopper

Okanagan College interns to develop Multi-Channel User Acquisition Marketing System for technology start-up, ShopHopper.
Interns will develop a multi-channel marketing system to allow ShopHopper to hit user acquisition and sales goals. This research and applied project will involve the development of detailed processes for each type of marketing initiative, testing and re-testing different content strategies and channels, consistent creative content development specialized to each marketing channel, strategic community development on social media, and the successful execution of blitz public relations and legacy media campaigns. With a researched and developed marketing system, ShopHopper will be able to reach user acquisition milestones and also give local retailers the growth marketing sales channel needed to scale their eCommerce business, compete with big-eCom/big box stores, and sustain themselves as independent retailers.

Assessing hydrothermal methods to monetize pulp and paper biomass residues

Biomass residues from forestry operations (sawdust, bark, pulp and paper sludge etc.) have a myriad of potential applications if repurposed, however are often simply disposed of in landfills or stockpiled at sawmills. In this work we will investigate hydrothermal processing of two of the highest volume of residues produced; sludge from pulp and paper processing (a “wet” biomass) and bark, sawdust, and chips.

Sensory Friendly Solutions Go to Market 2022

Sensory Friendly Solutions, a B Corp Certified, for-profit social enterprise is undertaking a project to improve accessibility and inclusion by establishing the pathways to deliver products and services to businesses and organizations that make them more sensory-friendly for their customers and their employees.

StrokeSENS ML brain data improvement and verification

Circle Neurovascular Imaging (Circle NVI), a wholly owned subsidiary of Circle Cardiovascular Imaging (Circle CVI) and a joint venture with the Calgary Stroke Program, is building a software as a service business aimed at providing physicians with an acute stroke decision aid tool, StrokeSENS™ that will leverage artificial intelligence (AI), advanced image-processing, and network connectivity to support physicians and other healthcare team members to simplify stroke care, with a focus on enabling front line stroke centers. Circle NVI’s mission is to simplify stroke care by augmenting front-line physician decision making.

The intern, working closely with the company’s medical affairs and R&D functions in collaboration with the University of Calgary, will aid the company in the preparation and analysis of medical image data in support of product quality assurance and clinical validation. The intern will have the opportunity to leverage technical skills as an image processor while working on project activities related to process innovation for data management, visualization, and quality control.

Biotic communities in restoring salt marshes

Salt marshes are important coastal ecosystems that provide many services. Due to their high soil fertility, they have a long history of being converted to farmland. There is now growing interest in restoring salt marshes to protect against coastal erosion, mitigate sea level rise, and provide increased habitat for fish, birds, etc. Ducks Unlimited Canada and partners initiated 5 salt marsh restoration projects between 2010–2020, in the Bay of Fundy and southern Gulf of St. Lawrence, with goals of reverting pastureland or freshwater impoundments back to salt marsh, and assessing effectiveness of restoration methods. The undergraduate Co-op MITACS intern will assist, and thus gain experience, in quantify patterns and rates of restoration of biotic communities, including plants and invertebrates on the marsh platform, aquatic fauna in salt pools, and fish entering the marsh via creeks. This information will help determine best management strategies and be useful to various industries (environmental consulting, agriculture, transport) and agencies interested in salt marsh restoration.

Developing efficient computational simulationtools for geophysical applications

Quantitative interpretation of magnetic data through inversion for general distributions of magnetic susceptibility has played an increasingly important role in mineral exploration in recent years. The goal of the proposed project is to develop efficient and robust computational simulation tools for the inversion of magnetization at a specified depth using ground/airborne magnetic data. A numerical algorithm based on the preconditioned conjugate gradient method with Teoplitz matrix, which is well studied in the field of image processing, is extended to construct a fast and robust method for geophysical applications. The method provides a more accurate and detailed magnetic mapping, so that the geologist will have a better understanding for subsurface geology environment. Preliminary research has demonstrated that significant improvement compared to the existing method using the re-weighted regularized conjugate gradient algorithm can be achieved by the proposed method. Working together with TerraNotes, we plan to refine and promote this new technique to geophysical community.