Compound recommendation for plant health using machine learning and computational chemistry

Virtual screening is a computational technique used in drug discovery to search large libraries of small molecules in order to identify those structures which are most likely to bind to a drug target, typically a protein receptor or enzyme. Virtual screening is thought to have the potential to speed the rate of discovery by reducing the need for expensive and time-consuming lab tests to physically test thousands of diverse compounds, often with an expected hit rate on the order of 1% or less with still fewer expected to be real leads following further testing.

Research on the Social and Ecological Impacts of “The Thingery” Community Sharing Platform

The Thingery Sharing Inc. is the logistics provider and parent organization of five co-operatively owned community-level goods lending libraries known as Thingeries located throughout the Lower Mainland of BC. As a data-intensive enterprise, Thingery Sharing Inc. has the potential to track the social and ecological impacts of community level goods sharing. However, the existing literature provides insufficient guidance on how to structure indicators of social impact in the newly emerging sharing economy.

The Use of Enhanced Percentages of XY and YY Males and Protemics to Increase Freshwater Closed Contained Farmed Production of Sockeye Salmon

At harvest, the males of a mixed female/male culture of farmed Sockeye salmon are larger in freshwater culture. This research will enhance the percentages of male fish in a mixed female/male cultured population of Sockeye so as to increase the harvest weight of the fish. In addition, proteomics will be used to identify key markers of metabolic processes that can be used in ‘real time’ to ensure the Sockeye are cultured in a way that ensures the good welfare of the fish.

Statistical and Physiological Beat Modelling of Seismocardiogram Signal - Year 2

"Seismocardiogram (SCG) is a signal that is captured by placing an accelerometer on the human chest. This signal captures very important timing information such as opening and closing of the heart valves. In addition to these timing information, the non-invasive nature of this signal makes it an attractive solution for remote monitoring of patients with heart conditions.
The morphology of SCG signal changes depending on different types of heart conditions and diseases. A mathematical model represents the morphology of a signal in terms of certain parameters.

Investigation of remote diabetic retinopathy screening implementation on British Columbia healthcare costs

Fifty percent of diabetic patients are expected to develop some level of a vision threatening problem known as diabetic retinopathy (DR). Although blindness caused by DR is very common amongst diabetic patients, it is preventable in at least 90% of the patients through annual screening and proper follow up. However, financial burdens, lack of access to a specialist (specially in remote areas) to perform routine checkup and the specialists’ busy schedules make it almost impossible for many patients to follow up properly on the status of their disease.

Machine learning approaches for event prediction, relation modeling, and inference

Machine learning approaches are transforming fields such as finance, healthcare, electronic commerce, social networks, and natural disaster forecasting. We propose collaborative research that develops novel methods and applications of machine learning techniques for event prediction, modeling relations between entities, and inference techniques that can impact these domains. In the context of event prediction, we will develop methods based on the point process framework.

Intelligent mini-unmanned Aerial Vehicles (UAVs) for automated skin cancer screenings

The main goal of this project is to design a UAV-based image acquisition system to capture high quality full body images which will be integrated into DermEngine Full Body Imaging (FBI) module. With this system, we intend to achieve consistency between different images that FBI needs to analyze.

Community Land Trusts: Exploring civil society’s role in reconciliation and the housing crisis

This research project aims to explore how civil society organizations in Metro Vancouver might devise Community Land Trusts that allow their property interests to intersect with their social mission. Metro Vancouver Alliance, a broad-based community organizing alliance of faith, labour, community, and education sectors, previously conducted listening campaigns identifying reconciliation and affordable housing as common priorities. Some MVA faith institutions have expressed interest in redeveloping their property through CLTs to serve this shared social mission.

Design Analytics

Architectural design data have mostly been limited to visual representations, specifications and contractual documents. Today, design firms generate vastly more and diverse data, but lack adequate access to tools to gain insight from such data. Yet the field of “visual analytics” provides concepts and systems exactly for working with such data. The proposed research aims at the visualization and analytics of design data, that is, collections of designs, their alternatives, project documentation, and other data collected from buildings and their settings.

The Development and Implementation of a Cumulative Effects Management System in Metlakatla Territory

The proposed research is the second phase in the development of a strategic resource management system with the Metlakatla First Nation. Metlakatla are developing a cumulative effects management (CEM) program to deal with the combined impacts of numerous major industrial projects proposed in Metlakatla traditional territory on British Columbia’s North Coast. Phase 1 of the of the CEM program focused on identifying and assessing the condition of high-priority Metlakatla valued components (e.g., butter clams, housing supply).