New AI-based video system helps seniors stay safe and independent

The new tool uses a deep-learning computer vision system and motion-classification algorithms to capture events such as falls in real time, alert caregivers and give health-care professionals the information they need for immediate triage.

The system—developed in part by the Multimedia Research Centre led by Irene Cheng in the Department of Computing Science—transfers real-time video to an autonomous computer vision lockbox. If an event is detected, the system alerts a specified caregiver and provides a redacted video of the event.

Sound localization for acoustic monitoring of bird populations in response to fire and oil extraction in Alberta’s oil sands region

Sound localization involves the triangulation of the location of a sound source by recording it on multiple microphones. One potential application of sound localization technology is to monitor the movements of vocalizing animals passively, without the need for a human observer. This project aims to further develop and test sound localization technology, then to apply the technology to monitor the movements and behaviours of birds in Alberta’s oilsands region in the vicinity of inactive well pads in burned and unburned areas.

Characterizing wetlands of different restoration ages in central Alberta using drone-based information (an extension to current Mitacs project: Advanced mapping techniques applied to wetland drone base information; IT08204)

Wetlands provide important ecosystem services to human communities, such as groundwater recharge, storing floodwater, and supplying fishery resources. In Alberta, wetlands cover ~21% of the province, forming one of the Canada’s largest wetlands reserves; however, many of these wetlands have been impacted or lost through human activities. Over the past 30 years, there have been efforts made by the government and partner agencies to restore wetlands, but little is known about the rate of recovery and the state of these restored wetlands, relative to a natural reference condition..

Real-time Quantitative Analysis of Cannabinoids in Cannabis

The medical marijuana industry has attracted significant attention recently due to its impending legalization in Canada in the coming year. Along with legalization comes the need for accurate and dependable characterization of the components in the product that is to be consumed by the end user. Keystone Labs is a certified cannabis analysis lab with a growing client base. Hence, they are looking to increase their market share by developing a home testing kit that can be used by growers to monitor the plant's chemical composition as it matures.

Evaluation of the accuracy of the in-situ individual particle sizing technology

The research objectives are to better understand the limitations of a new particle sizing system in terms of accuracy on particle size, of accuracy on size distribution, of accuracy on particle concentration and finally of size dynamic range. During the research project, the sources of the limitations will be identified and improvements to the technology will be proposed. State-of-the-art equipment for the generation of particles with known sizes and concentrations available at the University of Alberta will be used for the characterization of the technology.

Effectiveness of EarlyDetect, a psychiatric assessment program, using a mobile APP interface

Mental health illness cost over $50 billion in the Canadian economy annually, and is prevalent at workplace. The cost and prevalence of menial health illness can be greatly mitigated with early detection and intervention. EarlyDetect is a program developed by Chokka Center for Integrative Health for convenient, accurate and reliable self-assessment of mental illness, and has been validated in a pen-and-paper form.

The intelligent virtual agent as a patient Personalized companion

In this project the intern will develop an intelligent virtual concierge and integrate it with Curatio’s social network platform. The intelligent concierge will learn about each user over time and act as a personal assistant of the user in using the social network platform.

Feature-based process modelling and customized software development for adopting ISO 10002 and ISO 10004 in Food Industry

Several customer satisfaction problems are identified in service industry as the causes of inefficiencies, and then further they could potentially lead to value destruction and loss of competitiveness. Such emerging organizational threats can be turned into opportunities by integrating a customer satisfaction management module into the existing operating software tool.

Statistical Machine Learning Framework in Retention and Attrition Modelling

Customer or member retention refers to the ability of a company to retain its customers, and customer attrition, as the counterpart of customer retention, refers to the loss of customers.

Evaluation Capacity Network: Aligning Evaluative Thinking and Practice among Early Childhood Stakeholders

This project aims to provide evidence and research support to BGCBigs in the implementation of their Building an Evaluation Framework and Capacity for Sustainability project. BGCBigs recognizes that achieving their goal of ‘supporting our children and youth on the path to success’ depends upon an organization committed to evaluative thinking, learning and utilization of evidence for decision-making. This project will enable BGCBigs to conduct quality evaluations and use evidence to improve programs for children and youth.

Pages