Detecting defect inducing changes

This project will look at improving the quality of software by using AI to determine if a defect / issue exists and if so where it exists for easier fixes. This research is innovative and this domain is not proven. The student will explore new techniques for a highly relevant issue in industry. The industry partner will gain insight and knowledge into how improvements can be made ultimately resulting in faster time to market and potential cost savings.

Continuous calibration, interpolation and predictive analytics using Machine Learning

The company provides devices to measure quality of curing light used in dental procedures. These devices produce high volume and high velocity data. This data is then used to forecast a future state and to make a well informed business/operation decision according to an expected future state. One of the challenges in application of such technology is to improve prediction accuracy of the forecast. The company has developed prediction models based on physical chemistry that have been very useful to both the vendors and dentists.

Robust Non-contact RF Sensing for Human Vital Sign and Activity Monitoring

Non-contact sensing for vital signs and human activities utilizing wireless signals has attracted a lot of attention in the last few years. Sensing using Ultra-wide-band or milli-meter wave radios is advantageous in its ability to penetrate garments or walls, operate under different lighting and weather conditions, and better preserve people’s privacy. Despite successful research demonstrations, there remain significant gaps in practical adoption and deployment. Many challenges need to be addressed to handle the presence of multiple subjects, subject diversity and environmental interferences.

AR Marine Visualization System

A sailor needs to obtain real-time information about the status of the sailboat and also derive an accurate approximation of the behaviour of the surrounding environment, in order to safely and successfully sail a boat. We also aim to investigate how providing vital knowledge using an immersive approach will affect the cognitive load on the sailor, thus potentially enhancing efficiency and safety at sea.

Sensor Rank and Selection to Determine the Best Sensor to Increase the Efficiency of a Garbage Disposal Service.

In this modern world one of the biggest problems we face is waste control. As the population grows, so too does the waste being produced by humans. Our company is proposing to add a sensor to commercial garbage bins to detect when bins are full and thus trigger waste collection. This project will aim to identify the best sensor to use in a commercial garbage bin and will propose adding network technology to create a “smart” system. Sensor framework design and selection will be researched by this undergraduate team.

User Adaptive Systems for Behaviour Change in Health And Wellness

There has been a dramatic increase in digital well-being products in recent years and there is a market saturated with ineffective user experiences and little to no sustainable, desired behavioural change. By assessing and enhancing the effectiveness of a personalized approach to digital well-being app interaction through machine learning and emotion-driven adaptive computing, we can develop a new, intelligent and highly effective digital well-being platform that can support lifestyle wellness behaviour change.

Creating a migration utility for a SaaS Content Management System (CMS) platform

A content management system (CMS), is an application that helps control the creation, publishing and archiving of site's content. CMSs also allow extending the functionalities of a site by installing modules or plugins. A considerable number of different CMS platforms with variety of sizes and capabilities can be found on the market. Some of the most popular CMSs are Joomla, Drupal, and WordPress. With the varies capabilities those CMS provide, organizations may decide to migrate their CMS-based Web applications to other CMS platforms to better meet their needs.

Intelligent Lawn Mow Routing using Automatic Vehicle Locator Technology for Smart City

In Winnipeg, MB, grass and weed growth can be seen during the summer, up until the middle of October. Weeds such as dandelions are hazardous to human health as they can trigger allergic and asthmatic reactions to the public. Their roots can grow up to two feet long if not removed on time. During the grass growth period, the City of Winnipeg uses many mowers of different sizes and horse-powers to mow and remove the weeds in boulevards, athletic fields, parks and other city owned green spaces. Currently, mowing routes are decided manually by the foremen. This is inefficient and time consuming.

Solving the integration problem for loyalty programs

Paying with a mobile phone within brick and mortar retailers is becoming increasingly popular, as it adds convenience as well as security to the payment process. Many retailers that use interac terminals with tap technology allow mobile phone payments in this way but are unable to integrate loyalty points into the mobile payment process.

Generative models for controlled generation of synthetic sequence-based datasets

At a high level, the goal of this project is to create a system for producing synthetic datasets based on real data. As a large financial crime detection firm, Verafin deals with large volumes of sensitive data which must be kept private, however they are also interested in collaborating with academics to gain new insights into their data.