Development and Application of Marine Mammal Density Estimation Methods for Directional and Omnidirectional Hydrophones

Estimates of the population density of marine mammals in an area and the change in population over space and time are critical inputs for managing the interactions of human activity and mammal populations. Visual surveys from boats, shore stations, and aircraft have served as the basis for most population estimates currently used by managers. However, these survey methods are generally only performed in good weather conditions and require many trained observers. These factors make visual surveys expensive and reduce the temporal and spatial coverage of population estimates.

Improving Efficiency and Robustness of Model-based Reinforcement Learning

Model-based reinforcement learning allows AI systems to learn and use predictive models of their environments to plan ahead, achieving tasks more efficiently. The proposed project aims to (i) develop methods for identifying when an uncertain and/or flawed model can be relied on to make plans, and when it cannot, and (ii) implement a method which allows an AI system to explore its environment exactly when exploration will be most useful for improving its model-based predictions and plans.

Real Estate Information System User Experience Analysis

Real estate information systems (REIS) provide real estate market participants with information that helps inform their decisions. Most prior REIS research has focused on price estimating and forecasting. Although price is important, it is not the only variable of interest.

This research seeks to investigate the needs of REIS users. Who are they? What information do they need? How should that information be presented to maximize its accessibility? How do users’ stated preferences for information differ from their revealed preferences?

Designing a virtual gym with innovative grammar recognition to develop an individualized exercise platform for older adults

Virtial-Gym motion-tracking-based system to exercise regularly and safely at home, guided by the expertise of physical therapists who can remotely monitor their clients’ progress. The innovative exercise grammar that therapists can use to describe personalised exercise regimens for their clients.

Automatic Understanding of the Semantics of Source Code For IdentifyingSensitive Code Fragments

Source code is what programmers write as instructions to the computer to execute to complete a desired task. All operating systems and applications on a computer or a mobile device is a runnable version of a compiled source code. Experienced programmers can easily browse and understand source code in different programming languages because they have the necessary technical background that is not available for every-day users.

Designing Student Success: Building a Mobile Application to Improve Student Retention and Persistence

Ipse offers self-help to students transitioning to college or university to achieve their goals in a way that suits their personality. It uses machine-learning and crowdsourcing to recommend action plans to the students. The proposed research in collaboration with Ipse is aimed at furthering our understanding of personality traits and identification of suitable action plans based on those traits. Specifically we will survey a target population to identify common student traits and the associated action plans.

Automated Land Use and Land Cover (LULC) Classification for Hydrological Modelling and Physically-Based Inflow Forecasting

The problem considered in this work is how to produce highly accurate and consistent land-use/land-cover (LULC) maps significantly faster than current semi?automated methods for use by Manitoba Hydro. The goal is to improve the ability to produce maps quickly and efficiently as priority needs arise. This project will use an approach for automated LULC mapping from satellite images using deep learning methods pioneered by the applicants. By classifying each pixel in a satellite image into LULC categories using neural networks, rapid and accurate LULC maps can be successfully produced.

Learning non-local features for 3D reconstruction of buildings

The goal of this project is to help automate the process of scanning buildings with consumer digital cameras. Currently, fully automated scanning with a commercial camera produces inaccurate scans, while accurate scans require significant manual effort on each individual photograph (of which there are many) of the building to be scanned. We plan to use modern machine learning techniques to reduce the human labor required to create very accurate 3D scans of buildings.

Hybrid and multi-device quantum machine learning models

Over the past 2-3 years, commercial quantum computing hardware has begun to come online. While emerging quantum processing devices (QPUs) are still small and noisy compared to ideal quantum hardware, they are nevertheless expected to demonstrate quantum supremacy soon. During the same period, quantum machine learning (QML) has emerged as a rapidly expanding research field, perceived as one of the most promising algorithmic paradigms for near-term quantum computers. In this project, the candidate will leverage their skills in machine learning to carry out research in QML.

Sentiment Analysis for the Assessment of Financial Fitness (SAFF)

We apply Artificial Intelligence (AI) on Sentiment Analysis for the Assessment of Financial Fitness (SAFF), which can help an individual to understand one’s latent feeling and reservation towards money saving, spending and planning. The SAFF framework can be applied to not only financial institutions, but also other sectors, e.g. healthcare, rehabilitation and education. Sentiment analysis can alert current situations, as well as to monitor long term financial development.