Library Fission: Improving APIs by observing real-world API usage

Modern software development heavily relies on external libraries. The proposed collaboration will create techniques and publicly-available tools useful to both users of external libraries and maintainers of these libraries. Our hypothesis is that different clients use different subsets of libraries’ API surfaces, and that it is possible to use clustering algorithms to automatically split libraries […]

Read More
Understanding cybersecurity data and analysis models with intelligent visualization

Cybersecurity incidents such as data breaches have become more critical and costly than ever, as we are generating, processing, and relying on more digital information every day. To quickly identify potential security attacks and prevent them in a sea of system activities, machine learning (ML) has been applied to support security analysts’ decisions. However, the […]

Read More
Optimization of Conductive Ink Formulations for Inkjet Printing of Circuits

The newly emerging field of printable electronics is expected to facilitate widespread low-cost electronic devices for applications such as flexible displays, identification labels, wearable electronics and rapid prototyping. This field incorporates a variety of printing technologies with conductive ink to deposit conductive traces on any material. However, companies like Voltera, who are creating new technologies […]

Read More
Predicting readmission and recovery rates of psychiatry patients in mental health facilities within Canada: A machine learning approach

Hospital readmission from in-patient psychiatry is increasingly problematic for patients and care administrators, as they often are associated with poor clinical outcomes and higher care costs. An understanding of factors that predispose in-patient psychiatry patients to hospital readmission would be critical in improving patient care and reducing healthcare-related costs. My research proposes to use machine […]

Read More
Building Spatio-temporal Transformers for Egocentric 3D Pose Estimation

Using a fisheye head-mounted camera to estimate human pose in 3D has become increasingly popular in recent years due to its ability to capture activities in unconstrained environments. Egocentric 3D human pose estimation (HPE) has a number of challenges due to self-occlusions and strong distortions. Intermediate heatmap-based representations have been found to be effective in […]

Read More
Automated Video Content Chaptering via Machine Learning

The research will focus on building a deep learning model to analyze video and audio streams of input video material, essentially creating something like a table of contents, for example: * Minutes 0-3: Introduction. Our topic is binomial coefficients. * Minutes 3-4: Problem source. * Minutes 4-6: Details of the mathematics. Calculations of values. * […]

Read More
Analyzing the potential of hydrogen fuel cell electric vehicles as distributed energy storage or generators to decarbonize transportation and power sectors

Decarbonizing the transportation sector and scaling up energy storage are critical for the transition to a net-zero economy. This project will study the potential of connecting fuel cell electric vehicles (FCEVs) to the electrical grid as distributed energy storage and/or electricity generators to supply electricity to the grid when needed. This FCEVs-to-grid pathway can maximize […]

Read More
Couling Inventory Validation

Cultural Planning encourages recognition of a community’s network of interrelated assets, and maintains that it is beneficial to conserve built cultural heritage resources. Many municipalities, including the City of Guelph, have undertaken cultural mapping initiatives, which are considered an initial step and a defining feature of this vein of planning. Guelph’s mapping initiative identifies the […]

Read More