Optimizing Pretrained Clinical Embeddings for Automatic COVID-related ICD Coding

We are building a machine learning algorithm to be able to better understand the unstructured clinical notes that doctors write about patients. This will help hospitals and healthcare systems standardize and extract insights from these notes to make them more useful for determining how sick COVID patients are and how they are improving over time.

Climate Finance and Youth Unemployment for COVID19 Recovery

The COVID19 crisis has had an immense impact in loss of employment across nations and sectors. Youth are one of the most impacted demographic groups as job security has become more precarious. With a main objective of addressing youth unemployment in recovery packages while remaining committed to climate progress, this project proposes a quantitative and qualitative research methodology to analyze the policy recommendations and financial figures found in economic recovery packages and policies.

COVID-19: Indoor light-activated, self-cleaning surfaces for continuous decontamination of air in HVAC systems

The risk of airborne disease transmission is high for essential workers even while wearing PPE. Since SARS-CoV-2 can remain airborne after a sneeze or cough for several hours, ideally, there would be effective methods to remove these infectious particles directly from the air. In this work, we develop a membrane-based technology capable of serving the two-in-one function of dehumidification and decontamination of the indoor air, which can be coupled to room A/C systems.

Localization, Monitoring, and Motion Coordination of Autonomous Indoor Service Robots

The proposed project will tackle the following inter-related research topics regarding localization, monitoring, and motion coordination of autonomous indoor service robots: (1) adaptive coverage-planning of arbitrary and uncertain non-convex indoor regions, (2) accurate and robust indoor localization of service robots using vision-based technologies, (3) deep learning based depth estimation and high-precision path-tracking control of service robots, (4) intelligent detection of certain robot system and environmental states.

Modeling Aerosol Dispersion in Dental Offices

The Ontario Dental Association requires the time of three hours between two clients in a dental office to prevent the transmission of COVID-19; however, this strict guideline poses a great challenge to the economics of dental business and the recovery of Ontario economy. The results of this study will help understand the COVID-19 transmission in dental offices and help develop technologies for the proper control of aerosols and splatters generated during the dental procedures.

Optimizing the productivity of the whooping cough, diphtheria, and tetanus vaccines’ manufacturing processes: software and hardware-based solutions

The current key challenges in manufacturing of pharmaceuticals in general and vaccines in particular is the lack of rapid measurements for monitoring the processes in real time, lack of understanding of the correlation between operating conditions to the productivity of antigens composing the vaccines and contaminations that affect the purification processes.

Development of numerical algorithms to customize acoustic treatment

Dymedso, a Canadian-based medical device SME specialized in pulmonary disease therapeutic and treatment equipment is a patented pioneer in using sound (acoustics) to treat patients requiring airway clearance such as Cystic Fibrosis COPD and the coronavirus family, SARS, MERS and naturally the COVID-19.

Low-speed computational aerodynamics and stability analysis of fuselage modifications in support of autonomous aircraft

As drones continue to gain traction as a tool for cargo delivery, engineers and regulators must seek new ways to mitigate the risk of developing ever larger aircraft. This project will conduct aerodynamic simulations and performance analysis of a pre-certified recreational aircraft that has been hypothetically retrofitted to operate as a cargo drone. Using Computational Fluid Dynamics and programming tools, this project will yield a novel and optimized cargo bay expansion aboard a Quad City Challenger II airplane in support of future operational trials with Transport Canada.

SARS-CoV-2 Genomics for COVID-19 wastewater tracking

This project aims to develop SARS-CoV-2 genomics tools to apply to the tracking of COVID-19 in municipal wastewater. Detection of SARS-CoV-2 genetic material in wastewater has been used to estimate prevalence of the virus in the corresponding community. This has the potential to be a relatively inexpensive early warning system that is complementary to testing in the clinic. However, genome sequencing to differentiate between lineages or genetic variants, which could be used to track origin of outbreaks, has not yet been applied to wastewater.

Deep learning-driven strategies for COVID-19 Detection and Risk Stratification

A critical step in the fight against COVID-19 is effective screening of infected patients for infection detection and risk assessment. While viral testing such as rt-PCR is the gold standard for infection detection as it is highly specific, it is moderately sensitive and is a very time-consuming, laborious, and complicated manual process that is in short supply. While faster viral testing methods are becoming available, they remain in short supply and do not provide important information on severity and extent.