Laleh Samarbakhsh

Professor Samarbakhsh of Ryerson University and Genius Camp Inc. are collaborating to bring the latest in AI and ML into the finance of digital marketing, just as more industries are being forced into online settings.

The objective of this research is to introduce a predictive financial model to help Genius Camp and others SMEs in the education industry disrupted by COVID-19 allocate their digital marketing budget more efficiently.

The data-backed solutions from this model will equip them with tools to make more informed decisions about going virtual and their resulting digital marketing initiatives, such as how to structure their social media campaigns to achieve the highest ROI.

Full project description here.

Babak Babaee

Professor Aaron Smith of the University of Ottawa, working with the CHEO Research Institute, will develop software to generate synthetic electronic health records (EHR) that have similar statistical properties to real EHR while preserving patient privacy.

The ability to share patient data without compromising patient privacy will allow more researchers to search for medically and COVID relevant insights and broad-based sharing will allow researchers to check their ideas about fighting COVID with both greater speed and accuracy.

The final result of this project will be a software package that can generate synthetic electronic health records using minimal computational resources for moderately sized datasets.

Pawel Pralat

Professor Pralat of Ryerson University and Security Compass Technologies Ltd. are teaming up to create an agent-based framework for building virtual models of an urban area.

Their framework will be used as a virtual laboratory for testing various scenarios and their implications for the development of pandemics. In order for conclusions to be reliable, the models – known in the literature as synthetic population models or digital twins – will be at scale, with the number of agents comparable with the population of the city.

The project will allow for the evaluation of different COVID-19 mitigation policy designs. This includes decreasing proneness to wearing masks; closing down some non-essential, high-contact, social network nodes (for example, hairdressers); limiting the number of people having simultaneous social gatherings; or reducing the number of people on streets via promoting actions such as #stayathome.

Full project description here.

Altaz Valani

Professor Bolic of the University of Ottawa in collaboration with J&M Group are focusing on early detection of COVID-19 using thermal imaging cameras that allow for non-contact, non-invasive monitoring of temperature, heart rate and breathing rate.

They will develop potential solutions based on advanced signal processing algorithms and machine learning models. At the end of the project, they expect to provide a minimal viable product to J&M Group, that will include a thermal camera, processing hardware, software and algorithms.

This project addresses early detection of COVID-19 in a non-invasive way, something that is of utmost benefit to elderly patients and the detection of viral symptoms in crowded areas.

Full project description here.

Hossam Hassanein

Professor Hassanein of Queen’s University and Kings Distributed Systems will accelerate the development of project Looking Glass, a free and open platform to better inform public policy.

The proposed KDS-led COVID-19 project will support the Looking Glass project, a free and open platform to better inform remediation strategies, public health interventions, and vaccine campaign strategies against COVID-19 – as well as time strategies to relax lockdown measures during the recovery phase – for municipalities, state/federal authorities by modelling transmission patterns of diseases based on reports from epidemiologists fused with economic report data, and high-resolution mobility data.

This project hopes to provide not only a powerful tool to forecast COVID-19 infection rates from actions such as re-opening schools but also to inform other critical public health issues like vaccination campaigns.

Full project description here.

Douglas Stewart
Mark Buchner

Professor Mark Buchner at Seneca is collaborating with OctoChain to develop tools, solutions and frameworks using blockchain technology to optimize personal support worker mobilization.

The TriNetra group and their Blockchain-focused company OctoChain are closely collaborating with ConnexHealth and Seneca researchers to extend the features of their blockchain-based platform to include machine learning/artificial intelligence (ML/AI) capabilities. The newly developed system will match candidates to job assignments based on their entire profile, including certifications, training, geography, work history, and availability. This technology will be instrumental in establishing a layer of trust and transparency in the professional healthcare industry.

Responding to the vastly changed Personal Support Worker market and constraints caused by the COVID-19 pandemic, this project will empower, efficiently mobilize and sustainably deploy individual PSWs.

Full project description here.

Neeraj Vashist, Manish Dixit, Garvin Franco
Rasha Kashef

Professors Dafna Sussman & Rasha Kashef of Ryerson University are teaming up with Mount Sinai Hospital to tackle the very difficult problem of achieving successful early intervention for pregnant women diagnosed with COVID-19.

The project aims to support medical professionals who are directly treating COVID-19 pregnancies. A comprehensive, anonymized data repository will be deployed in conjunction with dedicated prediction algorithms to score patients for their risk of severe deterioration. The repository together with the algorithm are expected to radically transform Canadian and, potentially, international healthcare providers’ ability to identify, manage and treat cases of COVID-19 in pregnant patients.

Full project description here.

Dafna Sussman
Matthieu Schapira

Emerging Canadian biotech company Cyclica will partner with Matthieu Schapira of the University of Toronto to design a new line of pan-coronavirus inhibitors.

This collaboration will discover new druggable, well-conserved sites on coronavirus protein surfaces and perform an AI-based virtual screen in search of chemical inhibitors, using Cyclica’s MatchMaker™ engine. The SOSCIP GPU-accelerated platform will be used to broaden Match Maker’s domain of applicability to non-human species by augmenting training with protein-ligand binding data from multiple species and re-optimizing neural networks. This collaboration will lead to new viral targeting strategies and a new platform to address emerging threats.

Full project description here.

Stephen Scott MacKinnon
Lise Bjerre

This collaboration between Associate Professor Lise Bjerre of the University of Ottawa and Larus Technologies proposes a novel, proactive approach known as predictive case identification to address the problem of early detection of asymptomatic/pre-symptomatic carriers of COVID-19.

By using a wide spectrum approach to data analysis at the individual-level, including AI/ML approaches for prediction, simulation and optimization, the team is aiming to create, simulate and evaluate a ‘smart isolation and testing strategy’ that would inform policy decision-making and allow partial reopening of economic and social life while minimizing the risk of a ‘second wave’ and further lockdowns. Harnessing data towards identifying people at-risk of contracting COVID-19 before they can spread the virus by predicting who is most likely to be infected is key to immediate isolation and targeted testing of presymptomatic and/or asymptomatic carriers. This could mean the difference between a prolonged lockdown, a second-wave — or the re-opening of ‘normal’ life.

Full project description here.

Rami Abielmona
Akramul Azim

Professor Azim of Ontario Tech University, in collaboration with Cyberworks Robotics, are working to develop intelligent robots to take humans' place in sanitizing hospitals and long-term care facilities.

This project aims to improve Cyberworks Robotics navigation technology on existing:

  • Floor disinfection machines (e.g. wet floor scrubbers)
  • High-intensity UV disinfection machines
  • Chemical mist disinfection machines

Using intelligent machines to sanitize would allow hospitals and LTC facilities to disinfect surfaces more safely and on a more frequent basis than with human cleaners, while simultaneously increasing the quality of cleaning by ensuring that some surfaces are not overlooked due to human error and neglect.

Full project description here.

Vivek Burhanpurkar
Ebrahim Ghafar-Zadeh

Professor Ghafar-Zadeh of York University and CMC Microsystems are researching the possibility of identifying COVID-19 in asymptomatic individuals using a ‘simple’ saliva test.

By employing the latest in Data Science and AI research on SOSCIP’s advanced computing platforms, the team hopes to develop a non-invasive, easy-to-use test that can be taken at home by anyone. Using advanced analytics on saliva samples in healthy and COVID-19-affected people, this project could have major impacts on national and international efforts to identify the spread of COVID-19 as and before it happens.

Full project description here.

Andrew Fung
Yongi Mao

This forward-thinking collaboration between the University of Ottawa’s Prof. Yongyi Mao and Advanced Symbolics Inc. aims to use AI to generate predictive models for forecasting and projecting the spread of COVID-19 cases across Canada.

By analyzing anonymized, user-generated data, the researchers expect to be able to determine accurate and timely models of viral spread across the country. Realistically capable of tracking the spread of any infectious disease, this project sets out an ambitious agenda to integrate a wide spectrum of data sources and data modalities as well as a diverse set of modern AI technologies, to fundamentally change the way we track, trace, and cope with epidemics and pandemics.

Full project description here.

Kenton White
Afshin Rahimi

Professor Afshin Rahimi and IFIVEO Canada Inc are collaborating to develop remote production monitoring in post-COVID manufacturing environments.

This project proposes an approach to use real-time computer vision and deep learning methods to verify social distancing requirements are maintained, while also ensuring that production operations remain optimized for non-essential personnel working remotely. The team expects to leverage their results into an ideal solution for Canadian manufacturers that are re-starting production in a COVID-19 world by ensuring that worker safety is maintained without sacrificing production throughput and quality.

Full project description here.

Khizer Hayat
Xu (Sunny) Wang

This research project featuring a collaboration between Wilfrid Laurier’s Professor Xu Wang and Lovell Corporation will develop a self-adaptive recommendation engine to match skilled workers with proper voluntary actions in direct response to the increased community need created by the COVID-19 pandemic.

Additionally, this project will develop a voluntary measurement index to quantify the impact of voluntary actions against Canadian economic goals and targets after the COVID-19 pandemic to monitor and evaluate the reopening of the economy in Canada  The proposed research also provides opportunities to capture quality data to perform needs and gaps analysis for stakeholders to monitor progress, reassign volunteer and focus resources, and to equip Canadian businesses and governments to achieve operational efficiency gains and enhance resource mobilization.

Kelly Lovell
Steven Wang

Building on the success of Studio 1 Labs’ Intelligent Bed Sheet, York University’s Professor Steven Wang and the team at Studio 1 Labs are looking to create an automated online monitoring system for abnormal respiratory patterns.

Accompanied by an AI-based severity index that scores breathing patterns to determine those at risk for faster health deterioration, they will provide a non-invasive solution to patient monitoring that also keeps a physical distance between patients and healthcare staff, in order to reduce the potential for transmission of the virus. Patients will simply only need to lay down on the Intelligent Bed Sheet for it to capture subtle symptoms that are not obvious to the naked eye, and can even be unknown to the patient themselves, radically changing the way that illness detection and monitoring can take place, at home and in medical settings.

Full project description here.

Ed Shim