Discover more stories about Mitacs — and the game-changing innovations driven by students and postdocs.
Researchers based in New Brunswick and Nova Scotia collaborate to analyze huge amounts of data produced by sensors that monitor critical infrastructures
In urgent situations like natural disasters — or even the current pandemic — Canadian first-response teams rely on mobile radio systems to communicate in a fast and secure way. Manufacturers globally also use radio systems in their production plants. Enabling radio communications requires a complex infrastructure with hundreds of thousands of radio repeater sites spread across North America and the globe.
A Mitacs-funded research team is working with the Nova Scotian company Rimot to develop a platform capable of using machine learning to identify what is happening with those sensors in a faster and more accurate way, to predict future issues, reduce outages, and improve reliability of the communications system.
“Land mobile radio systems generate large amounts of operational data and system alarms on a daily basis. Most of this vital data goes unused and requires sending a technician out to manually investigate every alarm,” explains Monica Wachowicz, data science professor and director of the People in Motion Laboratory at the University of New Brunswick (UNB). “This not only incurs the cost of additional trucks being dispatched, but also lost revenue during system downtime.”
Rimot has developed an advanced remote monitoring system that provides continuous data for real-time decision-making and remote asset management. That means that they can quickly identify a problem without the need of manual inspections. But analyzing the massive data volumes produced by Rimot’s sensors is a big task that now counts on the help of experts from UNB, Dalhousie University, and Acadia University.
Rimot’s product is enabled by Industrial Internet of Things (IIoT) systems, which connect sensors to cloud-hosted services. However, the large amounts of data being transmitted can congest networks and create performance challenges.
As a solution to potential infrastructure and connectivity hurdles, the research team proposed combining two technologies, cloud and edge computing. The former operates in a virtual, centralized data centre, while the latter brings computation closer to the source of the data.
“By eliminating the distance and time it takes to send data to centralized sources, we will experience improved speeds and performance of data transport, as well as devices and applications on the edge,” says Wachowicz.
She supervised Hung Cao, a Mitacs Accelerate intern and UNB postdoctoral fellow, in applying a conceptual framework that he developed during his PhD studies to address Rimot’s practical needs.
“The Mitacs project with Rimot had a perfect correlation with my IIoT research at UNB,” says Cao. “We were trying to develop an architecture and analyze the incoming data from the IIoT devices at any time and everywhere.”
The collaborative and multidisciplinary nature of this project makes it unique. While Wachowicz and Cao worked on the optimal mix of edge and cloud intelligence, researchers at Dalhousie are exploring security threats to IIoT systems, and Acadia’s team will soon work on a predictive model using external weather data.
“Our project is part of an emerging innovation ecosystem that is needed in the Atlantic region, where we can reach critical mass for harnessing collaborative efforts, meaningful impacts, and provide a unique environment for national and globally competitive businesses,” says Wachowicz.
She adds that the collaboration has initiated an exceptional experience for the Mitacs interns, as well as for her peers Jean-François Bousquet, Professor at Dalhousie’s Electrical and Computer Engineering Department, and Daniel Silver, Professor at Acadia’s Jodrey School of Computer Science and Director of the Acadia Institute for Data Analytics.
James Craig, Rimot’s Chief Technology Officer, explains that they wanted to bring all three institutions together as each has unique strengths. “It has been a pleasure working with all of them and we are now seeing the fruits of our labour pay off with research that is getting baked into our commercial offerings,” he says.
On the intern’s side, in addition to the benefits of collaborating with other universities, Cao highlights that a great professional gain was interacting with Rimot engineers to develop the working prototypes, as well as using real datasets provided by the company.
“As a data scientist, the most exciting was that I was provided a real dataset in a practical scenario, and could look for the value and insights hidden in the raw data with total freedom,” he says.
As next steps, Cao is working on scientific papers to share his research findings to date, while Rimot is working with the university partners to move to the next phase of the research. They are also assessing opportunities for unique intellectual property creation.
Mitacs’s programs receive funding from multiple partners across Canada. We thank the Government of Canada, the Government of Alberta, the Government of British Columbia, Research Manitoba, the Government of New Brunswick, the Government of Newfoundland and Labrador, the Government of Nova Scotia, the Government of Ontario, Innovation PEI, the Government of Quebec, Fonds de recherche du Québec – Nature et technologies, and the Government of Saskatchewan for supporting us to foster innovation and economic growth throughout the country.
Do you have a business challenge that could benefit from a research solution? If so, contact Mitacs today to discuss partnership opportunities: BD@mitacs.ca.