“We wanted to understand what people’s reactions to a bot might be in different types of workplace situations,” says Julia. “Will people trust the system the same way they trust a person? What kinds of challenges or barriers might arise when implementing chatbots as a tool in the workplace?”
The new tool uses a deep-learning computer vision system and motion-classification algorithms to capture events such as falls in real time, alert caregivers and give health-care professionals the information they need for immediate triage.
The system—developed in part by the Multimedia Research Centre led by Irene Cheng in the Department of Computing Science—transfers real-time video to an autonomous computer vision lockbox. If an event is detected, the system alerts a specified caregiver and provides a redacted video of the event.
Now, one Mitacs intern is searching for a solution. Arvind Srinivasan is researching an algorithm that will integrate real-time changes into existing mapping programs. The new algorithm allows the app to seamlessly adjust your route — without interrupting the navigation. Normally, unexpected changes to the map require more processing power to integrate. The resulting algorithm is slower and less useful as a navigation tool.
The app will use audio stories, such as podcasts, to enable users to communicate and feel as if they are doing the same activity at the same time, even though the activity might be taking place at different times in different places. For example, a mother and daughter living in different cities can hike together, with the mother initiating the story during her earlier hike and the daughter able to listen to her mother’s account while she herself goes for a hike.
This summer, Nathalia Soares Covre, a Mitacs intern from Brazil, is helping the modelEAU team develop a digital model of an innovative wastewater treatment process. This new process reduces the discharge of nitrogen into lakes and rivers so that plant operators can work to reduce the impact of urban wastewater on local ecosystems.
Wendlasida Ouedraogo is part of a research team at École Polytechnique de Montréal that is developing the next generation of computer vision software, which automates visual tasks, to help civil engineers and city planners get ahead of construction demand.
Kobo’s Big Data Director Darius Braziunas says he knew early on that to stay competitive in the e-book world Kobo would need to collaborate with university researchers to take their products to the next level.
Sana Maqsood, a PhD student at Carleton University, wants to educate young internet users on how to stay safe in the online world. Through Mitacs’ internship program, Sana is working with MediaSmarts — a local not-for-profit organization that promotes digital literacy among youth — to create a video game that helps players combat the risks found in cyberspace.
While most smartphones are adept at capturing close-range speech, noisy environments like rock concerts pose a different challenge. Screaming crowds drown out the music, leading to poor playback quality on the phone.
LG turned to ESS to develop audio-amplifying microchips that can distinguish between the melody and “malarkey” in a concert venue.
The MScAC degree is a unique two-year program that pairs graduate students with information technology companies for internships, following eight months of advanced courses in computer science. Caroline jumped at the opportunity to apply her skills in a business environment through a Mitacs Accelerate internship, a research grant awarded for students in the program.