Today in AI: University of Waterloo researchers build ‘algae AI’, Layer 6 wins RecSys Challenge

Canadian tech continues to make strides as an AI leader. Here’s the latest on Canada’s AI movers and shakers.

University of Waterloo researchers develop AI software to protect water supplies from toxins

Researchers at the University of Waterloo have developed AI technology to help guard water supplies from toxins and bacteria.

The researchers are using an AI software that can identify and quantify different types of bacteria and blue-green algae in water as these toxins pose a threat to shut down water systems. The AI software also leverages a microscope to automatically analyze water samples for algae cells in one to two hours, followed by a confirmation of results by a human analyst.

“We need to protect our water supplies,” said Monica Emelko, a professor of civil and environmental engineering and member of the Water Institute at the University of Waterloo. “This tool will arm us with a sentinel system, a more rapid indication when they are threatened. The exciting piece is that we’ve shown testing utilizing AI can be done quickly and well. Now it’s time to work through all the possible scenarios and optimize the technology.”

The research team is hoping to use AI to make water testing more efficient, as it currently takes up to two days to test water samples through a process of sending them to labs for manual analysis by technicians. The researchers said it may take up to three years to develop a commercial sample testing system for use in labs or treatment plants.

“This brings our research into a high-impact area,” said Alexander Wong, a systems design engineering professor at the University of Waterloo. “Helping to ensure safe water through widespread deployment of this technology would be one of the great ways to really make AI count.”

Layer 6 wins RecSys challenge

TD Bank Group announced that Layer 6, which works with enterprises, media, and ecommerce, has won the 2018 RecSys challenge. Layer 6 was acquired by TD Bank Group in January.

The RecSys challenge focused on developing tech that enables personalized music recommendations and automatic playlist continuation. The challenge consisted of two separate competitions requiring participants to use AI to improve personalization and make it easier to create playlists. Participants were also asked to use AI to extend listening beyond existing playlists by adding songs that are relevant and unique to each person’s taste.

For one competition, participants were restricted to use a music dataset provided by Spotify, while the other competition allowed participants to use external data to develop personalized music and playlist recommendations. Layer 6 won both competitions by leveraging its prediction engine, which combs through internal data sources to anticipate the needs of customers in real-time.

“Participating in competitions such as the RecSys Challenge allows us to benchmark our AI capabilities against the world’s best and contribute back to the global AI community,” said Tomi Poutanen, TD’s chief AI officer and co-founder of Layer 6. “AI is powering personalization across a wide range of industries, from music to banking to health care. TD continues to encourage us to push forward and both innovate and incubate new ideas. As we think about new products that will reimagine the customer experience, these types of competitions help us to hone our skills and talents and think differently about the work.”

Photo via Unsplash

Amira Zubairi

Amira Zubairi

Amira Zubairi is a staff writer at BetaKit. As a fourth-year journalism student who has written primarily about entrepreneurship, Amira has developed a growing interest in Canadian startup, business, and tech news. In her free time, Amira enjoys reading, baking and watching legal shows.