Australia Hopes Artificial Intelligence Can Curb Harassment of Women – VOA Asia

Australia Hopes Artificial Intelligence Can Curb Harassment of Women – VOA Asia

SYDNEY, AUSTRALA – Artificial intelligence that automatically detects threatening behavior at train stations is part of a new trial to improve safety for women traveling at night in Australia.

The New South Wales state government says nine out of 10 Australian women have experienced harassment on the street. It asked researchers to submit ideas to improve safety as part of its Safety After Dark Innovation Challenge. Four entries have been chosen and will be tested over the next six months.

One group from the University of Wollongong will develop artificial intelligence (A.I.) software that will examine real-time feeds from security cameras and alert an operator when it detects suspicious activity or an unsafe environment.

The A.I. will be trained to detect people fighting, agitated behavior, individuals being followed, and arguments. The university team says the software is a world-first, and that they were “pushing the limits of the technology.”

Researcher Elizabeth Muscat, who is a transport planner, is also developing algorithms that create safe routes for female travelers.

“It will give women the opportunity to make better informed choices on the routes they choose,” Muscat said. “So, maybe they would choose to take a route that offers them a higher level of passive surveillance or, meaning that a lot more people will be around, or businesses will be open, lighting is improved in that location. The end product could be a mobile application where women can on their own mobile phones have an application similar to Google Maps or another route-finding app where they could be able to choose which route they want to take home.”

Authorities in New South Wales, Australia’s most populous state, said the range of technology was “exciting.”

Research in 2018 showed that 20% of women in Sydney felt unsafe on public transport.

Source

Leave a Reply

%d bloggers like this: