SEOUL – Does a young woman dressed in summer just admire the view from the bridge? This is a question that South Korean researchers and the emergency services are working to answer using artificial intelligence to detect and prevent suicide attempts.
In this case, it’s one of the researchers, and human observation teams are showing how hard it is to tell.
But their evolving AI system is exploring ways to behave by analyzing the dispatch data of cameras, sensors and rescue services from April 2020, the Seoul Institute of Technology said Wednesday.
Based on several hours of video surveillance data and evaluation of details such as human hesitation, artificial intelligence can predict a dangerous situation and alert rescue teams immediately, said lead researcher Kim Jun Chul.
“We believe the new video surveillance will allow our crews to identify these cases more quickly and help us make quicker calls,” Kim Hyun Gil, who is in charge of the Yeouido Water Rescue Brigade, told Acesparks while observing the truth – from bridges across Seoul’s Han River. time images taken.
Kim’s team, along with researchers, his crew and Seoul’s fire and disaster headquarters, are developing the technology, which will be tested in October.
Their work cannot be reached quickly.
In 2019, South Korea, with a population of 52 million, recorded the highest suicide rate in the OECD. According to government figures, more than 13,700 people lost their lives that year.
Every year, about 500 suicide attempts are recorded on 27 bridges along the Khan River, which is about 500 km long.
The number of rescue shipments increased by about 30 percent in 2020 compared to the previous year, and many attempts were made by people in their 20s and 30s as the coronavirus pandemic caused great economic hardship and intensified the struggle for jobs, the rescue brigade said. he said.
“The system studies the frames on its own, which can lead to improved results by significantly reducing false alarms,” the lead researcher said.
.