A professor at Hongik University in South Korea, and his students have used artificial intelligence (AI) and machine learning (ML) algorithms to develop a model that can predict the probability of fires occurring using information held by Seoul’s city fire department.
According to Microsoft, the class led by Professor Jae Seung Lee used Azure Machine Learning Studio to run different ML modules until they were able to predict fires with a 90% accuracy rate.
The information they extracted from the datasets identified parts of the city with a high probability of fire — knowledge that has empowered firefighters to optimise their patrol routes and deployments.
Having more fire crews on duty in more “flammable” neighbourhoods means they can respond to calls faster and so secure the safety of people and minimise property damage.
“I used to think older districts, like Gangbuk, were more prone to fires. But the model revealed otherwise,” Lee said. “Newer districts, like Gangnam, are actually more susceptible to fire incidents, as there are more shops and people around the neighbourhood. Illegal parking also plays a role.”
The Fire Department had “a lot of data” about the causes of fires, their locations, as well as the casualty numbers, but they wanted to make sure the data would be shared in a way that protected citizens’ privacy.
To do that, Professor Lee suggested building a Microsoft virtual machine (VM), which kept data secure and restricted to only selected individuals.
Professor Lee now wants to apply the team’s predictive model to other city problems, such as crime and traffic.