Researchers at the Alan Turing Institute have developed an AI tool that can analyze people’s behaviors in cities 400 times faster than current methods.
Lead researcher Prof. Mark Girolami said that the system combines machine learning and classical numerical models to allow large-scale behavior analysis at city, regional, and national level.
The research has been published by the Proceedings of the National Academy of Science. It has examples like how traffic congestion measures can affect retail behavior in London.
“Analyzing how groups of people behave and move around in a city using observed data, such as traffic cameras, is a big challenge. But AI gives us the ability to simulate urban environments and study the behavior and movement of people more easily,” Girolami said.
“Our research describes one of the first ways to solve this problem using artificial neural networks and we hope that this method offers a powerful tool to understand the behavior of people in cities.”
