The new system learned past average speed in certain traffic locations along with congested areas on nearby roads, and traffic conditions during rush hour. (image: Korea Bizwire)
SEOUL, Jul. 10 (Korea Bizwire) — A research team led by Prof. Ko Sung-ahn at Ulsan National Institute of Science and Technology, jointly with Purdue University and Arizona State University, has developed an artificial intelligence (AI) system that predicts traffic conditions in the next 5 to 15 minutes.
Using this system will allow navigation programs to notify the driver how current traffic conditions may change in the next 5 minutes.
Unlike previous traffic prediction systems that rely on probability and statistics to analyze past traffic records for prediction, the new system comes with higher accuracy by adding a deep learning algorithm that considers real-time traffic situations.
The new system learned past average speed in certain traffic locations along with congested areas on nearby roads, and traffic conditions during rush hour.
The new system’s margin of error was less than an average of 4 kilometers per hour.
Traffic situations predicted by the AI system are visualized for easy understanding. Congestion levels and average driving speed, for instance, are described using colors and shapes.
“We will share the visualized data on the Urban Traffic Information Center (UTIC) website to allow drivers to easily understand the current traffic situation,” said Ko.
“The new system can also be used at traffic broadcasting services or navigation programs to find the best route during bad traffic situations.”
The study on the new system was published in the June 12th edition of IEE Transactions on Visualization and Computer Graphics.
(Yonhap)
