Short-term traffic prediction using fuzzy c-means and cellular automata in a wide-area road network

In this paper, we propose a short-term prediction method for forecasting traffic in a time-series manner for up to one hour ahead for all roads in a wide-area road network. The results of our research enable traffic to be simulated for a wide-area road network based on actual traffic data by combining fuzzy clustering and cellular automata. On application to an actual road network with 3,405 links, the proposed technique was found to be superior to the nearest neighborhood method for traffic prediction at times of congestion outbreak and alleviation and heavy congestion.