Using K-means algorithm for the road junction time period analysis

Abstract

Traffic congestion is one of the important issues in developed and developing countries. Due to the rapid development of information communication technology, the use of data mining technology in the intelligent traffic monitoring system has become the current trend of research and development. Use the information collected by the vehicle detector (VD) to analyze the causes of traffic congestion and find a suitable road junction time period classification. The k-means algorithm was used in cluster analysis to group the traffic flow and divide traffic time. According to the more precise analysis, the traffic congestion problem can be solved by the appropriate traffic signal lights cycle arrangements. The experimental result showed that the proposed mechanism can provide a suitable traffic flow classification and can indicate the difference of traffic pattern between weekday and weekend.