Identifying Traffic Congestion Pattern using K-means Clustering Technique

Abstract

With increase in urbanization and socio-economical growth, the number of vehicles in major metropolitan cities is increasing day by day. Therefore, traffic congestion is becoming a major concern of metropolitan cities all over the world. This results in tremendous air pollution, loss of valuable time and money of citizens. Hence, traffic congestion monitoring of different road segments is very essential for analyzing the problem associated with smooth mobility. Identifying the problematic road segments within the city is one of the important job for the transport authority to assess the road condition. That will assist the government agencies or policy makers to optimize traffic rules and regulations. This work identifies traffic congestion pattern which can classify the different road segments based on traffic density and average speed of vehicles. The traffic parameters are captured by in-road stationary sensors deployed in road segments. The proposed system uses k-means clustering algorithm to categorize the different road segments.