Investigating Relationships Between Roads Based on Speed Performance Index of Road on Weekdays

Abstract

Traffic congestion or traffic jam occurs as a ripple effect from a road congestion in the neighbouring area. Previous studies show that spatial correlation is exist between roads in neighbouring roads. There is similar traffic pattern observed between roads in a neighbouring area with respect to day and time. Nowadays, various machine learning model have been developed to predict traffic flow to provide traffic information. However, studies on relationships between road segments in a neighbouring area are still limited. It is important to investigate these relationships because they can assist drivers in avoiding roads which are impacted by road congestion or by a roadblock in a neighbouring area. Hence, this study investigates relationships of roads in a neighbouring area based on similarity of traffic condition. Traffic condition is influenced by number of vehicles and average speed of vehicles. In our study we determine traffic condition based on speed performance index of road in interval time. We used k-means clustering method to cluster condition of traffic flow on road segments. The experiments show that relationship roads can be revealed by clustering traffic condition in interval time.