A Bus-Arrival Time Prediction Model Based on Historical Traffic Patterns

Abstract

The emphasis of this research effort was on using historical GPS data to develop a dynamic model to forecast long-term path travel times between bus stops of origin and destination. This study was brought about by the shortcomings of the existing real-time short-term prediction system, which have been developed and utilised in Beijing. The developed model is based on cluster analysis and polynomial fitting for the prediction of running times between bus stations. The research also intends to test the proposed model using real-world data. In a test with real-world bus data in Beijing, China, the proposed model performed effectively in terms of both prediction accuracy and computing time.