Bus Schedule

This application presents an improved approach to predict the public bus arrival time based on location. After analyzing the components of bus arrival time systematically, the bus arrival time and dwell time at previous stops are chosen as the main input variables of the prediction model. At first, the algorithm of data interpolation and processing is designed to get the real-time of bus arrival as the input variables of the prediction models. Secondly, the statistical model is obtained based on the filtering the location, bus route and date of each bus respectively. Thirdly, a hybrid prediction model is proposed to predict the bus arrival time. The results show that the improved model outperforms the historical data based model in terms of prediction accuracy.