Based on the arrival time of buses in advance, passengers can arrange their travel routes better, for example, to choose the more suitable positionor time to transfer. Thus they may prefer to take advantage of the publictransportation system rather than other transport modes, for example, a taxi and private car. Global Position Systems (GPS) have been implemented in various public transit systems to obtain various types of real-time information such as vehicle locations, instant speed and journey times. So many researches have studied on transit arrival time prediction algorithm using real-time GPS data. The objectives of this paper are to develop and apply some models to predict bus arrival time using GPS data. In this study three prediction algorithms are designed and tested by the historical GPS data from Bus No.1 in Beijing. The test result shows that Neural Network isappropriate in dealing with this problem. For the covering abstract see E134653.
Abstract