Short-term passenger volume forecast and model analysis of Beijing public transport

ABSTRACT

The prediction of bus passenger volume is the fundamental research content of bus transfer optimization. In order to get more accurate passenger volume data and improve the utilization efficiency of urban traffic resources, according to randomness, time-varying and uncertainty of public transport passenger volume in Beijing, combined with the current new coronavirus pneumonia epidemic, this paper collected the relevant data of Beijing in the past 40 years, and predicted and analyzed them from four dimensions of public transport, urban scale and residents' economic level, taxi and sudden health events by BP neural network and regression analysis. The results show that BP neural network has good prediction results, and BP neural network is suitable for large sample size, which needs to fit or predict complex nonlinear relationships. © 2021 SPIE