Research on the Route Choice Behavior of Subway Passengers Based on AFC Data

摘要

This paper studies the route choice behavior of passengers from auto fare collection and timetable data using a method combined with Bayesian and Metropolis-Hasting sampling. First, influential factors of route choice such as in-vehicle travel time, transfer time, and in-vehicle crowding are selected. Then, formulations of these factors are established for a single passenger, which are merged into a logit model to model route choice behavior of subway passengers. Next, an algorithm that integrates Bayesian inference and Metropolis-Hasting sampling is designed to calibrate the parameters of the logit model. Finally, a case study of Beijing subway is applied to verify the validity of the developed model and algorithm.