Bayesian Network Modeling Analyzes Of Perceived Urban Rail Transfer Time

This study proposes a Bayesian network (BN)-based approach to research the relationships between metro transfer perception time (MTPT) in different seasons and its influencing factors, and explores the strategies on reducing the MTPT for the improvement of the transfer experiences of passengers. Taking the city of China, Beijing, as the study area, the data related to the MTPT are collected in different seasons. Based on study data, BN modeling results indicate that factors affecting the MTPT in four seasons are not the same. The results of scenario analysis of BN demonstrate that the improvement of the transfer environment is effective for passengers in spring and autumn, while the passengers in summer pay more attention to the time and the space comfort of the walking stage of transfer. In addition, passengers in winter are concerned about the time and the space comfort of both walking and waiting stages of transfer.