Passenger boarding choice prediction at a bus hub with real-time information

Abstract

Providing real-time bus information (e.g. current situation of an arriving bus) to passengers is becoming increasingly possible with the development of transportation information technology, such as intelligent transport systems. When multiple routes can reach a given destination, real-time information could be an important reference for passengers' decision-making regarding which bus to board. This paper presents a method for predicting passengers' boarding choice behaviours on common bus lines at a bus hub with real-time information. To account for the uncertainty in the decision-making process, cloud model theory, which is based on fuzzy sets, was adopted. Data from a bus hub in Dalian city of China are also presented to illustrate the applicability and effectiveness of the proposed method. The results show that providing real-time information could lead to a deviation from passengers' typical choices that are made without real-time information. The proposed model effectively predicts passenger's boarding choices and could be used to improve bus-dispatching models in the future.

Keywords:

• passenger boarding choice
• common bus routes
• real-time bus information
• cloud model

Funding

This work was supported by National Natural Science Foundation of China [51108053], the Trans-Century Training Program Foundation for Talents from the Ministry of Education of China [NCET-12-0752] and Liaoning Excellent Talents in University [LJQ2012045].