Learning the route choice behavior of subway passengers from AFC data. (1st April 2018)

• Record Type: Journal Article
• Authors: Xu, Xinyue; Xie, Liping; Li, Haiying; Qin, Lingqiao
• Is Part Of: Expert systems with applications. Volume 95(2018)
• Page Start: 324
• Page End: 332
• Publication Date: 2018-04-01
• Subjects: Subway -- Big data -- Route choice behavior -- Bayesian -- Crowding -- AFC; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2017.11.043
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Route choice behavior is learned from Auto Fare Collection, timetable and train loading data. The influence of in-vehicle crowding on route choice behavior is explicitly considered. Parameters of the route choice model are calibrated using the Bayesian and Metropolis-Hasting sampling method. The proposed data mining method outperforms three competing methods in terms of accuracy. Abstract: This paper learns the route choice behavior of passengers from Auto Fare Collection, timetable, and train loading data using a method combined with Bayesian inference and Metropolis-Hasting sampling. First, the influential factors of route choice such as in-vehicle travel time, transfer time, and in-vehicle crowding are given. Next, formulations are established based on AFC, timetable and train loading data, which are merged into a logit model of route choice behavior of subway passengers. Next, an algorithm integrating Bayesian inference and Metropolis-Hasting sampling is designed to calibrate parameters of the logit model. Finally, a case study of Beijing subway is applied to verify the validity of the model and algorithm. A detailed discussion shows that in-vehicle crowding plays a crucial role in passenger route choice behavior.