Rail Transit Travel Time Distribution and Prediction Based on Automatic Fare Collection Data

DOI

10.2991/emcs-16.2016.30How to use a DOI?

Keywords

Rail transit; Travel time; AFC data; Pedestrian flow; Prediction methodology

Abstract

With the development of urban rail transit line networking, precisely obtaining the travel time distribution and analyzing its characters has become very important. This paper is based out of Automated Fare Card data to obtain the travel time distributions by analyzing the transaction records from Automated Fare Collection system. Beijing Metro is used as a case study. By choosing typical Origins to Destinations with different travel distances and transfer times, travel time distributions are generated and get fitted to the curves. A linear model is used to describe the travel time with different distance and transfer times. With consideration of the actual travel distance, transfer times, the time period and some other factors, a travel time prediction method is proposed. This proposed measure is used to predict the travel time from the time point when passengers swipe their smartcards at the entry gate to the time point when they reach the exit gate. The outcomes of this research are validated by the actual OD data from the Beijing Metro case.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Kun Ma
AU  - Jiaxing Wen
AU  - Qi Wang
PY  - 2016/01
DA  - 2016/01
TI  - Rail Transit Travel Time Distribution and Prediction Based on Automatic Fare Collection Data
BT  - Proceedings of the 2016 International Conference on Education, Management, Computer and Society
PB  - Atlantis Press
SP  - 120
EP  - 123
SN  - 2352-538X
UR  - https://doi.org/10.2991/emcs-16.2016.30
DO  - 10.2991/emcs-16.2016.30
ID  - Ma2016/01
ER  -