Proceedings of the 2nd International Conference on Soft Computing in Information Communication Technology

Use of Back Propagation Artificial Neural Network to Predict Passenger Volume of Beijing Subway

Authors
Xiaoqing Zhang, Zhili Liu, Lan Li
Corresponding Author
Xiaoqing Zhang
Available Online May 2014.
DOI
https://doi.org/10.2991/scict-14.2014.10How to use a DOI?
Keywords
passenger volume prediction of Beijing subway; SPSS; B-P artificial neural network
Abstract
This paper analyze different aspects of factors that affecting passenger volume of Beijing subway, then select fifteen key factors from four aspects: internal structure of the urban rail transit system, urban demographic features, economic development and urban transport structure. Firstly, SPSS software is used to examine the multicollinearity among all the variables and then we remove three factors that are of strong multicollinearity with others. Finally, B-P artificial neural network model is established based on the remainder of factors to predict passenger volume of Beijing subway for the next few years. The results show that the average relative error of the past twenty year is 5.56%.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Cite this article

TY  - CONF
AU  - Xiaoqing Zhang
AU  - Zhili Liu
AU  - Lan Li
PY  - 2014/05
DA  - 2014/05
TI  - Use of Back Propagation Artificial Neural Network to Predict Passenger Volume of Beijing Subway
BT  - Proceedings of the 2nd International Conference on Soft Computing in Information Communication Technology
PB  - Atlantis Press
SP  - 39
EP  - 43
SN  - 1951-6851
UR  - https://doi.org/10.2991/scict-14.2014.10
DO  - https://doi.org/10.2991/scict-14.2014.10
ID  - Zhang2014/05
ER  -