Bus arrival time prediction based on Random Forest

DOI

10.2991/fmsmt-17.2017.167How to use a DOI?

Keywords

intelligent transportation system, bus arrival time prediction, random forest.

Abstract

In order to balance the traffic supply to meet the citizens demand for public transportation, reduce the pressure of urban traffic, enhance the competitiveness of public travel and improve the intelligent transportation system service, this paper proposes a bus arrival time prediction algorithm based on Random Forest. In this paper, traveling data of the 607 bus in Beijing is analyzed, the data are pretreated by using Space Rectangular Coordinate System instead of the traditional GPS Geodetic Coordinate System. The traffic junction number, travel distance, date type, time period, precipitation, visibility Six kinds of influencing factors were utilized to model the bus arrival time prediction model using Random Forest. The experimental results demonstrate that the mean absolute percentage error of the algorithm is 20.43% when under the condition of setting 800 decision trees.

Copyright

© 2017, 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  - Jian Li
PY  - 2017/04
DA  - 2017/04
TI  - Bus arrival time prediction based on Random Forest
BT  - Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)
PB  - Atlantis Press
SP  - 867
EP  - 872
SN  - 2352-5401
UR  - https://doi.org/10.2991/fmsmt-17.2017.167
DO  - 10.2991/fmsmt-17.2017.167
ID  - Li2017/04
ER  -