Recognition Method of Urban Residents' Travel Mode based on GPS Data

DOI

10.2991/icmeit-19.2019.18How to use a DOI?

Keywords

GPS; travel mode; mode recognition; trip recognition.

Abstract

The rising of big data and the Internet has brought about tremendous changes in travel. The rapid development of computer technology, network technology, wireless communication technology, portable devices, and location-based services provides an opportunity for the application of GPS technology to travel behavior survey. GPS technology has become a new technology to study urban residents' travel behavior and to identify urban residents' travel modes. This paper delivery a travel mode recognition method for urban residents' GPS travel data. Through the process of GPS data preprocessing, trajectory recognition and feature extraction, the recognition algorithm is designed to identify seven urban common travel modes, which are walking, bicycle, car, bus, taxi, subway and urban rail. In this paper, a trajectory recognition algorithm based on transition points is used to segment the trajectory of a single travel mode by identifying the transition points and pedestrian sections. The accuracy of the trajectory recognition process is about 79.8% by validating the open data set. For the extracted single trajectory, the Bagged Trees combined model is used to identify the travel mode with an accuracy of about 76.2%.

Copyright

© 2019, 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  - Huabin Liu
AU  - Chunfu Shao
PY  - 2019/04
DA  - 2019/04
TI  - Recognition Method of Urban Residents' Travel Mode based on GPS Data
BT  - Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)
PB  - Atlantis Press
SP  - 101
EP  - 105
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmeit-19.2019.18
DO  - 10.2991/icmeit-19.2019.18
ID  - Liu2019/04
ER  -