Research Article
A Passenger Flow Analysis Method Through Ride Behaviors on Massive Smart Card Data
114 downloads
@INPROCEEDINGS{10.1007/978-3-030-00916-8_35, author={Weilong Ding and Zhuofeng Zhao and Han Li and Yaqi Cao and Yang Xu}, title={A Passenger Flow Analysis Method Through Ride Behaviors on Massive Smart Card Data}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 13th International Conference, CollaborateCom 2017, Edinburgh, UK, December 11--13, 2017, Proceedings}, proceedings_a={COLLABORATECOM}, year={2018}, month={10}, keywords={Smart card data Passenger flow Ride behavior Urban computing}, doi={10.1007/978-3-030-00916-8_35} }- Weilong Ding
Zhuofeng Zhao
Han Li
Yaqi Cao
Yang Xu
Year: 2018
A Passenger Flow Analysis Method Through Ride Behaviors on Massive Smart Card Data
COLLABORATECOM
Springer
DOI: 10.1007/978-3-030-00916-8_35
Abstract
In transportation business, the analysis counts the ridership of given bus stops on given time duration. On the smart card data from the card readers of buses, the calculation of passenger flow faces challenges: the accuracy or the latency is blamed, and the scalability is poor on large volume data. In this paper, we propose an effective method on massive smart card data, in which ride behaviors are modeled and the passenger flow can be achieved and efficiently. Our method is implemented by Hadoop MapReduce, and proves minute-level latencies on weekly historical data with nearly linear scalability.
Copyright © 2017–2024 EAI
