Using Smart Card Data Trimmed by Train Schedule to Analyze Metro Passenger Route Choice with Synchronous Clustering
Authors:
Open Access
- 24 July 2018
- journal article
- research article
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2018, 1-13
Abstract
The metro passenger route choice, influenced by both train schedule and time constraints, is important to metro operation and management. Smart card data (Automatic Fare Collection (AFC) data in metro system) including inbound and outbound swiping time are useful for analysis of the characteristics of passengers’ route choices in metro while they could not reflect the property of train schedule directly. Train schedule is used in this paper to trim smart card data through removing inbound and outbound walking time to/from platforms and waiting time. Thus, passengers’ pure travel time in accord with trains’ arrival and departure can be obtained. Synchronous clustering (SynC) algorithm is then applied to analyze these processed data to calculate passenger route choice probability. Finally, a case study was conducted to illustrate the effectiveness of the proposed algorithm. Results showed the proposed algorithm works well to analyze metro passenger route choice. It was shown that passenger route choice during both peak period and flat period could be clustered automatically, and noise data are isolated. The probability of route choice calculated through SynC algorithm can be used to revise traditional model results.Keywords
Funding Information
- Ministry of Education of the People’s Republic of China (15YJCZH108, 2015A030310341)
- Natural Science Foundation of Guangdong Province (15YJCZH108, 2015A030310341)
This publication has 22 references indexed in Scilit:
- Calibrating Rail Transit Assignment Models with Genetic Algorithm and Automated Fare Collection DataComputer-Aided Civil and Infrastructure Engineering, 2014
- Validating travel behavior estimated from smartcard dataTransportation Research Part C: Emerging Technologies, 2014
- Estimation of a disaggregate multimodal public transport Origin–Destination matrix from passive smartcard data from Santiago, ChileTransportation Research Part C: Emerging Technologies, 2012
- Smart card data use in public transit: A literature reviewTransportation Research Part C: Emerging Technologies, 2011
- Transit Users’ Route‐Choice Modelling in Transit Assignment: A ReviewTransport Reviews, 2010
- Comparative analysis of transit assignment: evidence from urban railway system in the Tokyo Metropolitan AreaTransportation, 2010
- Estimation method for railway passengers’ train choice behavior with smart card transaction dataTransportation, 2010
- Data clustering: 50 years beyond K-meansPattern Recognition Letters, 2010
- Measuring transit use variability with smart-card dataTransport Policy, 2007
- Clustering by Passing Messages Between Data PointsScience, 2007