Abstract
In this article, we target at recovering the exact routes taken by commuters inside a metro system that are not captured by an Automated Fare Collection (AFC) system and hence remain unknown. We strategically propose two inference tasks to handle the recovering, one to infer the travel time of each travel link that contributes to the total duration of any trip inside a metro network and the other to infer the route preferences based on historical trip records and the travel time of each travel link inferred in the previous inference task. As these two inference tasks have interrelationship, most of existing works perform these two tasks simultaneously. However, our solution TripDecoder adopts a totally different approach. TripDecoder fully utilizes the fact that there are some trips inside a metro system with only one practical route available. It strategically decouples these two inference tasks by only taking those trip records with only one practical route as the input for the first inference task of travel time and feeding the inferred travel time to the second inference task as an additional input, which not only improves the accuracy but also effectively reduces the complexity of both inference tasks. Two case studies have been performed based on the city-scale real trip records captured by the AFC systems in Singapore and Taipei to compare the accuracy and efficiency of TripDecoder and its competitors. As expected, TripDecoder has achieved the best accuracy in both datasets, and it also demonstrates its superior efficiency and scalability.
- Ka Kee Alfred Chu and Robert Chapleau. 2010. Augmenting transit trip characterization and travel behavior comprehension: Multiday location-stamped smart card transactions. Transport. Res. Rec. 2183, 1 (2010), 29–40.Google Scholar
- Nicolò Colombo, Ricardo Silva, and Soong Moon Kang. 2017. Tomography of the London underground: A scalable model for origin-destination data. In Advances in Neural Information Processing Systems. MIT Press, 3062–3073. Google Scholar
Digital Library
- Thomas Holleczek, Shanyang Yin, Yunye Jin, Spiros Antonatos, Han Leong Goh, Samantha Low, Amy Shi-Nash et al. 2015. Traffic measurement and route recommendation system for mass rapid transit. In Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 1859–1868. Google Scholar
Digital Library
- Ling Hong, Wei Li, and Wei Zhu. 2017. Assigning passenger flows on a metro network based on automatic fare collection data and timetable. Discrete Dynam. Nature Soc. 2017 (2017).Google Scholar
- Fanglei Jin, Enjian Yao, Yongsheng Zhang, and Shasha Liu. 2017. Metro passengers’ route choice model and its application considering perceived transfer threshold. PLoS ONE 12, 9 (2017), e0185349.Google Scholar
- Yulin Liu, Jonathan Bunker, and Luis Ferreira. 2010. Transit users’ route-choice modelling in transit assignment: A review. Transport Rev. 30, 6 (2010), 753–769.Google Scholar
- Shoichiro Nakayama and Ryuichi Kitamura. 2000. Route choice model with inductive learning. Transport. Res. Rec. 1725, 1 (2000), 63–70.Google Scholar
- Bo Friis Nielsen, Laura Frølich, Otto Anker Nielsen, and Dorte Filges. 2014. Estimating passenger numbers in trains using existing weighing capabilities. Transport. A: Transport Sci. 10, 6 (2014), 502–517.Google Scholar
Cross Ref
- Agostino Nuzzolo, U. Crisalli, Luca Rosati, and Angel Ibeas. 2013. STOP: A short term transit occupancy prediction tool for APTIS and real time transit management systems. In Proceedings of the IEEE Conference on Intelligent Transportation Systems, Proceedings (ITSC’13). 1894–1899.Google Scholar
- Peter Rickwood and Garry Glazebrook. 2009. Urban structure and commuting in Australian cities. Urban Policy Res. 27, 2 (2009), 171–188.Google Scholar
- Ricardo Silva, Soong Moon Kang, and Edoardo M. Airoldi. 2015. Predicting traffic volumes and estimating the effects of shocks in massive transportation systems. Proc. Natl. Acad. Sci. U.S.A. 112, 18 (2015), 5643–5648.Google Scholar
Cross Ref
- Tony Smith, Chao-Che Hsu, and Yueh-Ling Hsu. 2008. Stochastic user equilibrium model with implicit travel time budget constraint. Transport. Res. Rec.: J. Transport. Res. Board 2085 (2008), 95–103.Google Scholar
- Guandong Sun, Yun Xiong, and Yangyong Zhu. 2017. How the passengers flow in complex metro networks? In Proceedings of the 29th International Conference on Scientific and Statistical Database Management. ACM, 23. Google Scholar
Digital Library
- Lijun Sun and Jian Gang Jin. 2015. Modeling temporal flow assignment in metro networks using smart card data. Proceedings of the IEEE 18th International Conference on Intelligent Transportation Systems. 836–841. Google Scholar
Digital Library
- Lijun Sun, Yang Lu, Jian Gang Jin, Der-Horng Lee, and Kay W. Axhausen. 2015. An integrated Bayesian approach for passenger flow assignment in metro networks. Transport. Res. Part C: Emerg. Technol. 52 (2015), 116–131.Google Scholar
Cross Ref
- Xiancan Tian and Baihua Zheng. [n.d.]. Using smart card data to model commuters’ response upon unexpected train delays. In Proceedings of the IEEE Conference on Big Data. 831–840.Google Scholar
- Gilles Vandewiele, Pieter Colpaert, Olivier Janssens, Joachim Van Herwegen, Ruben Verborgh, Erik Mannens, Femke Ongenae, and Filip De Turck. 2017. Predicting train occupancies based on query logs and external data sources. In Proceedings of the 7th International Workshop on Location and the Web. Google Scholar
Digital Library
- Yazhe Wang, Chih-Chieh Hung, Baihua Zheng, and Ee-Peng Lim. 2018. TripDecoder: Inferring routes of passengers of mass rapid transit systems by smart card transaction data. In Proceedings of the IEEE International Conference on Data Mining Workshops.Google Scholar
- Xinyue Xu, Liping Xie, Haiying Li, and Lingqiao Qin. 2018. Learning the route choice behavior of subway passengers from AFC dat. Expert Syst. Appl. 95 (2018), 324–332.Google Scholar
- Haodong Yin, Baoming Han, Dewei Li, Jianjun Wu, and Huijun Sun. 2016. Modeling and simulating passenger behavior for a station closure in a rail transit network. PLoS One 11, 12 (2016).Google Scholar
Index Terms
TRIPDECODER: Study Travel Time Attributes and Route Preferences of Metro Systems from Smart Card Data
Recommendations
Smart Travel Itinerary Planning Application using Held-Karp Algorithm and Balanced Clustering Approach
EBIMCS '19: Proceedings of the 2019 2nd International Conference on E-Business, Information Management and Computer ScienceIn this paper, a mobile application that could assist tourists in arranging travel itineraries has been developed. In the case of making an itinerary, often tourists have been determined the tourist destinations they want to visit, but they confused in ...
Comparative study on drivers' route choice response to travel information at different departure time
CAR'10: Proceedings of the 2nd international Asia conference on Informatics in control, automation and robotics - Volume 3Studying drivers' route choice behavior under the influence of travel information is important because it provides insight to improve the effect of travel information on traffic environment. This paper mainly aims to study the impact of travel ...
A study on topic models using LDA and Word2Vec in travel route recommendation: focus on convergence travel and tours reviews
AbstractAt present, we live in prosperity contrary to the past times. As income increases, people enjoy wealth, but more people tend to pursue their own inner happiness: travel. People go to other places or visit foreign countries for business or journey. ...






Comments