Advertisement

A Prediction Precision Inference Method for Passenger Alighting Station Based on the Condition Hypothesis

  • Fan Li
  • Qingquan Li
  • Zhao Huang
  • Jizhe XiaEmail author
Conference paper
  • 21 Downloads
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 617)

Abstract

Smart IC-card has been widely used in fare payment systems of public transport, which produces a large number of ticket checking records and spatiotemporal trajectory information. Accurately predicting passengers’ travel stations based on IC-card data plays an important role in intelligent transportation. However, incomplete IC-Card transaction records are widely existing. The IC-card not only does not record the actual boarding stations but also lacks the information of alighting stations because passengers do not need to swipe card when they get off. Therefore, it is difficult to construct the actual passenger travel link, which makes it challenging to predict alighting stations accurately. Targeting on this challenge, we propose a “Boarding Cluster to Alighting Station” alighting station prediction model (BCTAS) by condition hypothesis. First, the model analyzes the travel characteristics of passengers’ public transport. Second, the smart IC-card transaction records and map-matching algorithm are used to construct the mixed boarding station link. Third, the model performs the station clustering and cluster expansion to merge the same name station and the nearest station into a cluster, and further constructs the mixed boarding cluster link. Fourth, a Variable Order Markov Model that named Prediction by Partial Match (PPM) is adopted to predict the mixed boarding cluster link and then predict the boarding station. Fifth, the model infers the prediction precision of the alighting cluster and alighting station based on the condition hypothesis. Finally, our approach was evaluated by using the public transport data obtained in Shenzhen city, China. The results show that (a) with the increase of training data, the precision of the model is gradually enhanced, (b) by using the mixed boarding cluster link, the prediction precision of the boarding cluster and boarding station could reach 88.05% and 84.52% respectively, (c) Based on the condition hypothesis, it can be inferred that the lower limit of the prediction precision of the alighting cluster and alighting station is 78.09% and 74.96%, respectively.

Keywords

Alighting station prediction Smart IC-card transaction records Station clustering and cluster expansion Variable order Markov model Prediction by partial match model (PPM) Condition hypothesis 

References

  1. 1.
    Medina SAO, Erath A (2013) Estimating dynamic workplace capacities by means of public transport smart card data and household travel survey in Singapore. Transp Res Record J Transp Res Board 2344(-1):20–30Google Scholar
  2. 2.
    Long Y, Shen Z (2015) Finding public transportation community structure based on large-scale smart card records in Beijing. Geospatial Analysis to Support Urban Planning in Beijing. Springer International PublishingGoogle Scholar
  3. 3.
    Zhong C, Arisona, SM et al (2014) Detecting the dynamics of urban structure through spatial network analysis. Int J Geogr Inf Sci 28(11):2178–2199Google Scholar
  4. 4.
    Brockmann D, Hufnagel L, Geisel T (2006) The scaling laws of human travel. Nature 439(7075):462–465CrossRefGoogle Scholar
  5. 5.
    Gonzalez MC, Hidalgo CA, Barabasi A-L (2008) Understanding individual human mobility patterns. Nature 453(7196):779–782CrossRefGoogle Scholar
  6. 6.
    Song C, Qu Z, Blumm N et al (2010) Limits of predictability in human mobility. Science 327(5968):1018MathSciNetCrossRefGoogle Scholar
  7. 7.
    Jiang B, Yin J, Zhao S (2009) Characterizing the human mobility pattern in a large street network. Phys Rev E: Stat, Nonlin, Soft Matter Phys 80(1):1711–1715Google Scholar
  8. 8.
    Roth C, Kang SM, Batty M et al (2011) Structure of urban movements: polycentric activity and entangled hierarchical flows. PLoS ONE 6(1):e15923CrossRefGoogle Scholar
  9. 9.
    Lin M, Hsu WJ, Zhuo QL (2012) Predictability of individuals’ mobility with high-resolution positioning data. In: ACM Conference on Ubiquitous Computing, pp 381–390Google Scholar
  10. 10.
    Lian D, Zhu Y, Xie X et al (2014) Analyzing location predictability on location-based social networks. Adv Knowl Discovery Data Mining, 102–113Google Scholar
  11. 11.
    Kuge N, Yamamura T, Shimoyama O et al (2000) A driver behavior recognition method based on a driver model framework. SAE Trans 109(6):469–476Google Scholar
  12. 12.
    Pentland A, Liu A (1999) Modeling and prediction of human behavior. Neural Comput 11(1):229–242CrossRefGoogle Scholar
  13. 13.
    Zheng X, Han J, Sun A (2018) A survey of location prediction on Twitter. IEEE Trans Knowl Data Eng 30(9):1652–1671Google Scholar
  14. 14.
    Scellato S, Musolesi M, Mascolo C et al (2011) NextPlace: a spatio-temporal prediction framework for pervasive systems. In: International conference on pervasive computing. Springer, Berlin, pp 152–169Google Scholar
  15. 15.
    Du Y et al (2018) A geographical location prediction method based on continuous time series Markov model. PLOS ONE 13(11)Google Scholar
  16. 16.
    Noulas A, Scellato S, Lathia N et al (2012) Mining user mobility features for next place prediction in location-based services. In: IEEE international conference on data mining. IEEE, New York, pp 1038–1043Google Scholar
  17. 17.
    Li Q, Zheng Y, Xie X et al (2008) Mining user similarity based on location history. In: ACM Sigspatial international conference on advances in geographic information systems. ACM, New York, p 34Google Scholar
  18. 18.
    Jeung H, Liu Q, Shen HT et al (2008) A hybrid prediction model for moving objects. In: Proceedings of the 24th IEEE international conference on data engineering. IEEE Press, Cancun, Mexico, pp 70–79Google Scholar
  19. 19.
    Do TMT, Gatica-Perez D (2012) Contextual conditional models for smartphone-based human mobility prediction. In: ACM conference on ubiquitous computing. ACM, New York, pp 163–172Google Scholar
  20. 20.
    Montoliu R, Blom J, Gatica-Perez D (2013) Discovering places of interest in everyday life from smartphone data. Multimedia Tools Appl 62(1):179–207CrossRefGoogle Scholar
  21. 21.
    Ashbrook D, Starner T (2003) Using GPS to learn significant locations and predict movement across multiple users. Pers Ubiquit Comput 7(5):275–286CrossRefGoogle Scholar
  22. 22.
    Gambs S, Killijian M-O et al (2012) Next place prediction using mobility Markov chains. In: EUROSYS 2012 workshop on measurement, privacy, and mobility, p 3Google Scholar
  23. 23.
    Mathew W, Raposo R, Martins B (2012) Predicting future locations with hidden Markov models. In: ACM conference on ubiquitous computing. ACM, New York, pp 911–918Google Scholar
  24. 24.
    Begleiter R, El-Yaniv R, Yona G (2011) On prediction using variable order Markov models. J Artif Intell Res 22(1):385–421Google Scholar
  25. 25.
    Yang J (2015) Research on location prediction based on historical trajectory. Hangzhou University of Electronic Science and TechnologyGoogle Scholar
  26. 26.
    Hu J, Deng J, Huang Z (2014) A judgment probability model of the alighting stations of the passengers with the bus IC card based on the trip link. Transp Syst Eng Inf 14(2):62–67Google Scholar
  27. 27.
    Li D, Lin Y, Zhao X et al (2011) Estimating a transit passenger trip origin-destination matrix using automatic fare collection system. In: Database systems for advanced applications. Springer, Berlin, Heidelberg, pp 502–513Google Scholar
  28. 28.
    Zhang F, Yuan NJ, Wang Y et al (2015) Reconstructing individual mobility from smart card transactions: a collaborative space alignment approach. Knowl Inf Syst 44(2):299–323CrossRefGoogle Scholar
  29. 29.
    Jiayi L, Jin Z, Jingwen Z et al (2018) An algorithm to identify passengers’ alighting stations and the effectiveness evaluation. Geomatics and Information Science of Wuhan UniversityGoogle Scholar
  30. 30.
    Yilin W, Zhjgang J (2017) Individual station estimation from smart card transactions. J East China Normal Univ (Natural Science) 05:210–221Google Scholar
  31. 31.
    Chen BY, Yuan H, Li Q et al (2014) Map-matching algorithm for large-scale low-frequency floating car data. Int J Geogr Inf Sci 28(1):22–38CrossRefGoogle Scholar
  32. 32.
    Macqueen J (1965) Some methods for classification and analysis of multivariate observations. In: Proceedings of Berkeley symposium on mathematical statistics and probability, pp 281–297Google Scholar
  33. 33.
    Ester M, Kriegel H P, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: International conference on knowledge discovery and data mining. AAAI Press, Palo Alto, pp 226–231Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Shenzhen Key Laboratory of Spatial Smart Sensing and ServicesShenzhen UniversityShenzhenChina
  2. 2.College of Computer Science and Software EngineeringShenzhen UniversityShenzhenChina
  3. 3.College of Information EngineeringShenzhen UniversityShenzhenChina

Personalised recommendations