access icon free Deep-learning architecture to forecast destinations of bus passengers from entry-only smart-card data

Although smart-card data secures collective travel information on public transportation users, the reality is that only a few cities are equipped with an automatic fare collection (AFC) system that can provide user information for both boarding and alighting locations. Many researchers have delved into forecasting the destinations of smart-card users. Such effort, however, have never been validated with actual data on a large scale. In the present study, a deep-learning model was developed to estimate the destinations of bus passengers based on both entry-only smart-card data and land-use characteristics. A supervised machine-learning model was trained using exact information on both boarding and alighting. That information was provided by the AFC system in Seoul, Korea. The model performance was superior to that of the most prevalent schemes developed thus far.

Inspec keywords: learning (artificial intelligence); smart cards; public transport; traffic information systems

Other keywords: user information; bus passengers; boarding locations; entry-only smart-card data; destinations forecasting; collective travel information; AFC system; alighting locations; public transportation users; automatic fare collection system; deep-learning architecture; land-use characteristics; supervised machine-learning model

Subjects: Knowledge engineering techniques; Traffic engineering computing

References

    1. 1)
      • 16. Trépanier, M., Tranchant, N., Chapleau, R.: ‘Individual trip destination estimation in a transit smart card automated fare collection system’, J. Intell. Transp. Syst., 2007, 11, (1), pp. 114.
    2. 2)
      • 7. Chang, J., Park, K.: ‘Estimation of the value of walking travel time by meta-analysis’, J. Transp. Res., 2010, 17, pp. 1322.
    3. 3)
      • 18. Zhao, J.: ‘The planning and analysis implications of automated data collection systems: rail transit OD matrix inference and path choice modeling examples’. MS thesis, MIT, 2004.
    4. 4)
      • 13. Chapleau, R., Trepanier, M., Chu, K.K.: ‘The ultimate survey for transit planning: complete information with smart card data and GIS, France’. Proc. of the Eighth Int. Conf. on Survey Methods in Transport: Harmonisation and Data Comparability, Annecy, France, 2008, pp. 2531.
    5. 5)
      • 3. Wang, W., Attanucci, J.P., Wilson, N.H.: ‘Bus passenger origin–destination estimation and related analyses using automated data collection systems’, J. Public Transp., 2011, 14, (4), pp. 131150.
    6. 6)
      • 1. Barry, J., Newhouser, R., Rahbee, A., et al: ‘Origin and destination estimation in New York city with automated fare system data’, Transp. Res. Rec. J. Transp. Res. Board, 2002, 1817, (24), pp. 183187.
    7. 7)
      • 20. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘ImageNet classification with deep convolutional neural networks’, Adv. Neural Inf. Process. Syst., 2012, 25, pp. 10971105.
    8. 8)
      • 11. Nassir, N., Khani, A., Lee, S., et al: ‘Transit stop-level origin–destination estimation through use of transit schedule and automated data collection system’, Transp. Res. Rec. J. Transp. Res. Board, 2011, 2263, (16), pp. 140150.
    9. 9)
      • 10. Alsger, A.A., Mesbah, M., Ferreira, L., et al: ‘Use of smart card fare data to estimate public transport origin–destination matrix’, Transp. Res. Rec. J. Transp. Res. Board, 2015, 2535, pp. 8896.
    10. 10)
      • 14. Zhang, L., Zhao, S., Zhu, Y., et al: ‘Study on the method of constructing bus stops OD matrix based on IC card data’. 2007 Int. Conf. on Wireless Communications, Networking and Mobile Computing, September 2007, pp. 31473150.
    11. 11)
      • 2. Farzin, J.: ‘Constructing an automated bus origin–destination matrix using fare card and global positioning system data in São Paulo, Brazil’, Transp. Res. Rec. J. Transp. Res. Board, 2008, 2072, (4), pp. 3037.
    12. 12)
      • 4. Munizaga, M., Devillaine, F., Navarrete, C., et al: ‘Validating travel behavior estimated from smart card data’, Transp. Res. C, Emerg. Technol., 2014, 44, pp. 7079.
    13. 13)
      • 5. Zhang, F., Yuan, N.J., Wang, Y., et al: ‘Reconstructing individual mobility from smart card transactions: a collaborative space alignment approach’, Knowl. Inf. Syst., 2015, 44, (2), pp. 299323.
    14. 14)
      • 8. Nunes, A.A., Dias, T.G., Cunha, J.F.: ‘Passenger journey destination estimation from automated fare collection system data using spatial validation’, IEEE Trans. Intell. Transp. Syst., 2015, 17, (1), pp. 133142.
    15. 15)
      • 6. Munizaga, M., Palma, C.: ‘Estimation of a disaggregate multimodal public transport origin–destination matrix from passive smartcard data from Santiago, Chile’, Transp. Res. C, Emerg. Technol., 2012, 24, pp. 918.
    16. 16)
      • 12. Barry, J.J., Freimer, R., Slavin, H.: ‘Use of entry-only automatic fare collection data to estimate linked transit trips in New York City’, Transp. Res. Rec. J. Transp. Res. Board, 2009, 2112, pp. 5361.
    17. 17)
      • 17. Cui, A.: ‘Bus passenger origin–destination matrix estimation using automated data collection systems’. MS thesis, MIT, 2006.
    18. 18)
      • 21. Kyoungtae, K., Jaehong, M., Inmook, L.: ‘Analyzing passenger's tagging behavior using smart-card data’. Proc. of the 2014 Conf. of the Korean Society for Railway, Korea, October 2014, pp. 635638, in Korean.
    19. 19)
      • 9. Nassir, N., Hickman, M., Ma, Z.L.: ‘Activity detection and transfer identification for public transit fare card data’, Transportation, 2015, 42, (4), pp. 683705.
    20. 20)
      • 15. Zhao, J., Rahbee, A., Wilson, N.H.M.: ‘Estimating a rail passenger trip origin–destination matrix using automated data collection systems’, Comput. Civ. Infrastruct. Eng., 2007, 22, (5), pp. 376387.
    21. 21)
      • 19. Bengio, Y., Goodfellow, I.J., Courville, A.: ‘Deep learning’ (MIT Press, 2016).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2016.0276
Loading

Related content

content/journals/10.1049/iet-its.2016.0276
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading