access icon free Hybrid model for predicting anomalous large passenger flow in urban metros

Machine learning models have been widely adopted for passenger flow prediction in urban metros; however, the authors find machine learning models may underperform under anomalous large passenger flow conditions. In this study, they develop a prediction framework that combines the advantage of complex network models in capturing the collective behaviour of passengers and the advantage of online learning algorithms in characterising rapid changes in real-time data. The proposed method considerably improves the accuracy of passenger flow prediction under anomalous conditions. This study can also serve as an exploration of interdisciplinary methods for transportation research.

Inspec keywords: rail traffic; transportation; complex networks; behavioural sciences; learning (artificial intelligence); real-time systems

Other keywords: hybrid model; machine learning models; collective behaviour; complex network models; passenger flow prediction; prediction framework; real-time data; anomalous large passenger flow conditions; transportation; online learning algorithms; anomalous conditions; urban metros

Subjects: Social and behavioural sciences computing; Traffic engineering computing; Machine learning (artificial intelligence)

References

    1. 1)
      • 21. Li, H., Wang, Y., Xu, X., et al: ‘Short-term passenger flow prediction under passenger flow control using a dynamic radial basis function network’, Appl. Soft Comput. J., 2019, 83, p. 105620.
    2. 2)
      • 17. Sun, Y., Leng, B., Guan, W.: ‘A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system’, Neurocomputing, 2015, 166, pp. 109121.
    3. 3)
      • 35. Allström, A., Ekström, J., Gundlegård, D., et al: ‘Hybrid approach for short-term traffic state and travel time prediction on highways’, Transp. Res. Rec., 2016, 2554, (1), pp. 6068.
    4. 4)
      • 10. Lin, Y., Dai, X., Li, L., et al: ‘Pattern sensitive prediction of traffic flow based on generative adversarial framework’, IEEE Trans. Intell. Transp. Syst., 2019, 20, (6), pp. 23952400.
    5. 5)
      • 20. Wei, Y., Chen, M.C.: ‘Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks’, Transp. Res. C, Emerg. Technol., 2012, 21, (1), pp. 148162.
    6. 6)
      • 47. Strauss, D.J., Hartigan, J.A.: ‘Clustering algorithms’, Biometrics, 1975, 31, (3), pp. 793793.
    7. 7)
      • 14. Zhang, J., Shen, D., Tu, L., et al: ‘A real-time passenger flow estimation and prediction method for urban bus transit systems’, IEEE Trans. Intell. Transp. Syst., 2017, 18, (11), pp. 31683178.
    8. 8)
      • 13. Ma, Z., Xing, J., Mesbah, M., et al: ‘Predicting short-term bus passenger demand using a pattern hybrid approach’, Transp. Res. C, Emerg. Technol., 2014, 39, pp. 148163.
    9. 9)
      • 26. Liu, L., Chen, R.C.: ‘A novel passenger flow prediction model using deep learning methods’, Transp. Res. C, Emerg. Technol., 2017, 84, pp. 7491.
    10. 10)
      • 40. Castro-Neto, M., Jeong, Y.S., Jeong, M.K., et al: ‘Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions’, Expert Syst. Appl., 2009, 36, (3 PART 2), pp. 61646173.
    11. 11)
      • 27. Hao, S., Lee, D.H., Zhao, D.: ‘Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system’, Transp. Res. C, Emerg. Technol., 2019, 107, pp. 287300.
    12. 12)
      • 38. Chen, X., Zhang, S., Li, L.: ‘Multi-model ensemble for short-term traffic flow prediction under normal and abnormal conditions’, IET Intell. Transp. Syst., 2019, 13, (2), pp. 330339.
    13. 13)
      • 45. Rosenblatt, M.: ‘Remarks on some nonparametric estimates of a density function’, Ann. Math. Stat., 1956, 27, (3), pp. 832837.
    14. 14)
      • 32. Li, Y., Wang, X., Sun, S., et al: ‘Forecasting short-term subway passenger flow under special events scenarios using multiscale radial basis function networks’, Transp. Res. C, Emerg. Technol., 2017, 77, pp. 306328.
    15. 15)
      • 9. Sun, D., Zhao, Y., Lu, Q.C.: ‘Vulnerability analysis of urban rail transit networks: a case study of Shanghai, China’, Sustainability, 2015, 7, (6), pp. 69196936.
    16. 16)
      • 3. Liu, Y., Liu, Z., Jia, R.: ‘DeepPF: A deep learning based architecture for metro passenger flow prediction’, Transp. Res. C, Emerg. Technol., 2019, 101, pp. 1834.
    17. 17)
      • 16. Diao, Z., Zhang, D., Wang, X., et al: ‘A hybrid model for short-term traffic volume prediction in massive transportation systems’, IEEE Trans. Intell. Transp. Syst., 2019, 20, (3), pp. 935946.
    18. 18)
      • 46. Parzen, E.: ‘On estimation of a probability density function and mode’, Ann. Math. Stat., 1962, 33, (3), pp. 10651076.
    19. 19)
      • 49. Zou, J., Schiebinger, L.: ‘AI can be sexist and racist — it's time to make it fair’, Nature, 2018, 559, (7714), pp. 324326.
    20. 20)
      • 41. Jeong, Y.S., Byon, Y.J., Castro-Neto, M.M., et al: ‘Supervised weighting-online learning algorithm for short-term traffic flow prediction’, IEEE Trans. Intell. Transp. Syst., 2013, 14, (4), pp. 17001707.
    21. 21)
      • 48. Pedregosa, F., Varoquaux, G., Gramfort, A., et al: ‘Scikit-learn: machine learning in python’, J. Mach. Learn. Res., 2011, 12, pp. 28252830.
    22. 22)
      • 37. Haworth, J., Shawe-Taylor, J., Cheng, T., et al: ‘Local online kernel ridge regression for forecasting of urban travel times’, Transp. Res. C, Emerg. Technol., 2014, 46, pp. 151178.
    23. 23)
      • 4. Shenzhen Metro: ‘Shenzhen Metro Annual Report 2018’. Available at http://www.szmc.net/.
    24. 24)
      • 1. Bowes, D.R., Ihlanfeldt, K.R.: ‘Identifying the impacts of rail transit stations on residential property values’, J. Urban Econ., 2001, 50, (1), pp. 125.
    25. 25)
      • 44. Huang, Z., Wang, P., Zhang, F., et al: ‘A mobility network approach to identify and anticipate large crowd gatherings’, Transp. Res. B, Methodol., 2018, 114, pp. 147170.
    26. 26)
      • 54. Abadi, M., Barham, P., Chen, J., et al: ‘Tensorflow: a system for large-scale machine learning’. Proc. 12th USENIX Symp. on Operating Systems Design and Implementation, OSDI 2016, Savannah, Georgia, USA, 2016.
    27. 27)
      • 36. Salamanis, A., Margaritis, G., Kehagias, D.D., et al: ‘Identifying patterns under both normal and abnormal traffic conditions for short-term traffic prediction’, Transp. Res. Procedia, 2017, 22, pp. 665674.
    28. 28)
      • 33. Chen, E., Ye, Z., Wang, C., et al: ‘Subway passenger flow prediction for special events using smart card data’, IEEE Trans. Intell. Transp. Syst., 2019, PP, pp. 112.
    29. 29)
      • 29. Noursalehi, P., Koutsopoulos, H.N., Zhao, J.: ‘Real time transit demand prediction capturing station interactions and impact of special events’, Transp. Res. C, Emerg. Technol., 2018, 97, pp. 277300.
    30. 30)
      • 18. Ling, X., Huang, Z., Wang, C., et al: ‘Predicting subway passenger flows under different traffic conditions’, PLOS One, 2018, 13, (8), p. e0202707.
    31. 31)
      • 19. Tang, L., Zhao, Y., Cabrera, J., et al: ‘Forecasting short-term passenger flow: an empirical study on Shenzhen metro’, IEEE Trans. Intell. Transp. Syst., 2018, 20, (10), pp. 36133622.
    32. 32)
      • 52. Williams, C.K.I.: ‘Learning with kernels: support vector machines, regularization, optimization, and beyond’, J. Am. Stat. Assoc., 2003, 98, (462), pp. 489489.
    33. 33)
      • 43. Wang, H., Li, L., Pan, P., et al: ‘Early warning of burst passenger flow in public transportation system’, Transp. Res. C, Emerg. Technol., 2019, 105, pp. 580598.
    34. 34)
      • 34. Wu, T., Xie, K., Xinpin, D., et al: ‘A online boosting approach for traffic flow forecasting under abnormal conditions’. Proc. 2012 9th Int. Conf. on Fuzzy Systems and Knowledge Discovery (FSKD 2012), Chongqing, China, 2012, pp. 25552559.
    35. 35)
      • 11. Candia, J., González, M.C., Wang, P., et al: ‘Uncovering individual and collective human dynamics from mobile phone records’, J. Phys. A: Math. Theor., 2008, 41, (22), p. 224015.
    36. 36)
      • 15. Jiao, P., Li, R., Sun, T., et al: ‘Three revised Kalman filtering models for short-term rail transit passenger flow prediction’, Math. Probl. Eng., 2016, 2016.
    37. 37)
      • 51. Seabold, S., Perktold, J.: ‘Econometric and statistical modeling with python’. Proc. 9th Python in Science Conf., Austin, Texas, USA, 2010.
    38. 38)
      • 6. Zhang, J., Xu, X., Hong, L., et al: ‘Networked analysis of the shanghai subway network, in China’, Physica A, 2011, 390, (23–24), pp. 45624570.
    39. 39)
      • 55. Kingma, D.P., Ba, J.L.: ‘Adam: A method for stochastic optimization’. 3rd Int. Conf. on Learning Representations, ICLR 2015 – Conf. Track Proc., San Diego, California, USA, 2015.
    40. 40)
      • 39. Peled, I., Kamalakar, R., Azevedo, C.L., et al: ‘QTIP: quick simulation-based adaptation of traffic model per incident parameters’, J. Simul., 2020, pp. 121.
    41. 41)
      • 53. Balestrassi, P.P., Popova, E., Paiva, A.P., et al: ‘Design of experiments on neural network's training for nonlinear time series forecasting’, Neurocomputing, 2009, 72, (4–6), pp. 11601178.
    42. 42)
      • 30. Rodrigues, F., Borysov, S.S., Ribeiro, B., et al: ‘A Bayesian additive model for understanding public transport usage in special events’, IEEE Trans. Pattern Anal. Mach. Intell., 2017, 39, (11), pp. 21132126.
    43. 43)
      • 12. Box, G.E.P., Jenkins, G.M.: ‘Some recent advances in forecasting and control’, Appl. Stat., 1968, 17, (2), pp. 91109.
    44. 44)
      • 7. He, L., Liang, Q., Fang, S.: ‘Challenges and innovative solutions in urban rail transit network operations and management: China's Guangzhou metro experience’, Urban Rail Transit., 2016, 2, (1), pp. 3345.
    45. 45)
      • 23. Collobert, R., Weston, J.: ‘A unified architecture for natural language processing: deep neural networks with multitask learning’. Proc. 25th Int. Conf. on Machine Learning, Helsinki, Finland, 2008, pp. 160167.
    46. 46)
      • 24. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘ImageNet classification with deep convolutional neural networks’. Advances in Neural Information Processing Systems, Lake Tahoe, Nevada, USA, 2012, pp. 10971105.
    47. 47)
      • 28. Pereira, F.C., Rodrigues, F., Ben-Akiva, M.: ‘Using data from the web to predict public transport arrivals under special events scenarios’, J. Intell. Transp. Syst. Technol. Plann., Oper., 2015, 19, (3), pp. 273288.
    48. 48)
      • 8. Zhou, M., Dong, H., Ioannou, P.A., et al: ‘Guided crowd evacuation: approaches and challenges’, IEEE/CAA J. Autom. Sin., 2019, 6, (5), pp. 10811094.
    49. 49)
      • 22. Hinton, G., Deng, L., Yu, D., et al: ‘Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups’, IEEE Signal Process. Mag., 2012, 29, (6), pp. 8297.
    50. 50)
      • 25. Bai, Y., Sun, Z., Zeng, B., et al: ‘A multi-pattern deep fusion model for short-term bus passenger flow forecasting’, Appl. Soft Comput. J., 2017, 58, pp. 669680.
    51. 51)
      • 31. Ni, M., He, Q., Gao, J.: ‘Forecasting the subway passenger flow under event occurrences with social media’, IEEE Trans. Intell. Transp. Syst., 2017, 18, (6), pp. 16231632.
    52. 52)
      • 2. Wang, Y., Feng, H., Xi, X.: ‘Monitoring and autonomous control of Beijing subway HVAC system for energy sustainability’, Energy Sust. Dev., 2017, 39, pp. 112.
    53. 53)
      • 42. Ding, C., Duan, J., Zhang, Y., et al: ‘Using an ARIMA-GARCH modeling approach to improve subway short-term ridership forecasting accounting for dynamic volatility’, IEEE Trans. Intell. Transp. Syst., 2018, 19, (4), pp. 10541064.
    54. 54)
      • 5. MTA: ‘New York City Transit Annual Ridership’. Available at http://web.mta.info/nyct/facts/ridership/.
    55. 55)
      • 50. Dickey, D.A., Fuller, W.A.: ‘Distribution of the estimators for autoregressive time series with a unit root’, J. Am. Stat. Assoc., 1979, 74, (366), p. 427.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2020.0054
Loading

Related content

content/journals/10.1049/iet-its.2020.0054
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading