Efficient and Accurate Traffic Flow Prediction via Fast Dynamic Tensor Completion

  • Jinzhi Liao
  • Xiang Zhao
  • Jiuyang Tang
  • Chong Zhang
  • Mingke He
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 728)


Timely and accurate prediction of traffic flow plays an important role in improving living quality of the public, which greatly influences the polices and regulations to be enforced and abided by. In this paper, we focus on urban highway traffic prediction, and present a tensor completion based method, namely, DTC-F. It is conceived on the solid basis of dynamic tensor model for traffic prediction, and in this paper, fast low rank tensor completion and dynamic tensor structure are first combined to pursue high prediction performance. The proposed DTC-F method excavates the inner law of traffic flow data by taking account of multi-mode features, such as daily and weekly periodicity, spatial information, and temporal variations, etc. Empirical evaluation demonstrates the superiority of DTC-F, and indicates that the proposed method is potentially applicable in large and dynamic highway networks.



This work was in part supported by NSFC under grants Nos. 61402498, 71331008 and 71690233.


  1. 1.
    Ahmed, M.S., and A.R. Cook. 1979. Analysis of freeway traffic time-series data by using box-jenkins techniques. Transportation Research Record 722: 1–9.Google Scholar
  2. 2.
    Cetin, M., and G. Comert. 1965. Short-term traffic flow prediction with regime switching models. Transportation Research Record 23–31: 2006.Google Scholar
  3. 3.
    Chang, H., Y. Lee, B. Yoon, and S. Baek. 2012. Dynamic near-term traffic flow prediction: System oriented approach based on past experiences. IET Intelligent Transport Systems 6 (3): 292–305.CrossRefGoogle Scholar
  4. 4.
    Cichocki, Andrzej, Rafal Zdunek, Anh Huy Phan, and Shun-ichi Amari. 2009. Nonnegative Matrix and Tensor Factorizations—Applications to Exploratory Multi-way Data Analysis and Blind Source Separation. Wiley.Google Scholar
  5. 5.
    Dimitriou, Loukas, Theodore Tsekeris, and Antony Stathopoulos. 2008. Adaptive hybrid fuzzy rule-based system approach for modeling and predicting urban traffic flow. Transportation Research Part C: Emerging Technologies 16 (5): 554–573.CrossRefGoogle Scholar
  6. 6.
    El Faouzi, N.E. 1996. Nonparametric traffic flow prediction using kernel estimator. In Proceedings of The 13th International Symposium on Transportation and Traffic Theory, 41–54.Google Scholar
  7. 7.
    Hamed, M., H. Al-Masaeid, and Z. Said. 1995. Short-term prediction of traffic volume in urban arterials. Journal of Transportation Engineering 121 (3): 249–254.CrossRefGoogle Scholar
  8. 8.
    Jeong, Young-Seon, Young-Ji Byon, Manoel Mendonca Castro-Neto, and Said M. Easa. 2013. Supervised weighting-online learning algorithm for short-term traffic flow prediction. IEEE Transactions of Intelligent Transportation Systems 14(4): 1700–1707.Google Scholar
  9. 9.
    Kamarianakis, Y., and P. Prastacos. 1857. Forecasting traffic flow conditions in an urban network: Comparison of multivariate and univariate approaches. Transportation Research Record 74–84: 2003.Google Scholar
  10. 10.
    Kolda, T.G., E. Acar, D. M. Dunlavy, and M. Mørup. 2011. Scalable tensor factorizations for incomplete data. Chemometrics Intelligent Laboratory Systems 106(1): 41 – 56.Google Scholar
  11. 11.
    Kolda, T., and B. Bader. 2009. Tensor decompositions and applications. SIAM Review 51 (3): 455–500.MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Kolda, Tamara G., and Brett W. Bader. 2009. Tensor decompositions and applications. SIAM Review 51 (3): 455–500.MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Lee, S., and D. Fambro. 1999. Application of subset autoregressive integrated moving average model for short-term freeway traffic volume forecasting. Transportation Research Record 1678: 179–188.CrossRefGoogle Scholar
  14. 14.
    Levin, M., and Y.-D. Tsao. 1980. On forecasting freeway occupancies and volumes. Transportation Research Record 722: 47–49.Google Scholar
  15. 15.
    Liu, Ji, Przemyslaw Musialski, Peter Wonka, and Jieping Ye. 2013. Tensor completion for estimating missing values in visual data. IEEE Transactions on Pattern Analysis and Machine Intelligence 35 (1): 208–220.CrossRefGoogle Scholar
  16. 16.
    Nesterov, Y. 1998. Introductory lectures on convex programming, 119–120. Notes: Lecture.Google Scholar
  17. 17.
    Nesterov, Y. 2005. Smooth minimization of non-smooth functions. Mathemtaical Programming 103 (1): 127–152.MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Ran, Bin, Huachun Tan, Jianshuai Feng, Ying Liu, and Wuhong Wang. 2015. Traffic speed data imputation method based on tensor completion. Computational Intelligence and Neuroscience 364089:1–364089:9.Google Scholar
  19. 19.
    Ritchie, S.G., and C. Oh. 2005. Exploring the relationship between data aggregation and predictability to provide better predictive traffic information. Transportation Research Record 1935 (1): 28–36.Google Scholar
  20. 20.
    Sun, H.Y., H.X. Liu, H. Xiao, R.R. He, and B. Ran. 1836. Use of local linear regression model for short-term traffic forecasting. Transportation Research Record 143–150: 2003.Google Scholar
  21. 21.
    Sun, Shiliang, Changshui Zhang, and Yu. Guoqiang. 2006. A bayesian network approach to traffic flow forecasting. IEEE Transactions on Intelligent Transportation Systems 7 (1): 124–132.CrossRefGoogle Scholar
  22. 22.
    Tan, Huachun, Guangdong Feng, Jianshuai Feng, Wuhong Wang, Yu-Jin Zhang, and Feng Li. 2013. A tensor-based method for missing traffic data completion. Transportation Research Part C: Emerging Technologies 28:15 – 27. Euro Transportation: selected paper from the EWGT Meeting, Padova, September 2009.Google Scholar
  23. 23.
    Tan, Man-Chun, Sze Chun Wong, Jian-Min Xu, Zhan-Rong Guan, and Peng Zhang. An aggregation approach to short-term traffic flow prediction. IEEE Transactions on Intelligent Transportation Systems, 10(1):60–69.Google Scholar
  24. 24.
    Tan, Huachun, Wu Yuankai, Bin Shen, Peter J. Jin, and Bin Ran. 2016. Short-term traffic prediction based on dynamic tensor completion. IEEE Transactions on Intelligent Transportation Systems 17 (8): 2123–2133.CrossRefGoogle Scholar
  25. 25.
    Tchrakian, Tigran T., Biswajit Basu, and Margaret O’Mahony. 2012. Real-time traffic flow forecasting using spectral analysis. IEEE Transactions on Intelligent Transportation Systems 13 (2): 519–526.CrossRefGoogle Scholar
  26. 26.
    Van Der Voort, Mascha, Mark Dougherty, and Susan Watson. 1996. Combining kohonen maps with arima time series models to forecast traffic flow. Transportation Research Part C: Emerging Technologies 4 (5): 307–318.CrossRefGoogle Scholar
  27. 27.
    Vlahogianni, E., and M. Karlaftis. 2011. Temporal aggregation in traffic data: Implications for statistical characteristics and model choice. Transportation Letters 3 (1): 37–49.CrossRefGoogle Scholar
  28. 28.
    Williams, B.M. 2001. Multivariate vehicular traffic flow prediction: Evaluation of arimax modeling. Transportation Research Record 1776: 194–200.CrossRefGoogle Scholar
  29. 29.
    Williams, B.M., and L.A. Hoel. 2003. Modeling and forecasting vehicular traffic flow as a seasonal arima process: Theoretical basis and empirical results. Journal of Transportation Engineering 129 (6): 664–672.CrossRefGoogle Scholar
  30. 30.
    Zargari, Shahriar Afandizadeh, Salar Zabihi Siabil, Amir Hossein Alavi, and Amir Hossein Gandomi. 2012. A computational intelligence-based approach for short-term traffic flow prediction. Expert Systems 29(2): 124–142.Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Jinzhi Liao
    • 1
  • Xiang Zhao
    • 1
    • 2
  • Jiuyang Tang
    • 1
    • 2
  • Chong Zhang
    • 1
    • 2
  • Mingke He
    • 1
    • 2
  1. 1.National University of Defense TechnologyChangshaChina
  2. 2.Collaborative Innovation Center of Geospatial Information TechnologyWuhanChina

Personalised recommendations