Singular Point Probability Improve LSTM Network Performance for Long-term Traffic Flow Prediction

  • Boyi Liu
  • Jieren Cheng
  • Kuanqi Cai
  • Pengchao Shi
  • Xiangyan Tang
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 768)


Traffic flow forecasting is the key in intelligent transportation system, but the current traffic flow forecasting method has low accuracy and poor stability in the long-term period. For this reason, an improved LSTM Network is proposed. Firstly, the concept and calculation method of time singularity ratio of traffic data stream is proposed to predict long-term traffic flow. The singular point probability LSTM (SPP-LSTM) is presented. Namely, the algorithm discard the LSTM network unit form the network temporarily according to the singular point probability during the training process of the depth learning network, so as to get SPP-LSTM model. Finally, the paper amends the SPP-LSTM by ARIMA to realize the accurate prediction of 24-hour traffic flow data. Theoretical analysis and experimental results show that the SPP-LSTM has a high accuracy rate, stability and wide application prospect in the long-time traffic flow forecast with hourly period.


LSTM Singular point Depth learning Traffic flow forecasting 



This work was supported by the National Natural Science Foundation of China (Project no. 61762033, 61363071), The National Natural Science Foundation of Hainan (Project no. 617048), Hainan University Doctor Start Fund Project (Project no. kyqd1328). Hainan University Youth Fund Project (Project no. qnjj1444). State Key Laboratory of Marine Resource Utilization in the South China Sea, Hainan University. College of Information Science and Technology, Hainan University. Nanjing University of Information Science and Technology (NUIST), A Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions, Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology.


  1. 1.
    Alam, M., Ferreira, J., Fonseca, J.: Introduction to intelligent transportation systems. In: Intelligent Transportation Systems, pp. 1–17. Springer, Heidelberg (2016)Google Scholar
  2. 2.
    Moral-Muñoz, J.A., Cobo, M.J., Chiclana, F., et al.: Analyzing highly cited papers in Intelligent transportation systems. IEEE Trans. Intell. Transp. Syst. 17(4), 993–1001 (2016)CrossRefGoogle Scholar
  3. 3.
    Davis, G.A., Nihan, N.L.: Nonparametric regression and short-term freeway traffic forecasting. J. Transp. Eng. 117(2), 178–188 (1991)CrossRefGoogle Scholar
  4. 4.
    Dougherty, M.: A review of neural networks applied to transport. Transp. Res. Part C Emerg. Technol. 3(4), 247–260 (1995)CrossRefGoogle Scholar
  5. 5.
    Yanyan, X., Zhaixi, K.X., et al.: Short-term prediction method of freeway traffic flow. J. Traffic Transp. Eng. 2, 114–119 (2013)Google Scholar
  6. 6.
    Liu, F., Liu, B., Sun, C., et al.: Deep belief network-based approaches for link prediction in signed social networks. Entropy 17(4), 2140–2169 (2015)CrossRefGoogle Scholar
  7. 7.
    Bai, C., Peng, Z.R., Lu, Q.C., et al.: Dynamic bus travel time prediction models on road with multiple bus routes. Comput. Intell. Neurosci. 2015, 63 (2015)CrossRefGoogle Scholar
  8. 8.
    Yanchong, C., Darong, H., Ling, Z.: A short-term traffic flow prediction method based on wavelet analysis and neural network. In: 2016 Chinese Control and Decision Conference (CCDC), pp. 7030–1034. IEEE (2016)Google Scholar
  9. 9.
    Moretti, F., Pizzuti, S., Panzieri, S., et al.: Urban traffic flow forecasting through statistical and neural network bagging ensemble hybrid modeling. Neurocomputing 167, 3–7 (2015)CrossRefGoogle Scholar
  10. 10.
    Tian, Y., Pan, L.: Predicting short-term traffic flow by long short-term memory recurrent neural network. In: 2015 IEEE International Conference on Smart City/SocialCom/SustainCom (SmartCity), pp. 153–158. IEEE (2015)Google Scholar
  11. 11.
    Butt, M.: Selection of forecast model for consumption (four sectors) and transmission (two Pipelines) of natural gas in Punjab (Pakistan) based on ARIMA model. Int. J. Adv. Stat. Probab. 3(1), 115–125 (2015)CrossRefGoogle Scholar
  12. 12.
    Zhu, X., Sobhani, P., Guo, H.: Long short-term memory over recursive structures. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 1604–1612 (2015)Google Scholar
  13. 13.
    Rakkiyappan, R., Chandrasekar, A., Cao, J.: Passivity and passification of memristor-based recurrent neural networks with additive time-varying delays. IEEE Trans. Neural Netw. Learn. Syst. 26(9), 2043–2057 (2015)MathSciNetCrossRefGoogle Scholar
  14. 14.
    LukošEvičIus, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127–149 (2009)CrossRefMATHGoogle Scholar
  15. 15.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
  16. 16.
    Liang, M., Hu, X.: Recurrent convolutional neural network for object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3367–3375 (2015)Google Scholar
  17. 17.
    Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: ICML (3), vol. 28, pp. 1310–1318 (2013)Google Scholar
  18. 18.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  19. 19.
    Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12(10), 2451–2471 (2000)CrossRefGoogle Scholar
  20. 20.
    Yao, K., Cohn, T., Vylomova, K., et al.: Depth-gated recurrent neural networks (2015)Google Scholar
  21. 21.
    Chung, J., Gulcehre, C., Cho, K.H., et al.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)
  22. 22.
    Srivastava, N., Hinton, G.E., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetMATHGoogle Scholar
  23. 23.
    Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv preprint arXiv:1409.2329 (2014)
  24. 24.
    Bailey, D.H., Borwein, J.M., de Prado, M.L., et al.: Pseudomathematics and financial charlatanism: the effects of backtest over fitting on out-of-sample performance. Not. AMS 61(5), 458–471 (2014)MATHGoogle Scholar
  25. 25.
    Awad, A.I., Baba, K.: Singular point detection for efficient fingerprint classification. Int. J. New Comput. Architectures Appl. (IJNCAA) 2(1), 1–7 (2012)Google Scholar
  26. 26.
    Pati, J., Shukla, K.K.: A comparison of ARIMA, neural network and a hybrid technique for Debian bug number prediction. In: 2014 International Conference on Computer and Communication Technology (ICCCT), pp. 47–53. IEEE (2014)Google Scholar
  27. 27.
    Traffic data program of British Columbia. Public Traffic Data [EB/OL].
  28. 28.
    Chen, J., Wang, Y., Gu, C., et al.: Enhancement of the mechanical properties of basalt fiber-wood-plastic composites via maleic anhydride grafted high-density polyethylene (MAPE) addition. Materials 6(6), 2483–2496 (2013)CrossRefGoogle Scholar
  29. 29.
    Dunleavy, K., Pittaluga, S., Maeda, L.S., et al.: Dose-adjusted EPOCH-rituximab therapy in primary mediastinal B-cell lymphoma. N. Engl. J. Med. 368(15), 1408–1416 (2013)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2017

Authors and Affiliations

  • Boyi Liu
    • 1
    • 4
  • Jieren Cheng
    • 1
    • 2
  • Kuanqi Cai
    • 3
  • Pengchao Shi
    • 3
  • Xiangyan Tang
    • 1
  1. 1.College of Information Science and TechnologyHainan UniversityHaikouChina
  2. 2.State Key Laboratory of Marine Resource Utilization in South China SeaHaikouChina
  3. 3.Mechanical and Electrical Engineering CollegeHainan UniversityHaikouChina
  4. 4.University of Chinese Academy of SciencesBeijingChina

Personalised recommendations