A Short-Term Traffic Flow Prediction Method Based on Long Short-Term Memory Network

  • Yusheng Ci
  • Gaoqun XiuEmail author
  • Lina Wu
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 503)


In order to achieve the higher accuracy of the short-term traffic flow prediction, this paper proposed a prediction method based on the Long Short-Term Memory Network (LSTM) model. First, the original traffic flow data is processed by difference and scaling, so the trend is removed. And then the LSTM model is proposed to learn internal characteristic of the traffic flow and make the forecast. Comparing LSTM method with the traditional prediction model (back propagation neural network, BPNN), the experiment result shows that the proposed traffic flow prediction method has the better learnability for the short-term traffic flow and achieves higher accuracy for the prediction.


Short-term traffic flow prediction Deep learning LSTM 



This work was financially supported by the Grants from the MOE Project of Humanities and Social Sciences (16YJCZH114) and the Soft Science Project of Ministry of Housing and Urban-Rural Development of China (2016-R2-048).


  1. 1.
    Levin M, Tsao YD (1980) On forecasting freeway occupancies and volumes. Transp Res Rec 773Google Scholar
  2. 2.
    Williams BM, Hoel LA (2003) Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. J Transp Eng 129(6):664–672CrossRefGoogle Scholar
  3. 3.
    Park D, Rilett LR, Han G (1999) Spectral basis neural networks for real-time travel time forecasting. J Transp Eng 125(125):515–523CrossRefGoogle Scholar
  4. 4.
    Huang W, Song G, Hong H et al (2014) Deep architecture for traffic flow prediction: deep belief networks with multitask learning. IEEE Trans Intell Transp Syst 15(5):2191–2201CrossRefGoogle Scholar
  5. 5.
    Kuremoto T, Kimura S, Kobayashi K et al (2014) Time series forecasting using a deep belief network with restricted Boltzmann machines. Neurocomputing 137:47–56CrossRefGoogle Scholar
  6. 6.
    Wenhao H, Guojie S, Haikun H et al (2014) Deep architecture for traffic flow prediction: deep belief networks with multitask learning. IEEE Trans Intell Transp Syst 15(5):2191–2201CrossRefGoogle Scholar
  7. 7.
    Fu R, Zhang Z, Li L (2017) Using LSTM and GRU neural network methods for traffic flow prediction. Chin Assoc Autom, IEEEGoogle Scholar
  8. 8.
    Duan Y, Lv Y, Wang FY (2016) Travel time prediction with LSTM neural network. IEEE Int Conf Intell Transp Syst, IEEE, 1–4 Nov 2016Google Scholar
  9. 9.
    Zhao Z, Chen W, Wu X et al (2017) LSTM network: a deep learning approach for short-term traffic forecast. IET Intel Transp Syst 11(2):68–75CrossRefGoogle Scholar
  10. 10.
    LyuYisheng DuanYanjie, Wenwen Kang et al (2014) Traffic flow prediction with big data: a deep learning approach. IEEE Trans Intell Transp Syst 16(2):865–873Google Scholar
  11. 11.
    Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780CrossRefGoogle Scholar
  12. 12.
    Vlahogianni EI, Karlaftis MG, Golias JC (2005) Optimized and meta-optimized neural networks for short-term traffic flow prediction: a genetic approach. Transp Res Part C: Emerg Technol 13(3):211–234CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Transportation Science and EngineeringHarbin Institute of TechnologyHarbinChina
  2. 2.College of Automobile and Traffic Engineering, Heilongjiang Institute of TechnologyHarbinChina

Personalised recommendations