Short-term Passenger Flow Forecasting Based on Phase Space Reconstruction and LSTM

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 482)

Abstract

In this paper, the chaotic characteristics of the railway passenger flow are considered, and the PSR-LSTM (Phase Space Reconstruction-Long Short Term Memory) model is proposed by the phase space reconstruction method to recover the hidden trajectory in the passenger flow. First, this model uses C-C method to calculate the time delay and embedding dimension, and carry out phase space reconstruction. Afterwards, the LSTM neural network is used to predict short-term passenger flow. In the experimental part, it is proved that the passenger flow data with chaotic characteristics are reconstructed by phase space processing can get more accurate predictions. Then, in order to further verify the accuracy of the model, this model is compared with the BP neural network model and the SVR model, which is also subjected to phase space reconstruction processing. The experimental results show that the model has high accuracy.

Keywords

Chaotic characteristics Phase space reconstruction C-C method LSTM 

Notes

Acknowledgements

This work is supported by Railway Corporation Research Project (NO. 2016X005-B). Jiansheng Zhu is the corresponding author.

References

  1. 1.
    Huang Z, Feng S (2014) Grey forecasting model in the application of railway passenger flow prediction research. Technol Econ Areas Commun 16(1):57–60 (in Chinese)Google Scholar
  2. 2.
    Zhang B (2014) Study on short-term forecast of Shanghai-Nanjing intercity railway passenger flow. Chin Railways 2014(9):29–33 (in Chinese)Google Scholar
  3. 3.
    Dong S (2013) The research of short-time passenger flow forecasting based on improved BP neural network in urban rail transit. Beijing Jiaotong University (in Chinese)Google Scholar
  4. 4.
    Deng J, Kong F, Chen X (2008) Passenger flow forecast of urban rail transit based on support vector regression. J Chongqing Univ Sci Technol (Nat Sci Edn) 10(3):147–149 (in Chinese)Google Scholar
  5. 5.
    Takens F (2006) Determining strange attractors in turbulence. Lecture Notes Math 2006:366–381Google Scholar
  6. 6.
    Ma H, Li X, Wang G, Han C et al (2004) Selection of embedding dimension and delay time in phase space reconstruction. J Xi’an Jiaotong Univ 38(4):335–338 (in Chinese)Google Scholar
  7. 7.
    Kugiumtzis D (1998) State space reconstruction parameters in the analysis of chaotic time series—the role of the time window length. Physica D-Nonlinear Phenomena 95(1):13–28MathSciNetCrossRefMATHGoogle Scholar
  8. 8.
    Kim H, Eykholt R, Salas J (1999) Nonlinear dynamics, delay times, and embedding windows. Elsevier Science Publishers B. VGoogle Scholar
  9. 9.
    Broock W, Scheinkman J, Dechert W et al (1996) A test for independence based on the correlation dimension. Econometric Rev 15(3):197–235MathSciNetCrossRefMATHGoogle Scholar
  10. 10.
    Hochreiter S, Schmidhuber J (2012) Long short-term memory. Neural Comput 9(8):1735–1780CrossRefGoogle Scholar
  11. 11.
    Rosenstein M, Collins J, Luca C (1993) A practical method for calculating largest Lyapunov exponents from small data sets. Physica D-Nonlinear Phenomena 65(1–2):117–134MathSciNetCrossRefMATHGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.China Academy of Railway SciencesBeijingPeople’s Republic of China

Personalised recommendations