Advertisement

Prediction Modeling of Railway Short-Term Passenger Flow Based on Random Forest Regression

  • Li-hui Li
  • Jian-sheng Zhu
  • Xing-hua Shan
  • Xia Zhang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 503)

Abstract

The predication of short-term passenger flow plays a very important role for improving service quality and revenue High-speed railway operation. To precisely predict the short-term passenger flow, impact factors need to be deeply analyzed and a reasonable predication model is required. This chapter analyzed the impact factors for short-term passenger flow and proposed a prediction model based on random forest regression. With the passenger flow data between Beijing and Shanghai from July to August in 2015, a predication model is trained and reached 91% accuracy for daily passenger flow. Finally, the importance of each impact factor has been analyzed, and this information can also help high-speed railway operation. It is shown that the prediction model based on random forest regression for predicting short-term passenger flow can help to improve the high-speed railway operation.

Keywords

High-speed railway Random forest regression Prediction Short-term flow 

References

  1. 1.
    Hao J, Cui Y, Han J (2015) Prediction of the railway passenger volume based on the SARIMA model. Math Pract Theory 45(18):95–104Google Scholar
  2. 2.
    Wang Y, Xu R (2010) Forecast of short-term metro passenger flow based on the periodically varying characteristics. Urban Mass Transit 1:46–49Google Scholar
  3. 3.
    Luo Y-J, Liu J, Sun X et al (2015) Regression model for daily passenger volume of high-speed railway line under capacity constraint. J Cent S Univ 22:3666–3676CrossRefGoogle Scholar
  4. 4.
    Liu L (2016) Research of railway passenger volume forecast model based on PCA-BP neural network. Theory and Policy 38(6):43–47Google Scholar
  5. 5.
    Li X, Lv X, Liu J (2011) Forecast of railway short-term passenger flow based on RBF neural network. Railway Transport and Econ 33(6):86–89Google Scholar
  6. 6.
    Xu J, Wang D, Li Cet al (2014) Short_term passenger flow forecasting for urban rail transit based on dynamic feedback neural network. Mod Trans Technol 11(5):43–46Google Scholar
  7. 7.
    Wang L, Ma C ,Zhou X et al (2015) Estimation of wheat leaf SPAD value using RF algorithmic model and remote sensing data. Trans Chin Soc Agric Mach 46(1):259–265Google Scholar
  8. 8.
    Zhao B, Tan Z, Deng K (2016) Calculation of the tangent of major influence angle based on random forest regression model. Met Mine 3:172–175Google Scholar
  9. 9.
    Sun X, Shu Q, Ou G et al (2015) Remote sensing estimation of the biomass of artificial simao pine forest based on random forest regression. For Resour Manage 1:71–76Google Scholar
  10. 10.
    Song K, Tan Z, Deng K et al (2016) Prediction of the horizontal factor based on random forest regression model. Met Mine 6:180–184Google Scholar
  11. 11.
    Liu R, Mao J, Li Y (2016) Facial landmarks location based on random forest regression. J Electro Meas Instrum 30(5):684–693Google Scholar
  12. 12.
    Hou Y, Yang K, Li K (2015) Network reconstruction with random forest regression and its application. Chin J Health Stat 32(4):558–561Google Scholar
  13. 13.
    Nan J (2016) The analysis of influencing factor about railway passenger forecast. Transport Dev Reform Top 38(2):35–40Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Li-hui Li
    • 1
    • 2
  • Jian-sheng Zhu
    • 2
  • Xing-hua Shan
    • 2
  • Xia Zhang
    • 2
  1. 1.Postgraduate DepartmentChina Academy of Railway SciencesBeijingChina
  2. 2.Institute of Computing TechnologyChina Academy of Railway SciencesBeijingChina

Personalised recommendations