The use of deep learning combined with wavelet analysis in short-term passenger flow forecast of urban rail transit

Haiyong Yu; Lili Huang; Kang Chen

doi:10.1117/12.2620460

22 December 2021 The use of deep learning combined with wavelet analysis in short-term passenger flow forecast of urban rail transit

Haiyong Yu, Lili Huang, Kang Chen

Author Affiliations +

Proceedings Volume 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021); 1205824 (2021) https://doi.org/10.1117/12.2620460
Event: 5th International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 2021, Chongqing, China

Abstract

The wavelet ARIMA-RBF (Autoregressive Integrated Moving Average Model-Radial basis function) algorithm is proposed to improve the accuracy of the traditional short-term passenger flow forecast algorithm of urban rail transit. Wavelet analysis is used to extract and eliminate the noise in the short-term passenger flow data of urban rail transit. Then, ARIMA is adopted to model the previous short-term passenger flow data of urban rail transit and calculate the prediction results and prediction errors. Finally, the fitting result of prediction errors by RBF (Radial basis function) is added to the prediction results of ARIMA. The experimental results show that the prediction error of the designed model is the smallest for the short-term passenger flow prediction of urban rail transit. Although the prediction error on weekends is slightly higher than that on weekdays, the mean absolute percentage deviation of the model is only 3.05 %, which is better than ARIMA and RBF. The proposed algorithm provides certain data support for the application of wavelet analysis in short-term passenger flow forecast of urban rail transit.

Citation Download Citation

Haiyong Yu, Lili Huang, and Kang Chen "The use of deep learning combined with wavelet analysis in short-term passenger flow forecast of urban rail transit", Proc. SPIE 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 1205824 (22 December 2021); https://doi.org/10.1117/12.2620460

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available