Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach

Syuan Yi Chen, Wei Yao Chou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

An empirical mode decomposition based recurrent Hermite neural network (ERHNN) prediction model is proposed to predict short-term traffic flow in this study. First, a recurrent Hermite neural network (RHNN) prediction model with different orthonormal Hermite polynomial basis functions (OHPBFs) as activation functions is introduced. Then, to further mitigate the influence of noise and improve the accuracy of prediction, an empirical mode decomposition (EMD) method is derived to decompose the original short-term traffic flow data into several intrinsic mode functions (IMFs) and adopt them as the inputs for the RHNNs. Therefore, an ERHNN prediction model, which comprises good predictive ability for the nonlinear and non-stationary signals through the combination of the merits of OHPBFs, EMD and EHNN, is proposed to predict short-term traffic flow more effectively. The validity of the ERHNN prediction model is verified using all day short-term traffic flow data at high way I-80W in California. Simulation results demonstrate that the proposed ERHNN prediction model is with superior performance compared with the pure recurrent neural network (RNN) and RHNN prediction models.

Original languageEnglish
Title of host publication2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012
Pages1821-1826
Number of pages6
DOIs
Publication statusPublished - 2012 Dec 21
Event2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012 - Anchorage, AK, United States
Duration: 2012 Sep 162012 Sep 19

Publication series

NameIEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

Other

Other2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012
CountryUnited States
CityAnchorage, AK
Period12/9/1612/9/19

Fingerprint

Recurrent neural networks
Decomposition
Polynomials
Chemical activation

ASJC Scopus subject areas

  • Automotive Engineering
  • Mechanical Engineering
  • Computer Science Applications

Cite this

Chen, S. Y., & Chou, W. Y. (2012). Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach. In 2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012 (pp. 1821-1826). [6338665] (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). https://doi.org/10.1109/ITSC.2012.6338665

Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach. / Chen, Syuan Yi; Chou, Wei Yao.

2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012. 2012. p. 1821-1826 6338665 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, SY & Chou, WY 2012, Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach. in 2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012., 6338665, IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, pp. 1821-1826, 2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012, Anchorage, AK, United States, 12/9/16. https://doi.org/10.1109/ITSC.2012.6338665
Chen SY, Chou WY. Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach. In 2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012. 2012. p. 1821-1826. 6338665. (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). https://doi.org/10.1109/ITSC.2012.6338665
Chen, Syuan Yi ; Chou, Wei Yao. / Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach. 2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012. 2012. pp. 1821-1826 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).
@inproceedings{edad7cd1c70b4b5bba456fbc203c28aa,
title = "Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach",
abstract = "An empirical mode decomposition based recurrent Hermite neural network (ERHNN) prediction model is proposed to predict short-term traffic flow in this study. First, a recurrent Hermite neural network (RHNN) prediction model with different orthonormal Hermite polynomial basis functions (OHPBFs) as activation functions is introduced. Then, to further mitigate the influence of noise and improve the accuracy of prediction, an empirical mode decomposition (EMD) method is derived to decompose the original short-term traffic flow data into several intrinsic mode functions (IMFs) and adopt them as the inputs for the RHNNs. Therefore, an ERHNN prediction model, which comprises good predictive ability for the nonlinear and non-stationary signals through the combination of the merits of OHPBFs, EMD and EHNN, is proposed to predict short-term traffic flow more effectively. The validity of the ERHNN prediction model is verified using all day short-term traffic flow data at high way I-80W in California. Simulation results demonstrate that the proposed ERHNN prediction model is with superior performance compared with the pure recurrent neural network (RNN) and RHNN prediction models.",
author = "Chen, {Syuan Yi} and Chou, {Wei Yao}",
year = "2012",
month = "12",
day = "21",
doi = "10.1109/ITSC.2012.6338665",
language = "English",
isbn = "9781467330640",
series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",
pages = "1821--1826",
booktitle = "2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012",

}

TY - GEN

T1 - Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach

AU - Chen, Syuan Yi

AU - Chou, Wei Yao

PY - 2012/12/21

Y1 - 2012/12/21

N2 - An empirical mode decomposition based recurrent Hermite neural network (ERHNN) prediction model is proposed to predict short-term traffic flow in this study. First, a recurrent Hermite neural network (RHNN) prediction model with different orthonormal Hermite polynomial basis functions (OHPBFs) as activation functions is introduced. Then, to further mitigate the influence of noise and improve the accuracy of prediction, an empirical mode decomposition (EMD) method is derived to decompose the original short-term traffic flow data into several intrinsic mode functions (IMFs) and adopt them as the inputs for the RHNNs. Therefore, an ERHNN prediction model, which comprises good predictive ability for the nonlinear and non-stationary signals through the combination of the merits of OHPBFs, EMD and EHNN, is proposed to predict short-term traffic flow more effectively. The validity of the ERHNN prediction model is verified using all day short-term traffic flow data at high way I-80W in California. Simulation results demonstrate that the proposed ERHNN prediction model is with superior performance compared with the pure recurrent neural network (RNN) and RHNN prediction models.

AB - An empirical mode decomposition based recurrent Hermite neural network (ERHNN) prediction model is proposed to predict short-term traffic flow in this study. First, a recurrent Hermite neural network (RHNN) prediction model with different orthonormal Hermite polynomial basis functions (OHPBFs) as activation functions is introduced. Then, to further mitigate the influence of noise and improve the accuracy of prediction, an empirical mode decomposition (EMD) method is derived to decompose the original short-term traffic flow data into several intrinsic mode functions (IMFs) and adopt them as the inputs for the RHNNs. Therefore, an ERHNN prediction model, which comprises good predictive ability for the nonlinear and non-stationary signals through the combination of the merits of OHPBFs, EMD and EHNN, is proposed to predict short-term traffic flow more effectively. The validity of the ERHNN prediction model is verified using all day short-term traffic flow data at high way I-80W in California. Simulation results demonstrate that the proposed ERHNN prediction model is with superior performance compared with the pure recurrent neural network (RNN) and RHNN prediction models.

UR - http://www.scopus.com/inward/record.url?scp=84871216899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871216899&partnerID=8YFLogxK

U2 - 10.1109/ITSC.2012.6338665

DO - 10.1109/ITSC.2012.6338665

M3 - Conference contribution

AN - SCOPUS:84871216899

SN - 9781467330640

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 1821

EP - 1826

BT - 2012 15th International IEEE Conference on Intelligent Transportation Systems, ITSC 2012

ER -