Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (26): 212-214.DOI: 10.3778/j.issn.1002-8331.2010.26.066

• 工程与应用 • Previous Articles     Next Articles

Short-term traffic flow prediction method based on EMD and artificial neural network

LUO Xiang-long1,2,NIU Guo-hong3,PAN Ruo-yu4   

  1. 1.School of Information Engineering,Chang’an University,Xi’an 710064,China
    2.Institute of Wave and Information,Xi’an Jiaotong University,Xi’an 710049,China
    3.Xi’an Municipal Engineering Design & Research Institute Co.,Ltd.,Xi’an 710068,China
    4.School of Communication and Information Engineering,Xi’an Post & Telecommunication College,Xi’an 710064,China
  • Received:2009-02-20 Revised:2009-04-11 Online:2010-09-11 Published:2010-09-11
  • Contact: LUO Xiang-long

交通流量经验模态分解与神经网络短时预测方法

罗向龙1,2,牛国宏3,潘若禹4   

  1. 1.长安大学 信息工程学院,西安 710064
    2.西安交通大学 波动与信息研究所,西安 710049
    3.西安市政设计研究院有限公司,西安 710068
    4.西安邮电学院 通信与信息工程学院,西安 710064
  • 通讯作者: 罗向龙

Abstract: An approach to short-term traffic flow prediction based on Empirical Mode Decomposition(EMD) and artificial neural network is proposed.Firstly,the traffic flow is decomposed into different modes by EMD.Then,these different modes are predicted by appropriate artificial neural networks,respectively.Finally,the traffic flow is obtained by adding up all predictive value.This method is used to predict traffic flow using I-800 measurement data,the results show that the proposed method has high predictive accuracy,and better than the outcome of direct using neural network prediction.

Key words: short-term traffic flow, Empirical Mode Decomposition(EMD), artificial neural network, prediction

摘要: 基于经验模态分解(EMD)和神经网络,提出了一种短时交通流量预测方法。通过EMD分解把交通流量分解成不同的模态,利用神经网络对分解后的各分量进行预测,再将预测值累加得到最终的预测结果。利用EMD与神经网络模型对I-800数据库实测交通流量数据进行预测,结果表明该方法具有很高的预测精度,明显优于直接采用神经网络的预测结果。

关键词: 短时交通流量, 经验模态分解, 人工神经网络, 预测

CLC Number: