经验模态分解方法中端点问题的处理

计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (8): 27-30.

经验模态分解方法中端点问题的处理

刘慧婷^1,2,倪志伟¹,李建洋¹

1.合肥工业大学计算机网络所，合肥 230009
2.安徽大学计算机科学与技术学院，合肥 230039

收稿日期:2007-11-13 修回日期:2007-12-25 出版日期:2008-03-11 发布日期:2008-03-11
通讯作者: 刘慧婷

Endpoint-processing technique in empirical mode decomposition method

LIU Hui-ting^1,2,NI Zhi-wei¹,LI Jian-yang¹

1.Institute of Computer Network System，Hefei University of Technology，Hefei 230009，China
2.School of Computer Science and Technology，Anhui University，Hefei 230039，China

Received:2007-11-13 Revised:2007-12-25 Online:2008-03-11 Published:2008-03-11
Contact: LIU Hui-ting

摘要/Abstract

摘要： 经验模态分解方法可以有效提取非线性非稳定信号的瞬时特征，但是在利用样条插值获得信号上、下包络过程中存在着棘手的端点问题。有文献提出利用线性神经网络对信号进行延拓的方法，来解决经验模态分解方法中存在的端点问题。提出利用BP和RBF网络对信号进行延拓的方法解决该问题；并利用实验对三种网络的延拓效果进行比较，证明了RBF神经网络的有效性。

Abstract: The empirical mode decomposition method can extract instantaneous characteristics of non-linear and non-stationary signals effectively.But there is an involved end issue in the course of getting two envelops of the data using spline interpolation.A literature has made use of linear neural network to solve endpoint problems of empirical mode decomposition method.This paper proposes the use of BP and RBF network to solve the problems.Experiments are used to compare extension results of the three networks，and prove that RBF neural network is more effective.

刘慧婷^1,2,倪志伟¹,李建洋¹. 经验模态分解方法中端点问题的处理[J]. 计算机工程与应用, 2008, 44(8): 27-30.

LIU Hui-ting^1,2,NI Zhi-wei¹,LI Jian-yang¹. Endpoint-processing technique in empirical mode decomposition method[J]. Computer Engineering and Applications, 2008, 44(8): 27-30.