点击次数：

论文类型：期刊论文

发表时间：2009-08-01

发表刊物：EXPERT SYSTEMS WITH APPLICATIONS

收录刊物：SCIE、EI

卷号：36

期号：6

页面范围：10060-10067

ISSN号：0957-4174

关键字：Dual-wavelet; Spatial correlation; Singular spectrum analysis; Chaotic signals; Noise reduction

摘要：In this paper, an effective noise reduction method is proposed to remove Gaussian noise embedded in chaotic signals. The proposed method has two major steps: an optimal choice of wavelet decomposition scales and an estimation of the wavelet coefficients; the former is determined by the noise residual ratio based on dual-wavelet, whereas the latter is analyzed combining with the singular spectrum analysis and the spatial correlation theory. The chaotic signals generated by Lorenz model as well as the observed monthly series of sunspots are, respectively, applied for simulation analysis. the experimental results show that the performance of the proposed method is Superior to that of other methods. (C) 2009 Elsevier Ltd. All rights reserved.