ICA method with global optimal property based on wavelet transformation

BI Xue1; CHEN Xiang-dong2; LI Pai2

doi:10.13873/j.1000-97872007.08.002

Chinese

您当前的位置：

首页 >

文章列表页 >

ICA method with global optimal property based on wavelet transformation

更新时间：2025-09-11

- ICA method with global optimal property based on wavelet transformation
- Issue 8, Pages: 102-104+107(2007)
- 作者机构：
  
  1. 西华大学网络中心
  2. 西南交通大学信息科学与技术学院
  3. 西南交通大学信息科学与技术学院,四川,成都,610039
  4. ,四川,成都,610031
- 作者简介：
- 基金信息：
- DOI：10.13873/j.1000-97872007.08.002
  CLC： TN911.7
- Published：2007
- 稿件说明：
移动端阅览
[1]毕雪,陈向东,李湃.基于小波变换的全局最优独立分量分离算法[J].传感器与微系统,2007(08):102-104+107.

BI Xue1, CHEN Xiang-dong2, LI Pai2. ICA method with global optimal property based on wavelet transformation[J]. 2007, (8): 102-104+107.
[1]毕雪,陈向东,李湃.基于小波变换的全局最优独立分量分离算法[J].传感器与微系统,2007(08):102-104+107. DOI： 10.13873/j.1000-97872007.08.002.

BI Xue1, CHEN Xiang-dong2, LI Pai2. ICA method with global optimal property based on wavelet transformation[J]. 2007, (8): 102-104+107. DOI： 10.13873/j.1000-97872007.08.002.

摘要

提出一种利用小波变换的低频系数作为滑动因子的盲源分离算法

通过建立以分母作为预测误差的信噪比目标函数

优化过程导致广义特征值求解

广义特征值构成的特征向量就是要求的分离矩阵

求解过程无需迭代。通过实验证明:计算量小

分离精度高

相似系数分别到达了1和0.9998

同时

可根据需要灵活选择小波基。

Abstract

A kind of independent component analysis（ICA） method with global optimal property is proposed

which is based on low frequency part of wavelet transformation as moving factors and built a signal-to-noise ratio objective function on predictability error of denominator.Optimizing leads to get generalized eigenvalue and eigenvector which is the demanding separable matrix.Iteration is not necessary.The experiments show that computation is small and separable precision is higher

which can respectively get resembled coefficients of 1 and 0.999 8.Meanwhile it can choose wavelet basis flexibly based on different requirement.

关键词

Keywords

references

Blind Source Separation Using Temporal Predictability [J] . James V. Stone. Neural Computation . 2001 (7)

Stability Analysis of Learning Algorithms for Blind Source Separation [J] . Shun-ichi Amari,Tian-ping Chen,Andrzej Cichocki. Neural Networks . 1997 (8)

An Information-Maximization Approach to Blind Separation and Blind Deconvolution [J] . Anthony J. Bell,Terrence J. Sejnowski. Neural Computation . 1995 (6)

Views

156

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

PCA-ICA integrated technique for noise suppression of pulsed remote field eddy current inspection

A new image denoising method for monitoring in intense radioactive environment

Generation and denoising of the vibration noise during shock wave test

Application of kernel-ICA in monitor of phase error of current sensor

Study on electronic-nose recognition method with independent component analysis and back-propagation neural network

Related Author

LI Yi-li

YAN Bei

CHEN Zhen-mao

LI Yong

LIU Xiang-biao

XIE Xing-zhe

ZHANG Hua

SANG Rui-juan

Related Institution

Research Centre for Inspection and Evaluation of Nuclear Structural Integrity,State Key Laboratory for Strength and Vibration of Mechanical Structures,School of Aerospace,Xi’an Jiaotong University

Key Laboratory of Robotics,School of Information Engineering,Southwest University of Science and Technology

Key Laboratory of Instrumentation Science & Dynamic Measurement,Ministry of Education, North University of China

Institute of Semiconductors,Chinese Academy of Sciences

School of Information Science and Technology,Southwest Jiaotong University

⁰