Journal of Guangdong University of Technology ›› 2008, Vol. 25 ›› Issue (4): 56-60.

• Comprehensive Studies • Previous Articles     Next Articles

An Improved Fast-ICA Algorithm Based on Fourth-Order Cumulant

  

  1. Department of Computer and Information Science,City College of Dongguan University of Technology,Dongguan 523106,China
  • Online:2008-03-01 Published:2008-03-01

HTML

PDF (PC)

2291

Abstract: Fast-ICA method is a popular good algorithm nowadays.Tt proposes a new independent component analysis algorithm which uses fourth-order cumulant as the optimized criterion,and improves Newton iteration method by analyzing batch processing fixed-point fast-ICA method.The validity and performance of the proposed algorithm are verified by extensive computer simulations.

Key words: blind signal separation； fourth-order cumulant； fast-ICA；

[1] 刘海林.  基于广义特征值的病态混叠盲源分离算法[J]. 电子学报. 2006(11)

[2] 刘海林,谢胜利.  非线性盲源分离的多目标进化算法[J]. 系统工程与电子技术. 2005(09)

[3] 张荣,薛国民.  修正的三次收敛的牛顿迭代法[J]. 大学数学. 2005(01)

[4] [瑞典]Germund Dahlquist 著,包雪松 译.数值方法[M]. 高等教育出版社, 1990

[5] Comon P.Independent component analysis. A new conceptSignal Processing . 1994

[6] S. Amari,A. Cichocki,and H. Yang."A new learning algorithm for blind signal separation,". Advances in Neural Information Processing Systems . 1996

[7] Howard Hua Yang,shun-ichi Amari.Adaptive online learning algorithms for blind separation, Maximum Etropy and Minimum Mutual information. Neural Computation . 1997

[8] Hyvarinen A,Oja Erkki.Independent component analysis:Algorithmand applications. Neural Networks . 2000

[9] Hyvarinen A,Oja E.A fast fixed-point algorithm for independent component analysis. Neural Computation . 1997
No related articles found!
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © 2017 Journal of Guangdong University of Technology
Add：729 East Dongfeng RD., Guangzhou PRC. Postcode: 510090
Tel：020-37626653,020-37626139,020-37626396
Email：xbzrb@gdut.edu.cn
Supported:Beijing Magtech