A Multi-stage FastICA Algorithm to Remove Error Propagation

Yao Jun-liang; Yang Xiao-niu; Li Jian-dong; Zhang Yan; Han Wei-jia

doi:10.3724/SP.J.1146.2008.01546

Volume 31 Issue 11

Dec. 2010

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2009 > 31(11): 2643-2648

Yao Jun-liang, Yang Xiao-niu, Li Jian-dong, Zhang Yan, Han Wei-jia. A Multi-stage FastICA Algorithm to Remove Error Propagation[J]. Journal of Electronics & Information Technology, 2009, 31(11): 2643-2648. doi: 10.3724/SP.J.1146.2008.01546

Citation:

Yao Jun-liang, Yang Xiao-niu, Li Jian-dong, Zhang Yan, Han Wei-jia. A Multi-stage FastICA Algorithm to Remove Error Propagation[J]. Journal of Electronics & Information Technology, 2009, 31(11): 2643-2648. doi: 10.3724/SP.J.1146.2008.01546

Citation:

PDF( 299 KB)

A Multi-stage FastICA Algorithm to Remove Error Propagation

doi: 10.3724/SP.J.1146.2008.01546

Received Date: 2008-11-25
Rev Recd Date: 2009-04-27
Publish Date: 2009-11-19

Abstract

Abstract

This paper proposes a Multi-Stage FastICA Algorithm(MSFICA) to solve the problem of error propagation in the traditional successive FastICA algorithm. MSFICA removes the error propagation effect through a two-stage structure. In order to reduce the computational complexity, a dimension decrease method is used to get the initial values of separating vectors in the first stage. In the second stage, the algorithm uses the initial values and whitened observed signals to separate original signals, and does not need orthogonal projection. Simulation results indicate that the proposed algorithm can eliminate error propagation successfully and achieve better performance than existing parallel FastICA algorithm at the expense of a slightly increased complexity.

FullText(HTML)

References(1)

References

Li H L and Adali T. A class of complex ICA algorithms basedon the kurtosis cost function. IEEE Transactions on SignalProcessing, 2008, 19(3): 408-420.[2]Lu W and Rajapakse J C. ICA with reference[J].Neurocomputing.2006, 69(16-18):2244-2257[3]张瑾, 方勇. 基于分块Contourlet 变换的图像独立分量分析方法[J].电子与信息学报.2007, 29(8):1813-1816浏览[4]付卫红, 杨小牛. 基于盲源分离的CDMA 多用户检测与伪码估计. 电子学报, 2008, 36(7): 1319-1323.Fu W H and Yang X N. The multi-User detection and chipsequence estimation for CDMA system based on the blindsource separation. Acta Electronica Sinica, 2008, 36(7):1319-1323.[5]Hyvarinen A and Bingham E. A fast fixed-point algorithm forindependent component analysis of complex valued signals.Journal of Neural Systems, 2000, 10(1): 1-8.[6]张贤达. 矩阵分析与应用. 北京：清华大学出版社, 2004, 第10章.Zhang X D. Matrix Analysis and Applications. Beijing:Tsinghua University Press, 2004, Chapter 10.[7]Cardoso J F and Laheld B H. Equivariant adaptive sourceseparation[J].IEEE Transactions on Signal Processing.1996,44(12):3017-3030[8]Chi C Y. Turbo source extraction algorithm andnoncancellation source separation algorithms by kurtosismaximization[J].IEEE Transactions on Signal Processing.2006,54(8):2929-2942

Relative Articles

Supplements(0)

Cited By

Proportional views