全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
电子学报  2012 

基于ICA的盲信号分离正定性检验方法

DOI: 10.3969/j.issn.0372-2112.2012.11.025, PP. 2303-2308

Keywords: 盲信号分离,欠定,正定性,独立分量分析,基向量稳定性

Full-Text   Cite this paper   Add to My Lib

Abstract:

盲信号分离中,判断观测信号个数与实际信源个数的关系对于信号分离算法的选择和算法效果的评估非常重要,但目前还缺乏有效的方法对正定和欠定情况进行区分性检验.针对这一问题,本文提出两种检验方法.第一种方法通过分析整个数据序列ICA分解输出分量之间的独立性来实现.理论分析表明,欠定条件下ICA分解输出分量之间必然不具有独立性,而正定条件下,只要源信号满足独立的前提假设,ICA分解输出分量之间可以相互独立.第二种方法中,我们对数据序列不同位置添加等长时间窗,根据ICA分解基向量的稳定性来检验正定性.理论分析表明,正定条件下不同窗口数据ICA分解的基向量都收敛到混合阵的基向量上,而欠定条件下,分解得到的基向量随不同时窗内源信号分布的变化而改变.本文通过仿真实验,证明了这两种方法的可行性.

References

[1]  J Herault,C Jutten.Blind separation of sources,Partl:An adaptive algorithm based on neuromimetic[J].Signal Proeessing,1991,24(1):1-10.
[2]  Ye Jimin,Zhu Xiaolong,Zhang Xianda.Adaptive blind separation with an unknown number of sources [J].Neural Computation,2004,16(8):1641-1660.
[3]  Ishibashi T,Inoue K,Gotanda H,et al.Studies on estimation of the sources number in blind source separation problems .SICE-ICASE 2006 .Bexco,Korea:IEEE,2006.5169-5174.
[4]  Wax M,Kailath T.Detection of signals by information theoretic criteria [J].IEEE Trans Acoustics Speech and Signal Processing,1985,33(2):387-392.
[5]  谢胜利,孙功宪,肖明,等.欠定和非完全稀疏性的盲信号提取[J].电子学报,2010,38(5):1028-1031. Xie Shengli,Sun Gongxian,Xiao Ming,et al.Underdetermined and incompletely sparse blind signal extraction[J].Acta Electronica Sinica,2010,38(5):1028-1031.(in Chinese)
[6]  SAAB R,YILMAZ ?,MCKEOWN,et al.Underdetermined anechoic blind source separation via lq-basis-pursuit with q<1[J].IEEE Transactions on Signal Processing.2007,55(8):4004-4017.
[7]  Gai Kun,Shi Zhenwei,Zhang Changshui.Blind separation of superimposed moving images using image statistics[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34,1.
[8]  陆凤波,黄知涛,彭耿.基于时频分布的欠定混叠盲分离[J].电子学报,2011,39(9):2067-2072. Lu Fengbo,Huang Zhitao,et al.Underdetermined blind source separation (BSS):A time-frequency approach[J].Acta Electronica Sinica,2011,39(9):2067-2071.(in Chinese)
[9]  杨福生,洪波.独立分量分析的原理与应用[M].北京:清华大学出版社,2006. Yang Fusheng,Hong Bo.The Principle and Application of Independent Component Analysis[M].Beijing:Tsinghua University Press,2006.(in Chinese)
[10]  Pierre Comon.Independent component analysis,A new concept? [J].Signal Processing,1994,36(3):287-314.
[11]  Yamamoto K,Asano F,Rooijen WFG,et al.Estimation of the number of sound sources using support vector machines and its application to sound source separation .Proc ICASSP .Hong Kong:IEEE,2003.485-488.
[12]  YILMAZ ?,RICKARD S.Blind separation of speech mixtures via time-frequency masking[J].IEEE Transactions on Signal Processing,2004,52(7):1830-1847.
[13]  A Cichocki,S Amari.Adaptive Blind Signal and Image Processing (II.Corrected Edition)[M].UK:John Wiley,Chichester,2003.1-539.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133