独立分量分析在信号处理中的应用
|
摘要
独立分量分析(ICA)是近期发展起来的一种统计学方法,旨在寻求对非高斯分布数据进行有效的表示,使得各个分量在统计学上独立,或者尽最大可能地独立。文章介绍了独立分量分析的发展过程,基本理论等。许多应用中,这种表示意在获取数据的基本结构,包括特征提取和信号分离,目前主要应用在盲源分离,特征提取,盲反卷积等方面。
Independent component analysis(ICA) is recently developed as a kind of statistical methods,Sought to express the data of non-gaussian distribution effectively,made different components were independent or as much as possible to independence in statistics.This paper introduced the development of process of independent component analysis,basic theory,and so on.In many applications,this expression aimed to obtain the basic structure of data,including feature extraction and signal separation,at present,the main application in blind source separation,feature extraction,blind deconvolution,etc.
Independent component analysis(ICA) is recently developed as a kind of statistical methods,Sought to express the data of non-gaussian distribution effectively,made different components were independent or as much as possible to independence in statistics.This paper introduced the development of process of independent component analysis,basic theory,and so on.In many applications,this expression aimed to obtain the basic structure of data,including feature extraction and signal separation,at present,the main application in blind source separation,feature extraction,blind deconvolution,etc.
引文
[1]张新军.独立分量分析及其在多通道信号处理中的应用研究[D].汕头大学硕士学位论文,2003:15-16.
[2]Amari S,Chen T P,Cichocki A.Stability analysis of learningalgorithms for blind source separation[J].Neural Networks,1997,10(8):1345-1351.
[3]杨行峻,郑君里.人工神经网络与盲信号处理[A].2003:21.
[4]Bell A,Sejnowski T J.An information-maximization approach toblind separation and blind deconvolution[J].Neural Computa-tion,2005,7(6):1129-1159.
[5]翟葵,吴小培.基于独立分量分析的脑电信号消噪[J].现代制造工程2006(2):90
[6]赵彩华,刘琚,孙建德,闫华.基于小波变换和独立分量分析的含噪混叠语音盲分离[J].电子与信息学报2006(09):78.
[7]Jian Ji,Zheng Tian.Robust ICA Neural Network and Applica-tion on Synthetic Aperture Radar(SAR)Image Analysis[A].Lecture Notes in Computer Science.2006:108-110
[8]王岩.基于独立分量分析与神经网络的电子鼻模式识别[D].西南交通大学硕士学位论文.2006:41.
[9]李国福,曹思远,周鹏,韩瑞东.地震去噪中的P-ICA方法[C].中国地球物理第二十一届年会论文集,2005:87-89.
[10]李鸿燕,王华奎,独立分量分析在混叠通信信号分离中的应用[J].仪器仪表学报,2006(s1):66
[11]党红.权益结合法的发展路径分析[J].财会通讯(学术版),2006(4):21.
[2]Amari S,Chen T P,Cichocki A.Stability analysis of learningalgorithms for blind source separation[J].Neural Networks,1997,10(8):1345-1351.
[3]杨行峻,郑君里.人工神经网络与盲信号处理[A].2003:21.
[4]Bell A,Sejnowski T J.An information-maximization approach toblind separation and blind deconvolution[J].Neural Computa-tion,2005,7(6):1129-1159.
[5]翟葵,吴小培.基于独立分量分析的脑电信号消噪[J].现代制造工程2006(2):90
[6]赵彩华,刘琚,孙建德,闫华.基于小波变换和独立分量分析的含噪混叠语音盲分离[J].电子与信息学报2006(09):78.
[7]Jian Ji,Zheng Tian.Robust ICA Neural Network and Applica-tion on Synthetic Aperture Radar(SAR)Image Analysis[A].Lecture Notes in Computer Science.2006:108-110
[8]王岩.基于独立分量分析与神经网络的电子鼻模式识别[D].西南交通大学硕士学位论文.2006:41.
[9]李国福,曹思远,周鹏,韩瑞东.地震去噪中的P-ICA方法[C].中国地球物理第二十一届年会论文集,2005:87-89.
[10]李鸿燕,王华奎,独立分量分析在混叠通信信号分离中的应用[J].仪器仪表学报,2006(s1):66
[11]党红.权益结合法的发展路径分析[J].财会通讯(学术版),2006(4):21.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心