非线性盲源分离的原理及算法综述  

An Overview on Nonlinear Blind Source Separation: Theory and Algorithms

作　　者：王法松[1] 李宏伟[1] 沈远彤[1] 

机构地区：[1]中国地质大学数理系,武汉430074

出　　处：《信号处理》2005年第3期282-288,281,共8页Journal of Signal Processing

摘　　要：本文主要阐述了非线性盲源分离(BSS)/独立成分分析(ICA)模型的基本数学原理、分离算法、算法性能及其应用。首先对线性和非线性BSS/ICA的数学模型作了介绍,重点介绍了非线性BSS/ICA解的不确定性,然后在此基础上对近十年来出现的各种非线性BSS/ICA算法进行简单综述,着重分析了一类可解且应用比较广泛的非线性BSS/ICA模型-后非线性BSS/ICA模型及其分离算法。最后对非线性BSS/ICA存在的问题和发展趋势进行了总结。In this paper, we show the basic mathematic model and separated algorithms of blind source separation (BSS)/ independent component analysis (ICA) firstly, we discuss in more detail uniqueness issues about the nonlinear BSS/ICA problems. Then several algorithms proposed recently about nonlinear BSS/ICA are reviewed. Post-nonlinear (PNL) BSS/ICA algorithm is an important special case, where a nonlinearity is applied to linear BSS/ICA. Finally various separation algorithms proposed for PNL BSS/ICA and general nonlinear BSS/ICA are reviewed and give a conclusion about the problem and tendency on the development about nonlinear BSS/ICA.

关 键 词：盲源分离 非线性 独立成分分析(ICA) 综述 分离算法 CA模型 BSS ICA算法 数学原理 算法性能 数学模型 不确定性 应用比较 发展趋势 重分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TN911.7[自动化与计算机技术—计算机科学与技术]