基于FastICA的盲源分离算法研究  

Fast ICA based Blind Source Signal Separation

作　　者：谢志明[1] 吴德华[1] 

机构地区：[1]长沙航空职业技术学院,湖南长沙410124

出　　处：《数字技术与应用》2013年第6期140-141,共2页Digital Technology & Application

基　　金：湖南省高等学校科学研究项目(10C0008)

摘　　要：FICA是一种非常有效的盲信号分离算法,该算法比批处理甚至自适应处理具有更快的收敛速度。本文介绍了一种以四阶累计量为判据的固定点算法。运用matlab仿真,对四路不相关的源信号进行分离,仿真结果表明,该算法能有效的分离出四路源信号,获得了比较好的效果。The fast independent component analysis is a effective algorithm used in blind source separation,this algorithm have the fastest convergence speed more than the batch processing and the adaptive processing. This paper introduces affixer-point algorithm which uses fourth order cumulant as the optimized criterion. Four source signals were discreted by simulation using Madab,the results showed that this algorithm can discrete four signals effectively.

关 键 词：盲分离 独立分量分析 四阶累计量 

分 类 号：TN911[电子电信—通信与信息系统]