摘要
基于独立分量分析的盲源分离方法,采用快速独立分量分析(Fast Independent ComponentAnalysis,FastICA)的算法对混合的非高斯信号进行分离.通过对仿真信号的分离比较,使用峭度值和信噪比对分离函数tanh和gauss函数的性能进行了分析,研究分离函数的选择对于分离效果的影响。
The blind source separation based on independent component analysis is performed by means of FastlCA algorithms, with which the non-gussian signals will be separated. Through the separation and comparison of simulation signal,analysising the performance of the separation function 'tanh' and 'gauss' by using the Kurtosis information and SNR, and also discuss the selection of nonlinear functions on separation effect.
出处
《汽车实用技术》
2013年第7期48-51,共4页
Automobile Applied Technology
关键词
盲源分离
独立分量分析
超高斯
亚高斯
快速独立分量分析
blind source separation (BSS)
independent component analysis (ICA)
super-Gaussian
sub-Gaussian
fastICA