基于二次小波去噪的 FastICA 盲源分离研究

摘要

A three‐step method about noise mixed signal separation is put forward in this paper ,the wavelet filter de‐noising processing method and the fast independent component analysis(FastICA ) blind sources separation technique to are used realize the separation ,then the wavelet filtering method is used again to the separated signals .The simulation results show that the technique performs well in signal separation by comparing the waves and signal to noise ratio before and after separation and it has good denoising performance and separation effect .%论文针对含噪声混合信号分离问题，提出了三步处理法，首先采用小波滤波进行去噪处理，再采用快速独立分量分析（FastICA）盲源分离技术实现混合信号的分离，最后对分离后的信号二次使用小波滤波处理。仿真实验结果表明，该方法能够很好地分离含噪混合信号，从分离前后的波形及平均信噪比对照，去噪性能和分离效果良好。