基于小波变换和独立分量分析的心室晚电位识别

VLP recognization of combining wavelet transform and independent component analysis

由于晚电位(VLP)信号本身的复杂性以及生物个体差异,其检测的敏感性和特异性还不太高,因此探索和完善晚电位分析方法的研究很有意义。本文提出了一种结合小波变换WT(wavelet transform)和独立分量分析(independent component analysis,ICA)的VLP特征提取新方法——WICA。新方法的主要思路是先对心电信号进行小波变换,得到多导的小波变换系数序列,再对系数序列用ICA寻求解混阵W和分解出的晚电位独立分量。实验结果表明,WICA方法在一定程度上能够克服传统方法检测分辨率较低的弱点,并能获得较好的VLP识别。

The VLP signal is hardtv detected and distinguished because of its complexity complicacy and differences exist in individual, so it is meaningful that we seek and consummate the method of VLP analyses. According to the characteristics of EEG signal, WICA, a new approach of combining wavelet transform and ICA, is proposed. The main idea of this new method is then applied to the sub-band signals at different wavelet scale to get the coefficient array . then we search the demixing matrix computed according the ICA ,and we can get the independent component of VLP . The experiment results show that WICA can overcome the difficulties caused by low resolution of traditional methods and get better result of VLP pattern recognition.