结合小波包和ICA的脑电信号特征波提取方法*

为了更有效地提取脑电信号特征波，结合小波包和ICA（独立分量分析），提出了一种脑电特征波提取方法。首先对脑电信号进行小波包分解，然后进行相关频段信号的重构，从而提取出特征波的概貌作为初次提取的特征波；再利用ICA分离技术，以初次提取的特征波为参考信号对其进行增强。实验结果表明，对比于独立地应用某一种方法，两种方法相结合更能有效地提取脑电信号特征波。

Feature extraction of EEG signal based on wavelet package and ICA

In order to extract the feature of EEG signals efficiently,put forward the method combined wavelet package with ICA.Firstly,decomposed the original EEG signals by using wavelet package transformation, and extracted the rough feature wave by recomposing the related decomposed coefficients as the preliminary extraction. Then,used the fast ICA technique for boosting up the feature wave by separating the feature wave again. Compared with applying the two methods separately, method combined wavelet package and ICA is more efficient to extract feature wave.