摘要
提出一种新的多通道脑电信号盲分离的方法,将小波变换和独立分量分析(independentcomponentanalysis,ICA)相结合,利用小波变换的滤噪作用,将混合在原始脑电的部分高频噪声滤除后,再重构原始脑电作为ICA的输入信号,有效地克服了现有ICA算法不能区分噪声的缺陷。实验结果表明,该方法对多通道脑电的盲分离是很有效的。
A new method of blind signal separation(BSS) for multi-channel EEG is propo sed, which combines the Wavelet Transform with the independent component analys is (ICA). By using the noise filtering function of wavelet transform, some high-frequency noises were removed from the original EEG, and the original EEG was reconstructed again for the input of ICA. So the defect that ICA is impossible t o distinguish noises from source signals can be overcomed effectively. The expe rimental results show that this method is an effective way to BSS of multi-chan nel EEG.
出处
《生物物理学报》
CAS
CSCD
北大核心
2004年第1期77-82,共6页
Acta Biophysica Sinica
基金
国家自然科学基金重点项目(10234070)
福建省自然科学基金计划项目(C0310028)
关键词
脑电
小波变换
主成分分析
独立成分分析
盲信号分离
Electroencephalograph (EEG)
Wavelet transform
Principal component analysis(PCA)
Independent component analysis (ICA)
Blind signal se paration (BSS)
