基于ICA的EEG参考信号去除  

Removal Reference Signal in EEG Recording Base on FastICA

作　　者：陈士辉[1] 胡三清[1] 

机构地区：[1]杭州电子科技大学计算机学院,浙江杭州310018

出　　处：《杭州电子科技大学学报（自然科学版）》2014年第2期77-80,共4页Journal of Hangzhou Dianzi University：Natural Sciences

基　　金：杭州电子科技大学研究生优秀学位论文培育基金资助项目(yxlw2013004)

摘　　要：脑电信号的参考电极一般选耳垂或者乳突,正确去除参考信号对于研究脑电信号的相关性、相位同步性等有重要的意义。该文首先在采集脑电信号时用手指轻弹参考电极,然后运用独立成分分析中的快速算法分离脑电信号中的各个独立分量和相应的分离矩阵自动识别参考信号。研究结果表明该方法能有效识别和去除参考信号,在脑电信号的处理中有重要应用价值,值得深入研究和推广。The reference electrode of EEG signal is usually selected at earlobe or mastoid. Removing the reference signal is an important work to study coherence,phase synchronization etc. In this paper,we first introduce an EEG recording process that one taps the reference electrode of one subject regularly,then we apply FastICA to separate the independent components and get the corresponding separation matrix which is employed to identify the reference signal. The experimental results demonstrate that this method can identify and remove the reference signal efficiently. The proposed method will have important application in EEG analysis and is worthy of further study.

关 键 词：脑电信号 参考信号 独立成分分析 分离矩阵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]