一种基于盲源分离的眼电伪迹自动去除方法  

Automatic ocular artifact removal based on blind source separation

作　　者：计瑜[1] 沈继忠[1] 施锦河[1] 

机构地区：[1]浙江大学电子电路与信息系统研究所,浙江杭州310027

出　　处：《浙江大学学报（工学版）》2013年第3期415-421,464,共8页Journal of Zhejiang University：Engineering Science

摘　　要：为解决传统盲源分离算法(BSS)用于眼电伪迹去除大都存在伪迹过估计、需要人为辨别伪迹成分而不适合在线应用的不足,提出一种基于BSS算法的眼电伪迹自动去除方法.利用BSS算法对脑电信号进行分离得到独立成分,以相关系数作为判据,针对垂直眼电(VEOG)和水平眼电(HEOG)的各自特点确定不同的时间窗,寻找最优成分组合标定眨眼或眼动活动发生的时域区间,将找到的存在伪迹的成分区间置零并重建脑电(EEG)信号.通过真实P300脑电数据实验的结果表明:该方法能有效地自动去除眼电伪迹,且处理过程简单易行,克服了眼电伪迹过估计等问题.算法重建EEG信号与原始脑电(EEG)信号的平均相关系数分别从0.851 3和0.900 6提高到0.923 7,而均方误差分别减少了19.3%和16.6%,适合在线应用.Aiming at the problems such as the overestimation of ocular artifact,the need of human intervention,and the difficulty for online application in traditional blind source separation（BSS）-based methods for artifacts removal,a totally automatic method for removing ocular artifacts was proposed.BSS was used to separate electroencephalogram（EEG） signals to obtain the independent components.With the criterion of correlation coefficient,different time windows according to vertical electrooculogram（VEOG） and horizontal electrooculogram（HEOG）＇s respective characteristics were used to find the best components combination,by which the time intervals that have blink or eye movement activities could be calibrated.Then,the calibrated time intervals were removed and the EEG signals were reconstructed.With experiments of P300 signals processing,this method was proved to be effective and practical in removing ocular artifact automatically and overcoming the drawbacks above.Compare with related literatures,the experiment results showed that the proposed method increased the average correlation coefficient between the reconstructed EEG signals and the original EEG signals from 0.851 3 and 0.900 6 to 0.923 7 respectively,while the mean square error was decreased by 19.3% and 16.6%,contributing to online application.

关 键 词：眼电伪迹 自动去除 二阶盲辨识 相关系数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]