脑电中眼电伪迹的自动识别与去除  

The automatic identification and removal of ocular artifacts from EEG

作　　者：李明爱 刘帆 LI Ming＇ai;LIU Fan(Faculty of Information Technology,Beijing University of Technology,Beijing 100124;Beijing Key Laboratory of Computational Intelligence and Intelligent System,Beijing 100124)

机构地区：[1]北京工业大学信息学部,北京100124 [2]计算智能与智能系统北京市重点实验室,北京100124

出　　处：《北京生物医学工程》2018年第6期559-565,共7页Beijing Biomedical Engineering

基　　金：国家自然科学基金(81471770);北京市自然科学基金(7132021)资助

摘　　要：目的为改善脑电中眼电伪迹的去除效果,基于脑电的非平稳性和模糊特点,提出一种将离散小波变换与二阶盲辨识相结合,并以模糊熵为眼电伪迹判别准则的眼电伪迹去除方法。方法首先,采用离散小波变换对含噪的脑电信号进行多分辩分析,获得平稳性更好的多尺度小波系数;进而,选择同层的小波系数构成小波系数矩阵,并基于二阶盲辨识对其盲源分离,得到源信号的估计;进一步以模糊熵为判别依据,实现眼电伪迹的自动判别与剔除。实验数据采用BCI Competition IV公开数据库,使用信噪比、相关系数及均方根误差等常用伪迹判别指标进行衡量。结果本文方法相对于常用的眼电伪迹去除方法在多个性能指标上均取得最大值。结论本文提出的眼电伪迹去除方法,实现了眼电伪迹的自动精确判断与剔除,并表现出很好的稳定性。Objective Based on the nonstationary and fuzzy characteristics of electroencephalogram（EEG）, we proposed an electrooculogram （ EOG） removal method, in which discrete wavelet transform（DWT） is combined with second.order blind identification（SOBI）, and fuzzy entropy is used for discriminantof ocular artifacts（OA） . Methods DWT is used to analyze each channel of EEG with noise to obtain morestable multi.scale wavelet coefficients. Then, the wavelet coefficients in the same layer are selected to constructthe wavelet coefficient matrix, and it is further separated by using SOBI to get the estimation of source signals,whose fuzzy entropies are calculated and employed to realize the automatic identification and elimination of OA.The experimental data comes from the publication of Data Sets 2b database in BCI Competition IV. Thecommonly used performance indicators such as signal.to.noise ratio, correlation coefficient and root mean squareerror are used to measure the effect of artifact removal. Results This method achieves the maximum values overmultiple performance indicators relative to the commonly used methods. Conclusions The automatic andaccurate identification and elimination of OA is realized by this method, yielding more stable experimentalresults.

关 键 词：脑电信号 眼电伪迹 离散小波变换 二阶盲辨识 模糊熵 

分 类 号：R318.04[医药卫生—生物医学工程]