作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (3): 180-182,186. doi: 10.3969/j.issn.1000-3428.2012.03.061

• 人工智能及识别技术 • 上一篇    下一篇

基于CuBICA算法的EEG伪迹去除方法

罗志增,蔡新波   

  1. (杭州电子科技大学机器人研究所,杭州 310018)
  • 收稿日期:2011-06-03 出版日期:2012-02-05 发布日期:2012-02-05
  • 作者简介:罗志增(1965-),男,教授、博士,主研方向:传感器技术,多信息融合,生物医学信息检测;蔡新波,硕士研究生
  • 基金资助:
    国家自然科学基金资助项目(60874102)

EEG Artifact Removal Method Based on CuBICA Algorithm

LUO Zhi-zeng, CAI Xin-bo   

  1. (Robot Research Institute, Hangzhou Dianzi University, Hangzhou 310018, China)
  • Received:2011-06-03 Online:2012-02-05 Published:2012-02-05

摘要: 在高阶累积量和独立分量分析的基础上,提出一种基于CuBICA算法的脑电信号伪迹去除方法。针对脑电信号中常含有的眼电、心电等伪迹问题,利用小波包方法对原始脑电信号去噪,并进行中心化和白化处理,运用CuBICA算法对消噪后的脑电信号进行盲源分 离。分析分离后各信号间相关性,结果表明,CuBICA算法能成功分离脑电、眼电与心电信号,有效去除纯脑电信号中的各种伪迹。

关键词: 脑电信号, 伪迹去除, 盲源分离, 互相关系数, 独立分量分析, 累积量

Abstract: According to high order cumulant and Independent Component Analysis(ICA), this paper proposes a method of removing artifacts from Electroencephalogram(EEG) based on CuBICA. The Electroencephalogram which mixing with EOG and EKG signals are denoised by wavelet package analysis, after centering and whitening, the EEG signals which still containing EOG and EKG is separated by CuBICA algorithm. The cross correlation coefficient of the separated signals is analyzed, result shows that CuBICA algorithm can efficiently separate EOG and EKG from EEG, and get pure EEG.

Key words: Electroencephalogram(EEG), artifact removal, Blind Source Separation(BSS), cross correlation coefficient, Independent Component Analysis(ICA), cumulant

中图分类号: