电子学报 ›› 2016, Vol. 44 ›› Issue (5): 1032-1039.DOI: 10.3969/j.issn.0372-2112.2016.05.004

• 学术论文 • 上一篇    下一篇

眼电伪迹自动识别与去除的新方法

李明爱1,2, 郭硕达1, 田晓霞1, 杨金福1,2, 郝冬梅3   

  1. 1. 北京工业大学电子信息与控制工程学院, 北京 100124;
    2. 计算智能与智能系统北京市重点实验室, 北京 100124;
    3. 北京工业大学生命科学与生物工程学院, 北京 100124
  • 收稿日期:2014-08-14 修回日期:2015-05-05 出版日期:2016-05-25
    • 通讯作者:
    • 李明爱
    • 作者简介:
    • 郭硕达 男,2012年于武汉纺织大学获得学士学位,现为北京工业大学控制科学与工程专业硕士研究生,主要研究方向为脑机接口技术、信息处理与模式识别.
    • 基金资助:
    • 国家自然科学基金 (No.81471770,No.61201362); 北京市自然科学基金 (No.7132021,No.7132028)

A Novel Automatic Recognition and Removal Method of Ocular Artifacts

LI Ming-ai1,2, GUO Shuo-da1, TIAN Xiao-xia1, YANG Jin-fu1,2, HAO Dong-mei3   

  1. 1. College of Electronic Information & Control Engineering, Beijing University of Technology, Beijing 100124, China;
    2. Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124, China;
    3. College of Life Science and Bio-Engineering, Beijing 100124, China
  • Received:2014-08-14 Revised:2015-05-05 Online:2016-05-25 Published:2016-05-25

摘要:

为了改善脑电中的眼电伪迹过估计问题及环境干扰耦合引起的非线性混合对眼电去除效果的影响,提出一种基于快速核独立成分分析(Fast Kernel Independent Component Analysis,FastKICA)与离散小波变换(Discrete Wavelet Transform,DWT)的眼电自动去除方法,即(Fast Kernel Independent Wavelet Transform ,FKIWT)方法.首先,利用FastKICA方法对脑电信号进行分离得到独立成分,并以相关系数为依据识别出眼电伪迹;进而,基于DWT对眼电伪迹进行多分辨率分析,将逼近分量置零,而细节分量保持不变,使得重构所得眼电伪迹成分保留更多有用脑电信号;最后,利用FastKICA逆变换重建眼电去除后的脑电信号.实验结果表明:FKIWT不仅有效改善了眼电过估计问题,增强了抗干扰能力和鲁棒性,而且在线性混合和非线性混合情况下,均得到较好的伪迹去除效果,特别是在非线性混合时优势更为明显,适合于实际在线应用.

关键词: 非线性混合模型, 快速核独立成分分析, 离散小波变换, 眼电过估计, 鲁棒性

Abstract:

In order to improve the overestimation of ocular artifacts (OA) in electroencephalogram (EEG) and the OA removal effect of nonlinear mixture caused by environmental interference coupling, a novel automatic removal method is proposed based on fast kernel independent component analysis (FastKICA) and discrete wavelet transform (DWT), and it is denoted as FKIWT.The independent components are separated from the mixed EEG by using the FastKICA algorithm, and the correlation coefficient is applied to identify OA component;Then, the Multiresolution analysis of OA is achieved with DWT, the approximation wavelet coefficients are set to zero and the detail wavelet coefficients are not changed.So more useful EEG is remained in the reconstructed OA component;Furthermore, the clean EEG is restored with the inverse algorithm of FastKICA.The experimental results show that FKIWT can effectively improve the overestimation of OA and has perfect anti-interference ability and robustness.Meanwhile, the better effects of OA elimination are also obtained on the condition that the linear or nonlinear mixed model is adopted, and the latter's advantage is especially obvious.The FKIWT is suitable for on-line application.

Key words: nonlinear mixed model, fast kernel independent component analysis, discrete wavelet transform, overestimation of ocular artifacts, robustness

中图分类号: