脑机接口中基于约束独立分量分析和自适应滤波的眼电快速去除

Yang Bang-hua; He Liang-fei; Lin Lin; Wang Qian

doi:10.1631/FITEE.1400299

Your Location：

Home >

Browse articles >

脑机接口中基于约束独立分量分析和自适应滤波的眼电快速去除

计算机与自动化 | Updated：2022-06-06

- 脑机接口中基于约束独立分量分析和自适应滤波的眼电快速去除
- Fast removal of ocular artifacts from electroencephalogram signals using spatial constraint independent component analysis based recursive least squares in brain-computer interface*
- 信息与电子工程前沿（英文） 2015年16卷第6期页码：486-496
- Affiliations：
  
  Shanghai Key Laboratory of Power Station Automation Technology, Department of Automation, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200072, China
- Author bio：
  
  ‡Corresponding Author
  †E-mail:yangbanghua@126.comheliangfei126@126.comfxlinlin@shu.edu.cn
- Funds：
  
  *Project supported by the National Natural Science Foundation of China (Nos. 31100709 and 60975079) and the Shanghai Pujiang Program, China (No. 14PJ1431300)
- DOI：10.1631/FITEE.1400299
  中图分类号：
- 收稿：2014-08-18，
  
  修回：2015-05-07，
  
  录用：2015-01-13，
  
  纸质出版：2015-03
- Accepted：
Scan QR Code
脑机接口中基于约束独立分量分析和自适应滤波的眼电快速去除[J]. 信息与电子工程前沿（英文）, 2015,16(6):486-496.

Yang Bang-hua, He Liang-fei, Lin Lin, et al. Fast removal of ocular artifacts from electroencephalogram signals using spatial constraint independent component analysis based recursive least squares in brain-computer interface*[J]. Frontiers of Information Technology & Electronic Engineering, 2015, 16(6): 486-496.
脑机接口中基于约束独立分量分析和自适应滤波的眼电快速去除[J]. 信息与电子工程前沿（英文）, 2015,16(6):486-496. DOI： 10.1631/FITEE.1400299.

Yang Bang-hua, He Liang-fei, Lin Lin, et al. Fast removal of ocular artifacts from electroencephalogram signals using spatial constraint independent component analysis based recursive least squares in brain-computer interface*[J]. Frontiers of Information Technology & Electronic Engineering, 2015, 16(6): 486-496. DOI： 10.1631/FITEE.1400299.

摘要

目的

眼电是脑电的主要干扰，采用眼电信号作为参考的自适应滤波能有效消除眼电干扰。然而眼电采集不方便且繁琐。在脑机接口中为从脑电中去除眼电，提出基于约束独立分量分析和自适应滤波的快速去除方法。该方法具有无需记录眼电信号且快速的优点。

创新点

所提方法避免了实验过程中直接对被试者进行眼电信号采集，减少被试者在实验过程中的不适。该方法处理后的识别正确率比单纯用传统ICA算法和不进行任何处理的源信号分别提高了3.3%和12.6%。另外，该方法的时间耗费较上述两种算法分别降低了83.5%和83.8%，更好地满足脑机接口在线要求。

方法

该方法分为两个阶段：第一阶段的目的是提取纯净的EOG信号。首先用ICA算法将输入信号分离成相互独立的分量（IC）。计算每个IC的峰态系数值并依据该值自动识别EOG独立分量（图2）。然后运用经验模态分解（EMD）将所识别的EOG信号自适应分解成数个IMF。根据IMF频域特征，选择数个IMF组合成纯净的EOG信号（图3）。第二阶段的目的是结合SCICA和RLS滤波算法去除混合在EEG信号中的EOG伪迹。首先SCICA利用第一阶段分离出的纯净EOG信号作为参考模板，迅速将混合在源信号中的EOG信号识别分离出。然后将该EOG信号分量作为RLS滤波器参考信号进行自适应滤波，最终去除EOG伪迹（图7）。

结论

针对脑机接口脑电信号包含的眼电伪迹，提出一种基于约束独立分量分析和自适应滤波的快速自动去除方法。该方法去除效果良好，可用于脑机接口中眼电的在线自动消除。

Abstract

Ocular artifacts cause the main interfering signals within electroencephalogram (EEG) signal measurements. An adaptive filter based on reference signals from an electrooculogram (EOG) can reduce ocular interference

but collecting EOG signals during a long-term EEG recording is inconvenient and uncomfortable for the subject. To remove ocular artifacts from EEG in brain-computer interfaces (BCIs)

a method named spatial constraint independent component analysis based recursive least squares (SCICA-RLS) is proposed. The method consists of two stages. In the first stage

independent component analysis (ICA) is used to decompose multiple EEG channels into an equal number of independent components (ICs). Ocular ICs are identified by an automatic artifact detection method based on kurtosis. Then empirical mode decomposition (EMD) is employed to remove any cerebral activity from the identified ocular ICs to obtain exact artifact ICs. In the second stage

first

SCICA applies exact artifact ICs obtained in the first stage as a constraint to extract artifact ICs from the given EEG signal. These extracted ICs are called spatial constraint ICs (SC-ICs). Then the RLS based adaptive filter uses SC-ICs as reference signals to reduce interference

which avoids the need for parallel EOG recordings. In addition

the proposed method has the ability of fast computation as it is not necessary for SCICA to identify all ICs like ICA. Based on the EEG data recorded from seven subjects

the new approach can lead to average classification accuracies of 3.3% and 12.6% higher than those of the standard ICA and raw EEG

respectively. In addition

the proposed method has 83.5% and 83.8% reduction in time-consumption compared with the standard ICA and ICA-RLS

respectively

which demonstrates a better and faster OA reduction.

关键词

Keywords

references

MT Akhtar , W Mitsuhashi , CJ James . Employing spatially constrained ICA and wavelet denoising, for automatic removal of artifacts from multichannel EEG data . Signal Process , 2012 . 92 ( 2 ): 401 - 416 . DOI: 10.1016/j.sigpro.2011.08.005 http://doi.org/10.1016/j.sigpro.2011.08.005 .

A Arasteh , A Janghorbani , MH Moradi . A survey on EMD sensitivity to SNR for EEG feature extraction in BCI application . 2010 . Proc. 5th Cairo Int. Biomedical Engineering Conf . 175 - 179 . DOI: 10.1109/CIBEC.2010.5716061 http://doi.org/10.1109/CIBEC.2010.5716061 .

G Barbati , C Porcaro , P Zappasodi , 等 . Optimization of an independent component analysis approach for artifact identification and removal in magnetoencephalographic signals . Clin Neurophysiol , 2004 . 115 ( 5 ): 1220 - 1232 . DOI: 10.1016/j.clinph.2003.12.015 http://doi.org/10.1016/j.clinph.2003.12.015 .

B Blankertz , G Dornhege , M Krauledat , 等 . The non-invasive Berlin brain-computer interface: fast acquisition of effective performance in untrained subjects . NeuroImage , 2007 . 37 ( 2 ): 539 - 550 . .

HL Chan , YT Tsai , LF Meng , 等 . The removal of ocular artifacts from EEG signals using adaptive filters based on ocular source components . Ann Biomed Eng , 2010 . 38 ( 11 ): 3489 - 3499 . DOI: 10.1007/s10439-010-0087-2 http://doi.org/10.1007/s10439-010-0087-2 .

A Delorme , T Sejnowski , S Makeig . Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis . NeuroImage , 2007 . 34 ( 4 ): 1443 - 1449 . DOI: 10.1016/j.neuroimage.2006.11.004 http://doi.org/10.1016/j.neuroimage.2006.11.004 .

U Güçlü , Y Güçlütürk , CK Loo . Evaluation of fractal dimension estimation methods for feature extraction in motor imagery based brain computer interface . Procedia Comput Sci , 2011 . 3 589 - 594 . DOI: 10.1016/j.procs.2010.12.098 http://doi.org/10.1016/j.procs.2010.12.098 .

B Hazra , A Roffel , S Narasimhan , 等 . Modified cross-correlation method for the blind identification of structures . J Eng Mech , 2010 . 136 ( 7 ): 889 - 897 . DOI: 10.1061/(ASCE)EM.1943-7889.0000133 http://doi.org/10.1061/(ASCE)EM.1943-7889.0000133 .

P He , G Wilson , C Russell . Removal of ocular artifacts from electroencephalogram by adaptive filtering . Med Biol Eng Comput , 2004 . 42 ( 3 ): 407 - 412 . DOI: 10.1007/BF02344717 http://doi.org/10.1007/BF02344717 .

CW Hesse , CJ James . The FastICA algorithm with spatial constraints . IEEE Signal Process Lett , 2005 . 12 ( 11 ): 792 - 795 . DOI: 10.1109/LSP.2005.856867 http://doi.org/10.1109/LSP.2005.856867 .

L Huang , H Wang . Reducing the computation time for BCI using improved ICA algorithms . 2013 . Proc. 10th Int. Symp. on Neural Networks . 299 - 304 . DOI: 10.1007/978-3-642-39068-5_37 http://doi.org/10.1007/978-3-642-39068-5_37 .

TP Jung , S Makeig , C Humphries , 等 . Removing electroencephalographic artifacts by blind source separation . Psychophysiology , 2000 . 37 ( 2 ): 163 - 178 . DOI: 10.1007/978-3-540-74819-9_84 http://doi.org/10.1007/978-3-540-74819-9_84 .

MA Klados , C Bratsas , C Frantzidis , 等 . A kurtosis-based automatic system using naïve Bayesian classifier to identity ICA components contaminated by EOG or ECG artifacts . 2010 . Proc. XII Mediterranean Conf. on Medical and Biological Engineering and Computing . 49 - 52 . DOI: 10.1007/978-3-642-13039-7_13 http://doi.org/10.1007/978-3-642-13039-7_13 .

X Li , WB Wang . Studying on denoising of chaotic signal using ICA and EMD . 2013 . Proc. Int. Symp. on Geo-Informatics in Resource Management and Sustainable Ecosystem . 564 - 572 . DOI: 10.1007/978-3-642-45025-9_55 http://doi.org/10.1007/978-3-642-45025-9_55 .

Y Li , YH Koike . A real-time BCI with a small number of channels based on CSP . Neur Comput Appl , 2012 . 20 ( 8 ): 1187 - 1192 . DOI: 10.1007/s00521-010-0481-6 http://doi.org/10.1007/s00521-010-0481-6 .

N Mammone , G Inuso , F La Foresta , 等 . Multiresolution ICA for artifact identification from electroencephalographic recordings . 2007 . Proc. 11th Int. Conf. on Neural Networks . 680 - 687 . DOI: 10.1007/978-3-540-74819-9_84 http://doi.org/10.1007/978-3-540-74819-9_84 .

HAT Nguyen , J Musson , F Li , 等 . EOG artifact removal using a wavelet neural network . Neurocomputing , 2012 . 97 374 - 389 . DOI: 10.1016/j.neucom.2012.04.016 http://doi.org/10.1016/j.neucom.2012.04.016 .

X Qiao , D Li , Y Dong . P300 feature extraction based on parametric model and FastICA algorithm . 2009 . Proc. 5th Int. Conf. on Natural Computation . 585 - 589 . DOI: 10.1109/ICNC.2009.160 http://doi.org/10.1109/ICNC.2009.160 .

B Wang . Comprehensive Study on Removal of Artifacts from EEG Data. MS T , 2010 . Zhejiang University, Hangzhou, China , (in Chinese) .

I Winkler , S Brandl , F Horn , 等 . Robust artifactual independent component classiﬁcation for BCI practitioners . J Neur Eng , 2014 . 11 ( 3 ): 035013.1 - 03501310 . DOI: 10.1088/1741-2560/11/3/035013 http://doi.org/10.1088/1741-2560/11/3/035013 .

H Xu , W Song , ZP Hu , 等 . A speedup SVM decision method for online EEG processing in motor imagery BCI . 2010 . Proc. 10th Int. Conf. on Intelligent Systems Design and Applications . 149 - 154 . DOI: 10.1109/ISDA.2010.5687274 http://doi.org/10.1109/ISDA.2010.5687274 .

BH Yang , GZ Yan , T Wu , 等 . Subject-based feature extraction using fuzzy wavelet packet in brain-computer interfaces . Signal Process , 2007 . 87 ( 7 ): 1569 - 1574 . DOI: 10.1016/j.sigpro.2006.12.018 http://doi.org/10.1016/j.sigpro.2006.12.018 .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据