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. 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
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.
[1] Akhtar M T,Mitsuhashi W,James C J.Employing spatially constrained ICA and wavelet denoising,for automatic removal of artifacts from multichannel EEG data[J].Signal Processing,2012,92(2):401-416.
[2] Vijila C,et al.Artifacts removal in EEG signal using adaptive neuro fuzzy inference system[A].2007 International Conference of Signal Processing,Communications and Networking[C].Chennai:IEEE,2006.589-591.
[3] Jung T P,Makeig S,Humphries C,et al.Removing electroencephalographic artifacts by blind source separation[J].Psychophysiology,2000,37(2):163-178.
[4] Cardoso J F,Souloumiac A.Blind beamforming for non-Gaussian signals[J].IEE Proceedings-F Padar and Signal Processing,1993,140(6):362-370.
[5] Pham D T,Cardoso J F.Blind separation of instantaneous mixtures of nonstationary sources[J].IEEE Transactions on Signal Processing,2001,49(9):1837-1848.
[6] Karvanen J,Koivunen V.Blind separation methods based on Pearson system and its extensions[J].Signal Processing,2002,82(4):663-673.
[7] Shen H,Kleinsteuber M,Huper K.Local convergence analysis of FastICA and related algorithms[J].IEEE Transactions on Neural Networks,2008,19(6):1022-1032.
[8] Dermoune A,Wei T W.FastICA algorithm:Five criteria for the optimal choice of the nonlinearity function[J].IEEE Transactions on Signal Processing,2013,61(8):2078-2087.
[9] 李明爱,崔燕,杨金福.脑电信号中眼电伪迹自动去除方法的研究[J].电子学报,2013,41(06):1207-1213. LI Ming-ai,CUI Yan,YANG Jin-fu.Research on removing ocular artifact automatically from EEG signals[J].Acta Electronica Sinica,2013,41(06):1207-1213.(in Chinese)
[10] Klados M A,Papadelis C L,Bamidis P D.REG-ICA:A new hybrid method for EOG artifact rejection[A].20099th International Conference on Information Technology and Applications in Biomedicine[C].Larnaka:IEEE,2009.278-281.
[11] 李晓欧.基于独立分量分析和共同空间模式的脑电特征提取方法[J].生物医学工程学杂志,2010,27(06):1370-1374. LI Xiao-ou.EEG feature extraction basedon ICA and CSP algorithms[J].Journal of Biomedical Engineering,2010,27(06):1370-1374.(in Chinese)
[12] 万柏坤,等.ICA去除EEG中眼动伪差和工频干扰方法研究[J].电子学报,2003,31(10):1571-1574. WANG Bai-kun,ZHU Xin,YANG Chun-mei,et al.Study on applying independent component analysis to remove blink artifacts and power noise in EEG[J].Acta Electronica Sinica,2003,31(10):1571-1574.(in Chinese)
[13] Marchesi S,Bruzzone L.ICA and kernel ICA for change detection in multispectral remote sensing images[A].2009 IEEE International Geoscience and Remote Sensing Symposium[C].Cape Town:IEEE,2009.1231-1234.
[14] Tateyama T,Nakao Z,Chen Y W.Classification of brain matters in MRI by kernel independent component analysis[A].20084th International Conference on Intelligent Information Hiding and Multimedia Signal Processing Proceedings[C].Harbin:IEEE Computer Soc,2008.713-716.
[15] Shen H,Jegelka S,Gretton A.Fast kernel-based independent component analysis[J].IEEE Transactions on Signal Processing,2009,57(9):3498-3511.
[16] 罗志增,等.基于小波变换和盲信号分离的多通道肌电信号处理方法[J].电子学报,2009,37(04):823-827. LUO Zhi-zeng,et al.A method of multi-channel EMG disposal based on wavelet transform and blind signal separation[J].Acta Electronica Sinica,2009,37(04):823-827.(in Chinese)
[17] 王明祥,宁宇蓉,王晋国.基于Mallat算法的一维离散小波变换的实现[J].西北大学学报(自然科学版),2006,36(03):364-368. WANG Ming-xiang,NING Yu-rong,WANG Jin-guo.Realization of one dimension discrete wavelet transform based on Mallat algorithm[J].Journal of Northwest University(Natural Science Edition),2006,36(03):364-368.(in Chinese)
2016, Vol. 44 
