A Novel Method Based on Combination of Independent Component Analysis and Ensemble Empirical Mode Decomposition for Removing Electrooculogram Artifacts From Multichannel Electroencephalogram Signals

被引:4
作者
Teng, Chao-Lin [1 ,2 ,3 ]
Zhang, Yi-Yang [1 ,2 ,3 ]
Wang, Wei [4 ]
Luo, Yuan-Yuan [5 ]
Wang, Gang [1 ,2 ,3 ]
Xu, Jin [1 ,2 ,3 ]
机构
[1] Xi An Jiao Tong Univ, Sch Life Sci & Technol, Minist Educ, Key Lab Biomed Informat Engn, Xian, Peoples R China
[2] Minist Civil Affairs, Key Lab Neuroinformat & Rehabil Engn, Xian, Peoples R China
[3] Natl Engn Res Ctr Healthcare Devices, Guangzhou, Peoples R China
[4] Xi An Jiao Tong Univ, Affiliated Hosp 1, Dept Psychiat, Xian, Peoples R China
[5] Xian Mental Hlth Ctr, Dept Psychol, Xian, Peoples R China
基金
中国国家自然科学基金;
关键词
electrooculogram (EOG); artifacts; electroencephalogram (EEG); ensemble empirical mode decomposition (EEMD); independent component analysis (ICA); BLIND SOURCE SEPARATION; CANONICAL CORRELATION-ANALYSIS; OCULAR ARTIFACTS; EEG; ICA; IDENTIFICATION; SUPPRESSION;
D O I
10.3389/fnins.2021.729403
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Electrooculogram (EOG) is one of common artifacts in recorded electroencephalogram (EEG) signals. Many existing methods including independent component analysis (ICA) and wavelet transform were applied to eliminate EOG artifacts but ignored the possible impact of the nature of EEG signal. Therefore, the removal of EOG artifacts still faces a major challenge in EEG research. In this paper, the ensemble empirical mode decomposition (EEMD) and ICA algorithms were combined to propose a novel EEMD-based ICA method (EICA) for removing EOG artifacts from multichannel EEG signals. First, the ICA method was used to decompose original EEG signals into multiple independent components (ICs), and the EOG-related ICs were automatically identified through the kurtosis method. Then, by performing the EEMD algorithm on EOG-related ICs, the intrinsic mode functions (IMFs) linked to EOG were discriminated and eliminated. Finally, artifact-free IMFs were projected to obtain the ICs without EOG artifacts, and the clean EEG signals were ultimately reconstructed by the inversion of ICA. Both EOGs correction from simulated EEG signals and real EEG data were studied, which verified that the proposed method could achieve an improved performance in EOG artifacts rejection. By comparing with other existing approaches, the EICA obtained the optimal performance with the highest increase in signal-to-noise ratio and decrease in root mean square error and correlation coefficient after EOG artifacts removal, which demonstrated that the proposed method could more effectively eliminate blink artifacts from multichannel EEG signals with less error influence. This study provided a novel promising method to eliminate EOG artifacts with high performance, which is of great importance for EEG signals processing and analysis.
引用
收藏
页数:13
相关论文
共 37 条
[1]   AN INFORMATION MAXIMIZATION APPROACH TO BLIND SEPARATION AND BLIND DECONVOLUTION [J].
BELL, AJ ;
SEJNOWSKI, TJ .
NEURAL COMPUTATION, 1995, 7 (06) :1129-1159
[2]   Recovering EEG brain signals: Artifact suppression with wavelet enhanced independent component analysis [J].
Castellanos, Nazareth P. ;
Makarov, Valeri A. .
JOURNAL OF NEUROSCIENCE METHODS, 2006, 158 (02) :300-312
[3]   GPGPU-Aided Ensemble Empirical-Mode Decomposition for EEG Analysis During Anesthesia [J].
Chen, Dan ;
Li, Duan ;
Xiong, Muzhou ;
Bao, Hong ;
Li, Xiaoli .
IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 2010, 14 (06) :1417-1427
[4]   A Novel EEMD-CCA Approach to Removing Muscle Artifacts for Pervasive EEG [J].
Chen, Xun ;
Chen, Qiang ;
Zhang, Yu ;
Wang, Z. Jane .
IEEE SENSORS JOURNAL, 2019, 19 (19) :8420-8431
[5]   INDEPENDENT COMPONENT ANALYSIS, A NEW CONCEPT [J].
COMON, P .
SIGNAL PROCESSING, 1994, 36 (03) :287-314
[6]   Age-dependent electroencephalogram (EEG) patterns during sevoflurane general anesthesia in infants [J].
Cornelissen, Laura ;
Kim, Seong-Eun ;
Purdon, Patrick L. ;
Brown, Emery N. ;
Berde, Charles B. .
ELIFE, 2015, 4 :1-25
[7]   Canonical correlation analysis applied to remove muscle artifacts from the electroencephalogram [J].
De Clercq, Wim ;
Vergult, Anneleen ;
Vanrumste, Bart ;
Van Paesschen, Wim ;
Van Huffel, Sabine .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2006, 53 (12) :2583-2587
[8]   Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis [J].
Delorme, Arnaud ;
Sejnowski, Terrence ;
Makeig, Scott .
NEUROIMAGE, 2007, 34 (04) :1443-1449
[9]   Using ICA for removal of ocular artifacts in EEG recorded from blind subjects [J].
Flexer, A ;
Bauer, H ;
Pripfl, J ;
Dorffner, G .
NEURAL NETWORKS, 2005, 18 (07) :998-1005
[10]   EEG-Based Mobile Robot Control Through an Adaptive Brain-Robot Interface [J].
Gandhi, Vaibhav ;
Prasad, Girijesh ;
Coyle, Damien ;
Behera, Laxmidhar ;
McGinnity, Thomas Martin .
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2014, 44 (09) :1278-1285