[1]杨磊,杨帆,何艳.采用样本熵自适应噪声完备经验模态分解的脑电信号眼电伪迹去除算法[J].西安交通大学学报,2020,54(08):177-184.[doi:10.7652/xjtuxb202008023]
 YANG Lei,YANG Fan,HE Yan.An Electroencephalogram Artifacts Removal Algorithm for Electroencephalogram Signals Based on Sample Entropy-Complete Ensemble Empirical Mode Decomposition with Adaptive Noise[J].Journal of Xi'an Jiaotong University,2020,54(08):177-184.[doi:10.7652/xjtuxb202008023]
点击复制

采用样本熵自适应噪声完备经验模态分解的脑电信号眼电伪迹去除算法
分享到:

《西安交通大学学报》[ISSN:0253-987X/CN:61-1069/T]

卷:
54
期数:
2020年第08期
页码:
177-184
栏目:
出版日期:
2020-08-10

文章信息/Info

Title:
An Electroencephalogram Artifacts Removal Algorithm for Electroencephalogram Signals Based on Sample Entropy-Complete Ensemble Empirical Mode Decomposition with Adaptive Noise
文章编号:
0253-987X(2020)08-0177-08
作者:
杨磊1 杨帆2 何艳12
1.西安邮电大学通信与信息工程学院, 710121, 西安; 2.贵州医科大学生物与工程学院, 550041, 贵阳
Author(s):
YANG Lei1 YANG Fan2 HE Yan12
1. School of Communications and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an 710121, China; 2. School of Biology and Engineering, Guizhou Medical University, Guiyang 550041, China
关键词:
脑电图 眼电伪迹 独立成分分析 自适应噪声完备经验模态分解 小波
Keywords:
electroencephalogram electroencephalogram artifact independent component analysis complete ensemble empirical mode decomposition with adaptive noise wavelet
分类号:
R318.04
DOI:
10.7652/xjtuxb202008023
文献标志码:
A
摘要:
针对脑电(EEG)信号容易被眼电(EOG)伪迹污染,而常规伪迹去除算法会导致EEG有用信息大量丢失的问题,提出一种采用样本熵完备经验模态分解的EOG伪迹去除算法。首先,利用独立成分分析(ICA)算法将EEG分解为独立分量; 然后,对各独立分量进行样本熵分析,接着引入阈值对伪迹分量进行自动识别,识别后的伪迹分量经过自适应噪声完备经验模态分解(CEEMDAN)算法分解后采用小波阈值降噪; 最后采用逆CEEMDAN和逆ICA算法重构信号,达到伪迹去除的目的。采用公开的BCI2000运动想象数据集中60组数据进行实验,结果表明,所提算法的EOG伪迹自动识别正确率达80%,比基于峰度的伪迹识别算法提高约26.7%; 采用公开的Klados EEG数据集中15组数据进行实验,结果表明,重构后的EEG信号与纯净的EEG信号的相关系数为0.841,均方根误差较受污染信号降低约56.82%。实验结果证明了所提算法在提高伪迹去除能力的同时能够有效保留有用脑电信息。
Abstract:
An improved algorithm for removing electroencephalogram(EEG)artifacts based on sample entropy is proposed to solve the problem that EOG signals are easily polluted by electroencephalography(EOG)artifact, and conventional artifact removal algorithms lead to a large amount loss of useful EEG information. At first, EEG is decomposed into independent components by an independent component analysis(ICA)algorithm, then, sample entropy analysis for each independent component is employed. Then a threshold value is introduced to automatically identify the artifact component. The identified artifact component is decomposed by the complete ensemble empirical mode decomposition algorithm with adaptive noise(CEEMDAN), and then is denoised by the wavelet transform. Finally, both the inverse CEEMDAN and the inverse ICA algorithms are used to reconstruct the signal to achieve the purpose of artifact removal. Experiments are performed using 60 sets of data in the public BCI2000 motion imagination data set. Results show that the accuracy of automatic identification of EOG artifacts is 80%, and is about 26.7% higher than kurtosis-based algorithms. Experiment results performed on 15 sets of data in the public Klados EEG data set show that the correlation coefficient between the reconstructed EEG signal and the pure EEG signal is 0.841, and the root mean square error is reduced by about 56.82% compared with contaminated EEG signals. It is proved that the proposed algorithm achieves high performance not only in artifact removal but also in useful EEG information retainment.

参考文献/References:

[1] 王栋, 李扩, 刘晓芳, 等. 利用高频脑电的局灶性癫痫患者癫痫发作检测 [J]. 西安交通大学学报, 2018, 52(2): 148-154.
WANG Dong, LI Kuo, LIU Xiaofang. Seizuer detection in focal epilepsy patients using high frequency EEG signal [J]. Journal of Xi'an Jiaotong University, 2018, 52(2): 148-154.
[2] BAJAJ N, CARRIÓN J R, BELLOTTI F, et al. Automatic and tunable algorithm for EEG artifact removal using wavelet decomposition with applications in predictive modeling during auditory tasks [J]. Biomedical Signal Processing and Control, 2020, 55: 101624.
[3] MANNAN M M N, KAMRAN M A, JEONG M Y. Identification and removal of physiological artifacts from electroencephalogram signals: a review [J]. IEEE Access, 2018, 6: 30630-30652.
[4] CHEN X, XU X, LIU A, et al. Removal of muscle artifacts from the EEG: a review and recommendations [J]. IEEE Sensors Journal, 2019, 19(14): 5353-5368.
[5] JIANG X, BIAN G B, TIAN Z. Removal of artifacts from EEG signals: a review [J]. Sensors, 2019, 19(5): 987.
[6] ISSA M F, TUBOLY G, KOZMANN G, et al. Automatic ECG artefact removal from EEG signals [J]. Measurement Science Review, 2019, 19(3): 101-108.
[7] HAREZLAK K, KASPROWSKI P. Application of time-scale decomposition of entropy for eye movement analysis [J]. Entropy, 2020, 22(2): 168.
[8] MAMMONE N, LA FORESTA F, MORABITO F C. Automatic artifact rejection from multichannel scalp EEG by wavelet ICA [J]. IEEE Sensors Journal, 2011, 12(3): 533-542.
[9] CHEN X, CHEN Q, ZHANG Y, et al. A novel EEMD-CCA approach to removing muscle artifacts for pervasive EEG [J]. IEEE Sensors Journal, 2018, 19(19): 8420-8431.
[10] HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [EB/OL]. [2019-08-28]. https:∥royalsocietypub lishing.org/doi/pdf/10.1098/rspa.1988.0193.
[11] TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al. A complete ensemble empirical mode decomposition with adaptive noise [C]∥2011 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ, USA: IEEE, 2011: 4144-4147.
[12] 罗志增, 严志华, 傅炜东. 基于CEEMDAN-ICA的单通道脑电信号眼电伪迹滤除方法 [J]. 传感技术学报, 2018, 31(8): 75-80.
LUO Zhizeng, YAN Zhihua, FU Weidong. Electroencephalogram artifact filtering method of single channel EEG based on CEEMDAN-ICA [J]. Chinese Journal of Sensors and Actuators, 2018, 31(8): 75-80.
[13] ZHANG H, HE S. Analysis and comparison of permutation entropy, approximate entropy and sample entropy [C]∥2018 International Symposium on Computer, Consumer and Control. Piscataway, NJ, USA: IEEE, 2018: 209-212.
[14] HU Y, ZONG X, SHE J, et al. Denoising sEMG signals using the combination of complementary EEMD with adaptive noise and improved threshold [C]∥2019 IEEE International Conference on Industrial Cyber Physical Systems. Piscataway, NJ, USA: IEEE, 2019: 821-826.
[15] KLADOS M A, BAMIDIS P D. A semi-simulated EEG/EOG dataset for the comparison of EOG artifact rejection techniques [J]. Data in Brief, 2016, 8: 1004-1006.
[16] SCHALK G, MCFARLAND D J, HINTERBERGER T, et al. BCI2000: a general-purpose brain-computer interface(BCI)system [J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 1034-1043.
[17] VIJAYASANKAR A, KUMAR P R. Correction of blink artifacts from single channel EEG by EMD-IMF thresholding [C]∥2018 Conference on Signal Processing And Communication Engineering Systems. Piscataway, NJ, USA: IEEE, 2018: 176-180.
[18] DONOHO D L. De-noising by soft-thresholding [J]. IEEE Transactions on Information Theory, 1995, 41(3): 613-627.
[19] 詹展, 秦会斌. 基于新阈值函数的小波阈值去噪算法 [J]. 计算机技术与发展, 2019, 29(11): 47-51.
ZHAN Zhan, QIN Huibin. A wavelet threshold denoising algorithm based on new threshold function [J]. Computer Technology and Development, 2019, 29(11): 47-51.
[20] ISLAM K A, TCHESLAVSKI G V. Independent component analysis for EOG artifacts minimization of EEG signals using kurtosis as a threshold [C]∥2015 2nd International Conference on Electrical Information and Communication Technologies. Piscataway, NJ, USA: IEEE, 2015: 137-142.
[21] 李明爱, 刘帆. 脑电中眼电伪迹的自动识别与去除 [J]. 北京生物医学工程, 2018, 37(6): 559-565.
LI Ming'ai, LIU Fan. The automatic identification and removal of ocular artifacts from EEG [J]. Beijing Biomedical Engineering, 2018, 37(6): 559-565.
[22] ZENG K, CHEN D, OUYANG G, et al. An EEMD-ICA approach to enhancing artifact rejection for noisy multivariate neural data [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2015, 24(6): 630-638.
[23] JUNG T P, MAKEIG S, WESTERFIELD M, et al. Removal of eye activity artifacts from visual event-related potentials in normal and clinical subjects [J]. Clinical Neurophysiology, 2000, 111(10): 1745-1758.

备注/Memo

备注/Memo:
收稿日期: 2019-11-28。作者简介: 杨磊(1996—),女,硕士生; 何艳(通信作者),女,副教授。基金项目: 国家自然科学基金资助项目(81460206,81660298); 陕西省自然科学基础研究计划资助项目(2019JQ861)。
更新日期/Last Update: 2020-08-10