去除癫痫脑电信号运动伪迹的变分模态分解-自适应熵阈值方法

张力行; 张四聪; 徐光华; 李焕发; 吴永程

doi:10.7652/xjtuxb202201008

您当前的位置：

首页 >

文章列表页 >

去除癫痫脑电信号运动伪迹的变分模态分解-自适应熵阈值方法

更新时间：2025-05-08

- 去除癫痫脑电信号运动伪迹的变分模态分解-自适应熵阈值方法
- Variational Modal Decomposition-Adaptive Entropy Threshold Method for Electroencephalogram Motion Artifact Removal in Epileptic Seizure
- 西安交通大学学报 2022年56卷第1期页码：70-78
- 作者机构：
  
  西安交通大学机械工程学院,西安,712000
- 作者简介：
- 基金信息：
  
  : 2021-06-02。作者简介: 张力行(1997—),女,硕士生;张四聪(通信作者),女,副教授,硕士生导师。基金项目: 国家自然科学基金资助项目(51775415)
- DOI：10.7652/xjtuxb202201008
  中图分类号： TN386.1
- 网络首发：2022-01-10，
  
  纸质出版：2022
- 稿件说明：
移动端阅览
张力行, 张四聪, 徐光华, 等. 去除癫痫脑电信号运动伪迹的变分模态分解-自适应熵阈值方法[J]. 西安交通大学学报, 2022,56(1):70-78.

Variational Modal Decomposition-Adaptive Entropy Threshold Method for Electroencephalogram Motion Artifact Removal in Epileptic Seizure[J]. 2022, 56(1): 70-78.
张力行, 张四聪, 徐光华, 等. 去除癫痫脑电信号运动伪迹的变分模态分解-自适应熵阈值方法[J]. 西安交通大学学报, 2022,56(1):70-78. DOI： 10.7652/xjtuxb202201008.

Variational Modal Decomposition-Adaptive Entropy Threshold Method for Electroencephalogram Motion Artifact Removal in Epileptic Seizure[J]. 2022, 56(1): 70-78. DOI： 10.7652/xjtuxb202201008.

摘要

针对癫痫发作前期脑电信号中含有运动伪迹影响癫痫预测的问题

提出一种变分模态分解-自适应熵阈值(VMD-AET)的运动伪迹去除方法。设计了实验室环境下8种模拟运动状态

分析不同运动状态下脑电信号的变化规律; 利用VMD方法获得脑电信号各频带的变分模态分量

对分量进行能量熵求解和排序; 采用不同的熵阈值进行运动状态下伪迹分量的去除

比较得到能量熵的最优阈值

得到不含运动伪迹的脑电信号; 采用Matlab软件使用VMD-AET方法实现了脑电信号中运动伪迹的有效去除。实验结果表明:每种运动状态均能达到去伪迹效果

在跑步时伪迹去除率和信噪比提升最高; 对癫痫病人发作前期脑电信号的伪迹去除率为5.54%

信噪比提升达到10.35 dB; 与常用的独立成分分析和经验模式分解的阈值法进行对比

所提VMD-AET方法的伪迹去除率和信噪比提升了1.47%和3.36 dB

可满足对移动脑电运动干扰的预处理要求。

Abstract

A method called Variational Modal Decomposition-Adaptive Entropy Threshold(VMD-AET)is proposed aiming at solving the problem that the electroencephalographic(EEG)signal in pre-seizure contains motion artifacts

which affects the prediction of epilepsy. Firstly

eight simulated motion states in the laboratory environment are designed in order to analyze the variation rule of EEG signals under different motion states. Secondly

the variational modal function(VMF)of different frequency band is obtained by VMD

and the components are solved and sorted by energy entropy. Finally

different entropy thresholds are used to remove the artifacts in the moving state and the optimal threshold is obtained by comparison

and the EEG signals without motion artifact are obtained. The motion artifact can be removed effectively by VMD-AET method via the software Matlab. Experiment results show that motion artifacts in each motion state can be removed effectively

and the artifact removal rate and signal-to-noise ratio reach their maximum during running. The motion artifacts in the EEG signals of epileptic patients are effectively removed. The artifact removal rate of EEG signals of the patients in pre-seizure is 5. 54%

and the signal-to-noise ratio increases to 10.35 dB. By comparing our method with the independent component algorithm(ICA)and the empirical mode decomposition(EMD)threshold value method

the VMD-AET method's artifact removal rate and signal-to-noise ratio are improved by 1.47% and 3.36 dB

respectively

which is suitable for the preprocessing of portable EEG system.

关键词

Keywords

references

黄帅, 杜云梅, 梁会营, 等. 基于EEG的癫痫发作预测当前研究与进展 [J]. 中国数字医学, 2019, 14(3): 73-76.

HUANG Shuai, DU Yunmei, LIANG Huiying, et al. Current research and development of prediction of epilepsy based on EEG [J]. China Digital Medicine, 2019, 14(3): 73-76.

ACHARYA U R, HAGIWARA Y, ADELI H. Automated seizure prediction [J]. Epilepsy and Behavior, 2018, 88: 251-261.

魏进莲, 黄丽华. 癫痫发作预测研究进展 [J]. 护理与康复, 2019, 18(6): 41-44.

WEI Jinlian, HUANG Lihua. Research progress on seizure prediction [J]. Journal of Nursing and Rehabilitation, 2019, 18(6): 41-44.

ISSA M F, JUHASZ Z. Improved EOG artifact removal using wavelet enhanced independent component analysis [J]. Brain Sciences, 2019, 9(12): 355.

YANG Banghua, ZHANG Tao, ZHANG Yunyuan, et al. Removal of electrooculogram artifacts from electroencephalogram using canonical correlation analysis with ensemble empirical mode decomposition [J]. Cognitive Computation, 2017, 9(5): 626-633.

王振宇. 脑电信号伪迹去除方法的研究与应用 [D]. 成都: 电子科技大学, 2013: 18-19.

刘窈窈. 基于可穿戴式脑电设备的情绪识别及APP实现 [D]. 南京: 东南大学, 2019: 3-4.

SÖZER A T, FIDAN C B. Emotiv epoc ile duragan hal görsel uyarilmii potansiyel temelli beyin bilgisayar arayüzü uygulamasi [J]. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 2019, 8(1): 158-166.

DALY I, NICOLAOU N, NASUTO S J, et al. Automated artifact removal from the electroencephalogram: a comparative study [J]. Clinical EEG and Neuroscience, 2013, 44(4): 291-306.

CHEN Xun, LIU Aiping, CHEN Qiang, et al. Simultaneous ocular and muscle artifact removal from EEG data by exploiting diverse statistics [J]. Computers in Biology and Medicine, 2017, 88: 1-10.

ISLAM M S, EL-HAJJ A M, ALAWIEH H, et al. EEG mobility artifact removal for ambulatory epileptic seizure prediction applications [J]. Biomedical Signal Processing and Control, 2020, 55: 101638.

DE CLERCQ W, VERGULT A, VANRUMSTE B, et al. Canonical correlation analysis applied to remove muscle artifacts from the electroencephalogram [J]. IEEE Transactions on Biomedical Engineering, 2006, 53(12): 2583-2587.

CHEN Xun, LIU Aiping, PENG Hu, et al. A preliminary study of muscular artifact cancellation in single-channel EEG [J]. Sensors, 2014, 14(10): 18370-18389.

KIM B H, JO S. Real-time motion artifact detection and removal for ambulatory BCI [C]∥ Proceedings of the 3rd International Winter Conference on Brain-Computer Interface. Piscataway, NJ, USA: IEEE, 2015: 1-4.

OLIVEIRA A S, SCHLINK B R, HAIRSTON W D, et al. A channel rejection method for attenuating motion-related artifacts in EEG recordings during walking [J]. Frontiers in Neuroscience, 2017, 11: 225.

SALAZAR A. Independent component analysis(ICA): algorithms, applications and ambiguities [M]. New York, USA: Nova Science Publishers, 2000: 411-430.

樊凤杰, 白洋, 纪会芳. 基于EEMD-ICA的脑电去噪算法研究 [J]. 计量学报, 2021, 42(3): 395-400.

FAN Fengjie, BAI Yang, JI Huifang. Denoising method of EEG signal based on EEMD-ICA [J]. Acta Metrologica Sinica, 2021, 42(3): 395-400.

唐贵基, 王晓龙. 变分模态分解方法及其在滚动轴承早期故障诊断中的应用 [J]. 振动工程学报, 2016, 29(4): 638-648.

TANG Guiji, WANG Xiaolong. Variational mode decomposition method and its application on incipient fault diagnosis of rolling bearing [J]. Journal of Vibration Engineering, 2016, 29(4): 638-648.

ZHANG Tao, CHEN Wanzhong, LI Mingyang. AR based quadratic feature extraction in the VMD domain for the automated seizure detection of EEG using random forest classifier [J]. Biomedical Signal Processing and Control, 2017, 31: 550-559.

DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition [J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.

ZHANG Tao, HAN Zhiwu, CHEN Xiaojuan, et al. Assessing multi-layered nonlinear characteristics of ECG/EEG signal via adaptive kernel density estimation-based hierarchical entropies [J]. Biomedical Signal Processing and Control, 2021, 67: 102520.

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(8): 177-184.

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(8): 177-184.

郑近德, 陈敏均, 程军圣, 等. 多尺度模糊熵及其在滚动轴承故障诊断中的应用 [J]. 振动工程学报, 2014, 27(1): 145-151.

ZHENG Jinde, CHEN Minjun, CHENG Junsheng, et al. Multiscale fuzzy entropy and its application in rolling bearing fault diagnosis [J]. Journal of Vibration Engineering, 2014, 27(1): 145-151.

张超, 陈建军, 郭迅. 基于EEMD能量熵和支持向量机的齿轮故障诊断方法 [J]. 中南大学学报(自然科学版), 2012, 43(3): 932-939.

ZHANG Chao, CHEN Jianjun, GUO Xun. Gear fault diagnosis method based on ensemble empirical mode decomposition energy entropy and support vector machine [J]. Journal of Central South University(Science and Technology), 2012, 43(3): 932-939.

ISLAM M K, RASTEGARNIA A, YANG Zhi. A wavelet-based artifact reduction from scalp EEG for epileptic seizure detection [J]. IEEE Journal of Biomedical and Health Informatics, 2016, 20(5): 1321-1332.

-------

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

频域注意力机制下的癫痫脑电信号分类

经验模态分解和Kolmogorov测度的癫痫预测算法

表情驱动下脑电信号的建模仿真及分类识别

结合运动想象和动作观察的伸-握动作识别方法

针对局灶性癫痫患者的脑电微状态分析