脑电信号多维特征融合与分类算法研究

doi:10.3778/j.issn.1002-8331.2012-0505

摘要/Abstract

摘要： 针对目前运动想象脑电信号特征提取单一，分类识别准确率低等现象，结合卷积神经网络分类器，提出了一种多维度特征加权融合的特征融合算法来提高运动想象脑电识别率。对预处理后的脑电信号进行小波包变换，提取其共空间特征、能量特征、边际谱熵特征以及非线性动力学特征，然后加权融合，使用卷积神经网络分类器分类。为验证算法的合理性，使用BCI-IV Dataset 2a数据集对提出的特征融合算法进行验证分析，结果表明，所提出的加权特征融合算法结合CNN分类器可以有效提高运动想象识别准确率。实验中，9位志愿者平均分类准确率达到75.88%，平均Kappa系数为0.70。

关键词: 脑机接口, 运动想象, 卷积神经网络, 小波包变换, 特征融合

Abstract: Aiming at the current phenomenon of single feature extraction of motor imagery EEG signals and low classification recognition rate, this paper combines the classifier of convolutional neural networks and proposes a feature fusion algorithm of multi-feature weighted fusion to improve motor imagery EEG recognition rate. It performs wavelet packet transform on the preprocessed EEG signals, extracts its common space features, energy features, marginal spectral entropy features and nonlinear dynamics features, then performs weighted fusion. Finally, the paper uses convolutional neural network classification to classify. To verify the rationality of the algorithm, it uses dataset which is the BCI-IV Dataset 2a to verify and analyze the proposed algorithm. The results show that the proposed weighted feature fusion algorithm with CNN classifier can effectively improve the recognition rate of motion imagination. In the experiments, the average classification accuracy of 9 volunteers is 75.88%, and the average Kappa coefficient is 0.70.

Key words: brain-computer interface, motor imagery, convolutional neural network, wavelet packet transform, feature fusion

朱永清, 王文格. 脑电信号多维特征融合与分类算法研究[J]. 计算机工程与应用, 2022, 58(13): 146-153.

ZHU Yongqing, WANG Wenge. Research on Multi-Dimensional Feature Extraction and Classification Algorithm of EEG Signal[J]. Computer Engineering and Applications, 2022, 58(13): 146-153.

参考文献

[1] NIJHOLT A，TAN D.Brain-computer interfacing for inte-lligent systems[J].IEEE Intelligent Systems，2008，23（3）：72-79.
[2] VOZNENKO T I，CHEPIN E V，URVANOV G A.The control system based on extended BCI for a robotic wheelchair[J].Procedia Computer Pence，2018，123：522-527.
[3] BIASIUCCI A，LEEB R，ITURRATE I，et al.Brain-actuated functional electrical stimulation elicits lasting arm motor recovery after stroke[J].Nature Communications，2018，9（1）：2421.
[4] LOBO-PRAT J，KOOREN P N，STIENEN A H，et al.Non-invasive control interfaces for intention detection in active movement-assistive devices[J].Journal of Neuroengineering & Rehabilitation，2014，11（1）：168.
[5] 李明爱，崔燕，杨金福，等.基于HHT和CSSD的多域融合自适应脑电特征提取方法[J].电子学报，2013（12）：2479-2486.
LI M A，CUI Y，YANG J F，et al.An adaptive multi-domain fusion feature extraction with method HHT and CSSD[J].Acta Electronica Sinica，2013（12）：2479-2486.
[6] CHEN S F，LUO Z Z，GAN H T.An entropy fusion method for feature extraction of EEG[J].Neural Computing & Applications，2018，29（10）：857-863.
[7] 杨默涵，陈万忠，李明阳.基于总体经验模态分解的多类特征的运动想象脑电识别方法研究[J].自动化学报，2017，43（5）：743-752.
YANG M H，CHEN W Z，LI M Y.Multiple feature extraction based on ensemble empirical mode decomposition for motor imagery EEG recognition tasks[J].Acta Automatica Sinica，2017，43（5）：743-752.
[8] FU K，QU J F，CHAI Y，et al.Classification of seizure based on the time-frequency image of EEG signals using HHT and SVM[J].Biomedical Signal Processing and Control，2014，13：15-22.
[9] LUO T J，ZHOU C L，CHAO F.Exploring spatial-frequency-sequential relationships for motor imagery classification with recurrent neural network[J].BMC Bioinformatics，2018，19（1）：344.
[10] COLLAZOS-HUERTAS D F，áLVAREZ-MEZA A M，ACOSTA-MEDINA C D，et al.CNN-based framework using spatial dropping for enhanced interpretation of neural activity in motor imagery classification[J].Brain Informatics，2020，7（1）：169-173.
[11] SHE Q，HU B，LUO Z，et al.A hierarchical semi-supervised extreme learning machine method for EEG recognition[J].Medical & Biological Engineering & Computing，2019，57（1）：147-157.
[12] LIN B，ZHANG W，ZHANG X.Feature extraction of motion imagination EEG based on S transform and CSP[C]//Proceedings of the 37th Chinese Control Conference（CCC），2018.
[13] 孙会文，伏云发，熊馨，等.基于HHT运动想象脑电模式识别研究[J].自动化学报，2015（9）：1686-1692.
SUN H W，FU Y F，XIONG X，et al.Identification of EEG induced by motor imagery based on Hilbert-Huang transform[J].Acta Automatica Sinica，2015（9）：1686-1692.
[14] JI N，MA L，DONG H，et al.EEG signals feature extraction based on DWT and EMD combined with approximate entropy[J].Brain Sciences，2019，9（8）：201.
[15] 杨帮华，章云元，李华荣，等.基于二阶盲辨识结合小波包的脑电信号预处理[J].上海交通大学学报，2015，49（12）：1900-1906.
YANG B H，ZHANG Y Y，LI H R，et al.Electroencephalography preprocessing method based on SOBI-WPD in brain computer interface[J].Journal of Shanghai Jiao Tong University，2015，49（12）：1900-1906.
[16] 袁瑞，魏庆国.基于小波包分解与近似熵的脑电特征提取方法研究及在脑机接口中的应用[J].南昌大学学报（理科版），2017，41（3）：282-287.
YUAN R，WEI G Q.The method for feature extraction of EEG signals based on wavelet packet decomposition and approximate entropy and its application in brain computer interfaces[J].Journal of Nanchang University（Natural Science），2017，41（3）：282-287.
[17] 于沐涵，陈峰.基于HCSP和模糊熵的脑电信号分类[J].计算机工程与设计，2018，39（2）：557-562.
YU M H，CHEN F.Classification of EEG signal based on HCSP and fuzzy entropy[J].Computer Engineering and Design，2018，39（2）：557-562.
[18] RICHMAN J S，MOORMAN J R.Physiological time-series analysis using approximate entropy and sample entropy[J].American Journal of Physiology，2000，278（6）：2039-2049.
[19] Graz University.BCI competition IV[DB/OL].[2020-12-15].
http：//www.bbci.de/competition/iv/#dataset2a.
[20] 何群，邵丹丹，王煜文，等.基于多特征卷积神经网路的运动想象脑电信号分析及意图识别[J].仪器仪表学报，2020，41（1）：138-146.
HE Q，SHAO D D，WANG Y W，et al.Analysis and intention recognition of motor imagery EEG signals based on multi-feature convolutional neural network[J].Chinese Journal of Scientific Instrument，2020，41（1）：138-146.
[21] MCFARLAND D J，MINER L A，VAUGHAN T M，et al.Mu and Beta rhythm topographies during motor imagery and actual movements[J].Brain Topography，2000，12（3）：177-186.
[22] 刘宝，唐雨琦，蔡梦迪，等.基于CSP-PSO-SVM的运动想象EEG信号特征提取与分类算法[J].中南大学学报（自然科学版），2020，51（6）：1551-1564.
LIU B，TANG Y Q，CAI M D，et al.EEG signal motion imagination feature extraction and classification algorithm based on CSP-PSO-SVM[J].Journal of Central South University（Science and Technology），2020，51（6）：1551-1564.
[23] SHAHTALEBI S，ASIF A，MOHAMMADI A.Siamese neural networks for EEG-based brain-computer interfaces[C]//Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society（EMBC） in Conjunction with the 43rd Annual Conference of the Canadian Medical and Biological Engineering Society，2020.