摘要
提出了一种基于ICA和局部能量最大的单次自动提取脑电信号中N2和P3成分的方法。实验采集了七名健康受试者在观察"模拟阅读"刺激界面状态下的32导的脑电信号,利用Fast ICA算法对单试次脑电信号进行盲源分离,将得到的32个分量用样本方差最大方法,在固定时间段自动提取脑电信号中N2和P3成分。把N2、P3分量直接作为单次提取的特征,利用支持向量机进行分类,同时和最优单通道时域特征的分类进行对比。结果表明:基于ICA方法可以有效地自动提取单次脑电信号中N2和P3成分,且分类效果比最优单通道有显著提高。
This paper introduces a method of single automatically extract EEG of N2 and P3 component based on ICA and big-gest local energy. Experiment collectes seven healthy people 32 lead EEG in the state of observed at"Imitating-Reading"stimula-tion interface. Firstly,single trial EEG is taken into blind source separation using the Fast ICA algorithm to 32 component result. Sec-ondly,automatic extraction N2 and P3 components in the 32 component result at the fixed time period,using maximum sample vari-ance method. The N2,P3 component directly are as a single extraction feature and SVM classification method is used to classify,atthe same time compared with the classification that using characteristics parameters of best single-channel in the time-domain. Theresults indicate that using automatic extraction of a single EEG N2 and P3 component based on ICA method is effective and classification results has risen considerably than the best single channel.
引文
[1]Arnold N,Tapios S.Estimation of parameters and eigen2modes of multivariate autoregressive models[J].ACMTrans2 actions on Mat hematical Software,2001,27(1):27257.
[2]罗志增,李文国.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(4):823-827.LUO Zhizeng,LI Wenguo.A Method of Mu Iti-Channe IEMG Disposa I Based On Wavelet Transform and BIindSigna I Separation[J].Chinese Journal of electronics,2009,37(4):823-827.
[3]Aviyente S,Bernat E M,Malone S M,et al.Time-Frequen-cy Data Reduction for Event Related Potentials:Combin-ing Principal Component Analysis and Matching Pursuit[J].Eurasip Journal on Advances in Signal Processing,2010(1):1-13.
[4]Feng Z.Intelligent diagnosis on ERP performance by us-ing classified wavelet neural network[J].Computer Engi-neering&Applications,2010.
[5]Hironaga N,Ioannides A A.Localization of individual areaneuronal activity[J].Neuroimage,2007,34(4):1519-34.
[6]陈洪波,李蓓蕾,陈真诚.基于ICA的脑电信号P300少次自动提取[J].电子学报,2012,40(6):1257-1262.CHEN Hongbo,LI Beilei,CHEN Zhencheng.Automatical-ly Extract P300 Within Several Trials from EEG Based onICA[J].Chinese Journal of electronics,2012,40(6):1257-1262.
[7]张宇,张建华,王行愚,等.基于Fast ICA的P300电位快速提取方法[J].华东理工大学学报:自然科学版,2009,35(5):750-755.ZHANG Yu,ZHANG Jianhua,WANG Xingyu,et al.A Fas-t ICA-based Approach to Extracting P300 Potential[J].Journal of East China University of Science and Technolo-gy(Natural Science Edition),2009,35(5):750-755.
[8]万柏坤,杨建刚,綦宏志,等.基于扩展Infomax ICA的ERP少次提取方法研究[J].北京生物医学工程,2005,24(4):241-245.WAN Baikun,YANG Jiangang,QI Hongzhi,et al.Studyon the Several Trials Extraction of ERP Based on Extend-ed-lnfomax ICA[J].Beijing Biomedical Engineering,2005,24(4):241-245.
[9]官金安.脑—机接口及其信号的单次提取[D].武汉:华中科技大学,2005.GUAN Jinan.Brain-Computer Interface and the Sin-gle-Trial Estimaion of its communication Carriers[D].Wu-han:Huazhong University of Science and Technology,2005.
[10]官金安,陈亚光.脑控双页虚拟键盘的设计与性能分析[J].中国临床康复,2006,10(9):124-126.GUAN Jinan,CHEN Yaguang.Design and performanceanalysis of mental controlled dual virtual keyboard[J].Chinese Journal of Clinical Rehabilitaion,2006,10(9):124-126.
[11]谢水清,杨阳,杨仲乐.脑-机接口中高性能虚拟键盘的实现[J].中南民族大学学报:自然科学版,2004,23(2):38-40.XIE Shuiqing,YANG Yang,YANG Zhongle.Implemen-tation of Virtual Keyboard in Brain-Computer Interfacewith Direct X[J].Journal of South-Central University forNationalities(Natural Science Edition),2004,23:38-40.
[12]GAO W,GUAN J A,GAO J,et al.Multi-ganglion ANNbased feature learning with application to P300-BCI sig-nal classification[J].Biomedical Signal Processing&Control,2015,18:127-137.
[13]贾贝.在线IR_BCI系统软件设计[D].武汉:中南民族大学,2015.JIA Bei.The Software Design of Online IR_BCI System[D].Wuhan:South-central University For Nationalities,2015.
[14]吴小培,冯焕清,周荷琴,等.独立分量分析及其在脑电信号预处理中的应用[J].北京生物医学工程,2001,20(1):35-37.WU Xiaopei,FENG Huanqing,ZHOU Heqin,et al.D In-dependent Component Analysis and Its Application forPreprocessing EEG[J].Beijing Biomedical Engineering,2001,20(1):35-37.
[15]李梅.模拟阅读BCI信号空时特征提取与模式识别[D].武汉:中南民族大学,2013.LI Mei.EEG Spatial-temperal feature extraction andclassification for Imitating Reading based BCI[D].Wu-han:South-central University For Nationalities,2013.
[16]Sitaram R,Zhang H,Guan C,et al.Temporal classifica-tion of multichannel near-infrared spectroscopy signalsof motor imagery for developing a brain-computer inter-face[J].Neuroimage,2007,34(4):1416-27.