期刊文献+

基于ELM运动想象脑电信号的分类 被引量:7

CLASSIFICATION OF MOTOR IMAGERY ELECTROENCEPHALOGRAM BASED ON ELM
下载PDF
导出
摘要 针对运动想象脑电信号的分类识别,提出一种基于小波变换和共空间模式滤波的方法进行特征提取。对EEG进行3层小波分解,提取相关层数小波系数的特征量;同时利用共空间模式对EEG进行空间滤波,提取其转换后信号的方差作为特征量,并将这两类特征量进行组合。该方法结合了时频域和空间域的特征信息,可提高分类识别的效果。最后选取BCI2003中Data setⅢ数据作为样本,分别用极限学习机和基于粒子群算法的支持向量机进行分类识别。实验结果表明极限学习机分类学习时间较快,最优识别率为94.2857%,证明了该方法更适用于脑机接口系统。 In this paper,a proposed method has been introduced to classify the motor imagery EEG,whose features are extracted by using discrete wavelet transform and CSP. The EEG signal is decomposed to three levels and the statistics of wavelet coefficients of correlative level are calculated. Meanwhile,CSP is applied to EEG for space filtering and the variance of converted data is extracted as the features vector.Then the two characteristic quantities are combined. This method combines the features of frequency domain and spatial domain to improve the recognition performance. Finally,using Data set Ⅲ from BCI2003 as the sample to classify this method by using extreme learning machine and support vector machine which is based on particle swarm algorithm. The classification results show that the ELM needs less time to classify and the method obtains the best recognition accuracy at 94. 2857,which proves the method is more adaptable to brain computer interface system.
出处 《计算机应用与软件》 CSCD 2016年第10期187-190,206,共5页 Computer Applications and Software
基金 浙江省自然科学基金项目(LY12F03013) "十二五"浙江省高校重中之重学科-仪器科学与技术学生开放实验项目(JL150527)
关键词 运动想象 小波变换 共空间模式 支持向量机 极限学习机 Motor imagery Wavelet Transform Common spatial patterns Support vector machine Extreme learning machine
  • 相关文献

参考文献13

  • 1Gao Shangkai,Wang Yijun,Gao Xiaorong.Visual and auditory braincomputer interfaces[J].IEEE Transactions on Biomedical Engineering,2014,61(5):1436-1447.
  • 2Li X,Wang Y R,Song J L,et al.Research on classification method of combining support vector machine and genetic algorithm for motor imagery EEG[J].Journal of Computational Information Systems,2011,7(12):4351-4358.
  • 3Esposito M,Carotenuto M.Intellectul disabilities and power spectra analysis during sleep:a new perspective on borderline intellectual functioning[J].Journal of intellectual disability research,2014,58(5):421-429.
  • 4Thanh Nguyen,Khosravi Abbas,Creighton Douglas,et al.EEG signal classification for BCI applications by wacelets and interval type-2 fuzzy logic systems[J].Expert Systems With Applications,2015,42(9):615-624.
  • 5Han M,Sun L L.EEG signal classification for epilepsy diagnosis based on AR model and RVM[C]//2010 International Conference on Intelligent Control and Information Processing.Da Lian,Liaoning,China:Wang Jun,Han Min,2010:134-139.
  • 6Hsu Weiyen.Embedded prediction in feature extraction:Application to single-trail EEG discrimination[J].Clinical EEG and Neuroscience,2013,44(1):31-38.
  • 7Rosso O A,Martin M T,Figliola A,et al.EEG analysis using wavelet based information tools[J].Journal of Neuroscience Methods,2006,153(2):163-182.
  • 8赵建林,周卫东,刘凯,蔡冬梅.基于SVM和小波分析的脑电信号分类方法[J].计算机应用与软件,2011,28(5):114-116. 被引量:15
  • 9Tomida Naoki,Tanaka Toshihisa,Ono Shunsuke,et al.Active data selection for motor imagery EEG classification[J].IEEE Transactions on Biomedical Engineering,2015,62(2):458-467.
  • 10Vong Chi Man,Tai Keng Lam,Pun Chin Man,et al.Fast and accurate face detection by sparse Bayesian extreme learning machine[J].Neural Computing&Appplications,2015,26(5):1149-1156.

二级参考文献44

共引文献69

同被引文献40

引证文献7

二级引证文献16

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部