| 运动意识任务的模式识别方法研究 |
| |
| 引用本文： | 徐宝国,宋爱国,费树岷.运动意识任务的模式识别方法研究[J].仪器仪表学报,2011,32(1). |
| |
| 作者姓名： | 徐宝国 宋爱国 费树岷 |
| |
| 作者单位： | 1. 东南大学仪器科学与工程学院,南京,210096
2. 东南大学自动化学院,南京,210096 |
| |
| 基金项目： | 国家863项目，国家自然科学基金 |
| |
| 摘 要： | 针对脑机接口研究中运动想象脑电信号的模式识别问题,提出了一种基于离散小波变换和AR双谱的特征提取方法.该方法首先利用Daubechies类小波函数对二路脑电信号进行3层分解,抽取小波系数的均值、能量均值、均方差三个特征;然后,采用5阶AR模型进行双谱估计,抽取双谱切片特征;最后,将这两类特征进行组合后使用马氏距离线性判别进行分类.利用BCI2003竞赛的标准数据,该方法使得EEG的识别正确率达到92.86%,与竞赛的最好结果(89.29%)相比提高了3.57%,为BCI研究中脑电信号的模式识别提供了有效的手段.
|
| 关 键 词： | 脑机接口 小波变换 AR双谱 运动想象 |
Pattern recognition method of motor imagery tasks |
| |
| Xu Baoguo,Song Aiguo,Fei Shumin.Pattern recognition method of motor imagery tasks[J].Chinese Journal of Scientific Instrument,2011,32(1). |
| |
| Authors: | Xu Baoguo Song Aiguo Fei Shumin |
| |
| Affiliation: | Xu Baoguo1,Song Aiguo1,Fei Shumin2(1.School of Instrument Science and Engineering,Southeast University,Nanjing 210096,China,2.School of Automation,China) |
| |
| Abstract: | Aiming at the issue of motor imagery electroencephalography(EEG) pattern recognition in the research of brain-computer interface(BCI),a novel feature extraction method based on discrete wavelet transform(DWT) and autoregressive(AR) bispectrum is proposed.Firstly,two-channel EEG signals are decomposed to three levels using Daubechies wavelet function.Secondly,the mean,average power and standard deviation of the wavelet coefficients are computed.Thirdly,bispectrum is estimated using fifth-order AR model and d... |
| |
| Keywords: | brain-computer interface wavelet transform AR bispectrum motor imagery |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
