摘要
在脑机接口研究中,针对脑电特征抽取,提出一种基于小波包最优基分解的方法.依据距离准则,从小波包库中选择一个对分类最优的小波包基;在该小波包基包含的所有分解系数中,抽取部分具有最大可分性的系数作为有效特征;不同通道脑电信号有效特征的结合,构成分类的特征矢量.通过对该特征矢量可分性和识别精度两个性能指标的评估,并与现有分类结果进行比较,表明了所提出方法的有效性.
In the study of brain-computer interfaces, a method based on best basis of wavelet packet decomposition was proposed. The method is used for the feature extraction of electroencephalogram. The best basis of wavelet packet is selected from wavelet packet library according to the distance criterion. The wavelet packet basis contains many decomposition coefficients, parts of which with maximal separability are extracted as effective features. The eigenvector is obtained by combining the effective features of electroencephalograph signals from different channels. The performance of the eigenvector was evaluated via two indexes of separability and recognition accuracy. Furthermore, compared with the existing classification results, the effectiveness of the proposed method was demonstrated.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2005年第11期1879-1882,共4页
Journal of Shanghai Jiaotong University
关键词
脑机接口
小波包分解
脑电
特征抽取
最优基
brain-computer interface (BCI)
wavelet packet decomposition (WPD)
electroencephalogram(EEG)
feature extraction
best basis