基于小波包分解的意识脑电特征提取

Imaginary EEG feature extraction based on wavelet packet decomposition

针对2种不同意识任务(想象左手运动和想象右手运动)的脑-机接口(brain-computer interface,BCI)设计,提出了基于小波包分解的特征提取方法。首先深入研究了小波包变换,结合事件相关去同步化(event-related desynchronization,ERD)/事件相关同步化(event-related synchronization,ERS)现象,提出以小波包分解系数来考虑特征,然后对C3、C4导联脑电信号进行小波包分解系数方差和相对能量2种特征的提取,最后采用最简线性分类器进行分类。结果表明,2种特征对应的最大分类正确率均达到了85%,对应时间分别为4.34 s和4.39 s。因此,在保证分类正确率的前提下,所提方法更加简单和有效,为大脑意识任务分类提供了新思路。

Aiming at the design of the brain-computer interface （BCI） for classifying different imagined movements of both left and right hands, a feature extraction method based on wavelet packet decomposition is proposed. Firstly, the wavelet packet transform is studied in depth and an idea of taking wavelet packet coefficients as the features is suggested based on event-related desynchronization/event-related synchronization （ERD/ERS） phenomena. Then, two EEG features of the variances and relative energies of the wavelet packet coefficients are extracted from the EEG signals of channels C3 and C4; and finally, the feature signals are classified using a most simple linear classifier The results show that the maximum classification accuracies of both features reach 85% , and the corresponding times are 4.34 s and 4.39 s, respectively. So, under the precondition of guaranteeing the classification accuracy, the proposed method is more efficient and simpler, which provides a new reference for brain imaginary task classification.