中文摘要：

为了实现脑-计算机接口（brain—computer interface，BCI）系统，对大脑C3，C4处采集的二路运动想象脑电信号的特征进行了提取和分类。在分析小波包频带划分特点的基础上，利用小波包能量进行特征提取并使用基于马氏距离的线性判别分析进行了左右手运动想象模式分类，结果表明该方法提取的特征向量较好的反映了运动想象脑电信号的事件相关去同步（event—related desynchronization，ERD）和事件相关同步（event—related synchronization，ERS）的变化时程。另外，该方法识别率高，适合脑-计算机接口的应用。

英文摘要：

In order to realize brain-computer interface （BCI） system, the features of motor imagery EEG signals sampled from the C3 and CZ positions of the brain were extracted and classified. Based on the analysis of the frequency band division characteristic of wavelet packet transform （ WPT）, the wavelet packet energy was used to extract the features and the linear discriminate analysis based on Mahalanobis distance was utilized to classify the pattern of left and right hand motor imagery. The results show that the eigenvector extracted by the proposed method effectively reflects the event-related desynchronization and event-related synchronization time course changes of motor imagery EEG. In addition, the proposed method can obtain high recognition rate and can be utilized in BCI system.