中文摘要：

为了实现脑-计算机接口(Brain-computer interface,BCI)系统,对运动脑电信号的特征进行了提取和分类。将多路脑电信号进行CAR(Common average reference)滤波后,利用小波变换和AR参数模型提取特征并使用基于马氏距离的线性判别分析对运动脑电信号进行分类。结果表明,该方法提取的特征向量较好地反应了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,为BCI研究中脑电信号的模式识别提供了有效的手段。

英文摘要：

To realize the brain-computer interface(BCI) system,features of motor electroence phalogram(EEG) are extracted and classified.Firstly,the multi-channel EEG signals are filtered by the common average reference(CAR) method.And then wavelet coefficients and the autoregressive parameter model are used to extract features,and the linear discriminate analysis based on the mahalanobis distance is utilized to classify the motor EEG.Results show that the eigenvector extracted by the method can reflect the process of...