CSSD＋AAR模型在脑电信号处理中的应用

针对BCI技术中的脑电信号处理方法和事件相关去同步化的特点，提出了一种结合时、频、空域的特征提取方法。结合CSSD和AAR模型来提取脑电特征，并对基于AAR模型系数的特征提取方法进行了探讨，最终选择卡尔曼平滑算法提取模型系数，然后将提取的特征用简单的线性分类器进行分类。实验结果表明测试集的分类正确率达到了94．08％，而且这种特征提取方法有很好的时间分辨率，适合于在线分类。这是一种正确率高，时间分辨率高，适合在线分类的好方法。

Application of CSSD and AAR in EEG Signal Processing

Identification and classification technology plays an important role in the study of brain computer interface （BCI） system. In this paper, a new algorithm is proposed to deal with the complex brain signals, extract features and classify single-trial electroencephalogram （EEG）. The proposed algorithm combines CSSD algorithm and adaptive autoregressive （AAR） model with linear discrimination analysis to extract features from multi-channel EEG. This algorithm is applied to Data Set I of BCI Competition III. The experiment results show that the proposed method could classify EEG signals with high accuracy.