中文摘要：

研究基于脑电信号排列组合熵的运动意识任务自动分类方法。求出时变脑电信号所对应的排列组合熵时间序列,它能很好的反映出事件相关去同步（ERD）和事件相关同步（ERS）现象,因此能有效地提取人脑想象左右手运动任务时的特征,最终利用K-近邻法模式分类方法对想象左右手运动任务进行分类决策。对国际脑机接口竞赛相关数据进行测试,最高准确率达到88.57%,最大互信息达到0.42。基于排列组合熵的脑电信号特征,可以作为脑电意识任务的有效分类依据。

英文摘要：

To present a new application of permutation entropy method for automatic brain consciousness task classification. The permutation entropy feature effectively reflected ERD/ERS time course changes, and used as feature parameters for the left and right hand motor imaginary. Finally, K-neighbors pattern recognition method was applied to optimal decision. The experiment data from BCI competition was analyzed, and classification was made, the maximum rate of accuracy was up to 88. 57%, and maximum mutual information was up to 0. 42. Based on the permutation entropy of EEG signals, consciousness task classification can be made effectively.