基于脑电信号的思维任务分类

Classification for Different Mental Tasks Based on EEG Signals

脑电信号(EEG)是研究脑活动的一种重要的信息来源,基于脑电信号的人与计算机的通信已成为一种新的人机接口方式。文中主要对不同心理作业的思维脑电信号运用独立分量分析进行预处理,然后采用AR模型提取特征,最后应用BP神经网络对AR系数特征进行训练和分类。实验表明,此方法可以达到很好的分类效果。

Electroeneephalogram （EEG） signal is an important information source of underlying brain processes. The communication based on EEG between human brain and computer is a new modlity of human- computer interaction. EEG signal of different mental tasks is preprocessed by independent component anlysis（ICA）. AR model coefficient is extracted as feature vector, and classifies the mental tasks based on BP network. According to the analysis and experiment results,the method can get high correct rate of Classification.