基于脑电的意识活动特征提取与识别

Mental task classification based on adaptive autoregressive model and support vector machine

基于脑电信号的非平稳特性,用自适应自回归模型(AAR)提取脑电信号的特征,利用该模型对同一实验对象的两种不同意识任务的脑电信号进行特征提取,并将AAR模型得到的特征与支持向量机(SVM)分类器相结合,作为支持向量机的输入进行训练和测试,取得了良好的识别效果.实验结果证明,支持向量机分类器用于不同意识任务分类效果很好.

Considering the non -stationarity of EEG signals, AAR（ adaptive autoregressive） model is proposed to extract features from it, the model is applied to EEG signals recording from one subject performing two different mental tasks. The resulting features are sent to a surport vector machine （SVM） classifier, for training and testing,and the result is perfect. Experiments turn out that SVM classifier can get good results for different mental tasks classification.