基于PNN神经网络的EEG信号分类方法研究

Classification for EEG Signals of Different Mental Tasks Based on PNN Neural Network

主要对不同思维脑电信号运用时域回归方法进行预处理,然后用AR模型提取特征,最后应用PNN算法对AR系数特征进行分类.实验表明,此方法可以达到很好的分类效果.

Through time-domain regression method for EEG Denoising pretreatment,AR model coefficient is extracted as feature vector,and classifies the mental tasks based on PNN network.According to the an analysis and experiment results,the method can get high correct rate of Classification.