Feature Extraction of Mental Task Based on the Method of Sample Entropy
Guizhi Xu · Microcomputer Information · 2008
In this paper, a nonlinear dynamic method called Sample Entropy (SampEn) was applied to extract the feature of EEG signals got from five different mental tasks, thereafter a three-layer BP neural network classifier was applied to classify the feature extracted. The results show that it gets better effect for classifying mental task to extract the feature by sample entropy. Due to simply calculation and steady result, sample entropy has its high practical value in the field of brain computer interface (BCI).