Entropy Analysis of brain activity in emotional stress assessment

This paper proposes an emotional stress assessment system using EEG signals, therefore a new approach to emotional stress state analysis by approximate and wavelet entropy is described in this paper. We designed an efficient acquisition protocol to acquire the EEG signals in five channels (FP1, FP2, T3,T4 and Pz), under pictures induction environment (calm-neutral and negative excited) for participants.After a brief introduction to the concept, the approximate entropy (ApEn) and wavelet entropy (WE) were extracted from two different EEG time series. The result showed that the classification accuracy in two emotional stress states was 73.25% using the support vector machine (SVM) classifier. The simulations showed that the classification accuracy is good and the proposed methods are effective.

Keywords:

Approximate Entropy , Complexity , EEG signals , Emotional Stress , Wavelet Entropy