Stress State Assessment by Complexity and Entropy

This paper focus on the stress assessment by electroencephalograph(EEG) analysis. The KC complexity, Approximate Entropy and Wavelet Entropy were extracted and analyzed of the EEG data as the features of stress state. The game "Fruit Ninja" was selected as the stress stimuli, and 92 groups EEG data that from eight subjects were collected. Then, the features were fused by the Optimal Support Vector Machine to assess the stress state. The results show that the highest accuracy is about 94%, and average accuracy of stress assessment is 82%, and the level of sensitivity to stress is different between the two brain regions. The left hemisphere is more sensitive to stress than the right one.