Abstract：The positive correlation is known between the four rhythms of human Electroencephalogram (EEG) signals, i.e. δ wave, θ wave, α wave and β wave, and the human mental stress statements. So the energy values of the four rhythms of EEG, together with their nonlinear parameters, are used to evaluate the mental stress statements. In this paper, the four rhythms of EEG is firstly reconstructed by using of the technique of wavelet package transformation, where a 6-level-frame is achieved to decompose the original EEG signal with the help of the mother wavelet function of “db20”. Then, the corresponding frequency-band energy ratio (FBER) of each rhythm is calculated and used to estimate the statement of mental stress quantitatively. Some nonlinear parameters of the α wave, including maximum Lyapunov exponent, approximated entropy and complexity degree, are also calculated and a synthesized evaluating criterion is combined to determine the mental stress statement. The proposed method is confirmed to be effective with 10 sets of EEG data, in which the accuracy is high when evaluating those of fatigue or non-fatigue states, meanwhile it is not so better to identify the different mental stress states of weak, middle and serious fatigue.
韩清鹏 . 利用EEG信号的小波包变换与非线性分析实现精神疲劳状态的判定[J]. , 2013, 32(2): 182-188.
Han Qingpeng. Evaluation of Human Mental Stress Statements Based on Wavelet Package Transform and Nonlinear Analysis of EEG Signals. , 2013, 32(2): 182-188.
2013, Vol. 32 
