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

PDF(2609 KB)

振动与冲击 ›› 2013, Vol. 32 ›› Issue (2) : 182-188.

论文

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

韩清鹏

作者信息 +

Evaluation of Human Mental Stress Statements Based on Wavelet Package Transform and Nonlinear Analysis of EEG Signals

Han Qingpeng

Author information +

文章历史 +

摘要

EEG（脑电）信号的4个节律(δ波、θ波、α波、β波)与人的精神疲劳状态有对应关系，不同节律的能量值及其非线性特征参数可以用于疲劳状态的判定。本文首先利用小波包分解与重构技术，构造了以“db20”为基小波函数的6层分解，得到EEG信号的4个节律。然后，对4个节律信号分别计算相应的节律的频带能量比例值，这些频带能量比例值作为对人体精神状态进行评价的量化指标。通过计算EEG信号α波的非线性特征参数，包括最大Lyapunov指数、近似熵、复杂度，并将这些非线性特征参数组成疲劳状态的综合评估判据，可以实现疲劳状态的判定。10组EEG信号的分析结果表明了该本文方法的有效性，其中对疲劳和非疲劳状态的判定准确率较高，而对轻微疲劳、中等疲劳和严重疲劳三种状态的准确区分稍差一些。

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.

导出引用

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]. 振动与冲击, 2013, 32(2): 182-188

Han Qingpeng. Evaluation of Human Mental Stress Statements Based on Wavelet Package Transform and Nonlinear Analysis of EEG Signals[J]. Journal of Vibration and Shock, 2013, 32(2): 182-188