Automatic recognition of cognitive fatigue from physiological indices by using wavelet packet transform and kernel learning algorithms

Cognitive fatigue is an extremely sophisticated phenomenon, which is influenced by the environment, the state of health, vitality, and the capability of recovery. A single parameter can not fully describe it. In this paper, power spectral indices of HRV and wavelet packet parameters of EEG are firstly combined to analyze the impacts of long time switch task on autonomic nervous system and central nervous system. Then wavelet packet parameters of EEG are extracted as the features of brain activity in different cognitive fatigue state, kernel principal component analysis (KPCA) and support vector machine (SVM) are jointly applied to differentiate two states. The experimental results show that the predominant activity of autonomic nervous system of subjects turns to the sympathetic activity from parasympathetic activity after the task. The wavelet packet parameters of EEG are strongly related with cognitive fatigue. Moreover, the joint KPCA–SVM method is able to effectively reduce the dimensionality of the feature vectors, speed up the convergence in the training of SVM and achieve higher recognition accuracy (90.04%) of cognitive fatigue state. The KPCA–SVM method could be a promising tool for the evaluation of cognitive fatigue.