Pilot's cognitive state recognition using wavelet singular entropy and Gaussian process classification via full flight simulation
Zhengxiang Cai, Edmond Q. Wu, Shan Fu, Dan Huang · 2015
Cognitive state of human is vital to the man-machine system. This research proposes a method of wavelet singular entropy and Gaussian process classification to recognize the human cognitive state via physiological data during flight simulation. Experiments are implemented in a 6-degree-of-freedom full flight simulator under an emergency flight scenario. Classification results validate the effectiveness of the proposed method. Further analysis suggests a three-channel physiological signal selection to be optimal for classification as a tradeoff of the accuracy and computational cost.