Pilots' fatigue state recognition faces two important issues: how to extract the characteristics that characterize fatigue and how to model fatigue characteristics. Firstly

the EEG (ElectroEncephaloGram) signal is extracted

and the instantaneous frequency domain information based on the affine pseudo-smooth Wigner-Ville distribution is calculated to construct the fatigue state index. Secondly

based on the periodic changes of each channel of EEG signals

the fatigue state classification algorithm of Gamma deep belief network is proposed. Unlike other learning network using convolution and pooling

the proposed network does not split the image or signal

but the hidden layer at the bottom can effectively learn the features of a specific region

and when the number of layers increases

the number of features increases and the features are more general. The Gibbs sampling algorithm for training the deep belief network is improved. The up-down Gibbs sampling is proposed to infer the network parameters. Finally

the experimental results show that the Gamma deep belief network in this paper has achieved satisfactory results in terms of recognition accuracy

stability and iteration time.