An Improved Neural Network Based on SENet for Sleep Stage Classification.

Sleep stage is an important step in analyzing sleep quality. Traditional manual analysis by psychologists is time-consuming. In this paper, we propose an automatic sleep staging model with an improved attention module and HMM. The model is driven by single channel EEG data. It automatically extracts features through two convolution kernels with different scales. Subsequently, an improved attention module based on SENet will perform feature fusion. The neural network will give a preliminary sleep stage based on the learned features. Finally, a Hidden Markov Model (HMM) will apply sleep transition rules to refine the classification. The proposed method is tested on sleep-EDFx dataset. The achievable accuracy of the proposed method on the Fpz-Cz channel is 0.85, and the kappa coefficient is 0.79. For the Pz-Oz channel, the accuracy is 0.82 and kappa is 0.75. Experimental results show that our improved attention module helps to improve classification accuracy. In addition, applying sleep transition rules through HMM helps to improve performance, especially N1, which is difficult to identify.