A New Method for Automatic Sleep Stage Classification.

Traditionally, automatic sleep stage classification is quite a challenging task because of the difficulty in translating open-textured standards to mathematical models and the limitations of handcrafted features. In this paper, a new system for automatic sleep stage classification is presented. Compared with existing sleep stage methods, our method can capture the sleep information hidden inside electroencephalography (EEG) signals and automatically extract features from raw data. To translate open sleep stage standards into machine rules recognized by computers, a new model named fast discriminative complex-valued convolutional neural network (FDCCNN) is proposed to extract features from raw EEG data and classify sleep stages. The new model combines complex-valued backpropagation and the Fisher criterion. It can learn discriminative features and overcome the negative effect of imbalance dataset. More importantly, the orthogonal decision boundaries for the real and imaginary parts of a complex-valued convolutional neuron are proven. A speed-up algorithm is proposed to reduce computational workload and yield improvements of over an order of magnitude compared to the normal convolution algorithm. The classification performances of handcrafted features and different convolutional neural networks are compared with that of the FDCCNN. The total accuracy and kappa coefficient of the proposed method are 92% and 0.84, respectively. Experiment results demonstrated that the performance of our system is comparable to those of human experts.