The proposed EEGSNet deep learning model achieved sleep stage classification accuracies ranging from 83.02% to 94.17% and improved N1 classification F1-scores across four public datasets.
Does the EEGSNet deep learning model improve automated sleep stage classification using EEG spectrograms?
The proposed EEGSNet deep learning model achieves high accuracy in automated sleep stage classification using EEG spectrograms, particularly improving performance in the challenging N1 stage.
The classification of sleep stages is an important process. However, this process is time-consuming, subjective, and error-prone. Many automated classification methods use electroencephalogram (EEG) signals for classification. These methods do not classify well enough and perform poorly in the N1 due to unbalanced data. In this paper, we propose a sleep stage classification method using EEG spectrogram. We have designed a deep learning model called EEGSNet based on multi-layer convolutional neural networks (CNNs) to extract time and frequency features from the EEG spectrogram, and two-layer bi-directional long short-term memory networks (Bi-LSTMs) to learn the transition rules between features from adjacent epochs and to perform the classification of sleep stages. In addition, to improve the generalization ability of the model, we have used Gaussian error linear units (GELUs) as the activation function of CNN. The proposed method was evaluated by four public databases, the Sleep-EDFX-8, Sleep-EDFX-20, Sleep-EDFX-78, and SHHS. The accuracy of the method is 94.17%, 86.82%, 83.02% and 85.12%, respectively, for the four datasets, the MF1 is 87.78%, 81.57%, 77.26% and 78.54%, respectively, and the Kappa is 0.91, 0.82, 0.77 and 0.79, respectively. In addition, our proposed method achieved better classification results on N1, with an F1-score of 70.16%, 52.41%, 50.03% and 47.26% for the four datasets.
Li et al. (Mon,) conducted a other in Sleep stage classification. EEGSNet deep learning model was evaluated on Classification accuracy, MF1, and Kappa. The proposed EEGSNet deep learning model achieved sleep stage classification accuracies ranging from 83.02% to 94.17% and improved N1 classification F1-scores across four public datasets.