This paper proposes a novel framework for automatically capturing the time-frequency nature of electroencephalogram (EEG) signals of human sleep based on the authoritative sleep medicine guidance. The framework consists of two parts: the first part extracts informative features by partitioning the input EEG spectrograms into a sequence of time-frequency patches. The second part is constituted by an attention-based architecture to efficiently search for the correlation between partitioned time-frequency patches and defining factors of sleep stages in parallel. The proposed pipeline is validated on the Sleep Heart Health Study dataset with new state-of-the-art results for the stages wake, N2, and N3, obtaining respective F1 scores of 0.93, 0.88, and 0.87, with only EEG signals used. The proposed method also has a high inter-rater reliability of 0.80 kappa. We also visualize the correspondence between sleep staging decisions and features extracted by the proposed method, providing strong interpretability for our model.
@article{arxiv.2204.03173,
title = {Automated Sleep Staging via Parallel Frequency-Cut Attention},
author = {Zheng Chen and Ziwei Yang and Lingwei Zhu and Wei Chen and Toshiyo Tamura and Naoaki Ono and MD Altaf-Ul-Amin and Shigehiko Kanaya and Ming Huang},
journal= {arXiv preprint arXiv:2204.03173},
year = {2023}
}