Single-channel EEG sleep staging based on data augmentation and cross-subject discrepancy alleviation

• Published in: Computers in biology and medicine Vol. 149; p. 106044
• Main Authors: He, Zhengling, Du, Lidong, Wang, Peng, Xia, Pan, Liu, Zhe, Song, Yuanlin, Chen, Xianxiang, Fang, Zhen
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.10.2022; Elsevier Limited
• Subjects: Accuracy; Adaptation; Algorithms; Classification; Data augmentation; Datasets; Deep learning; Domain adaptation; Domains; EEG; Electroencephalography; Electroencephalography - methods; Feature maps; Feature selection; Human error; Humans; Inspection; Internal Medicine; Machine Learning; Methods; Neural networks; Neural Networks, Computer; Other; Performance enhancement; Performance evaluation; Single-channel electroencephalogram (EEG); Sleep; Sleep disorders; Sleep stage classification; Sleep Stages; Support vector machines; Transfer attention; Visual fields; Transfer attention; Domain adaptation; Sleep stage classification; Single-channel electroencephalogram (EEG); Data augmentation
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.106044

Automatic sleep stage classification is an effective technology compared to conventional artificial visual inspection in the field of sleep staging. Numerous algorithms based on machine learning and deep learning on single-channel electroencephalogram (EEG) have been proposed in recent years, however, category imbalance and cross-subject discrepancy are still the main factors restricting the accuracy of existing methods. This study proposed an innovative end-to-end neural network to solve these problems, specifically, four data augmentation methods were designed to eliminate category imbalance, and domain adaptation modules were designed for the alignment of marginal distribution, conditional distribution, and channel and spatial level distribution of feature maps, as well as the capture of transferable regions on the feature maps using a transfer attention mechanism. We conducted experiments on two publicly available datasets (Sleep-EDF Database Expanded, 2013 and 2018 version), Cohen's kappa coefficient (k) of 0.77 (Fpz-Cz) and 0.73 (Pz-Oz) were realized on the Sleep-EDF-2013 dataset, and a k of 0.75 (Fpz-Cz) and 0.68 (Pz-Oz) were realized on the Sleep-EDF-2018 dataset. An experiment was also conducted on the dataset drawn from the 2018 Physionet challenge, which containing people with sleep disorders, and a performance improvement was still found. Our comparative experiments with similar studies showed that our model was superior to most other studies, indicating our proposed EEG data augmentation and domain adaptation based cross-subject discrepancy alleviation approach is effective to improve the performance of automatic sleep staging. •Domain adaptation modules for cross-subject discrepancy alleviation.•Four electroencephalogram signal augmentation algorithms to solve category imbalance.•Channel and spatial distribution adaptation with transfer attention.