Automatic sleep staging of single-channel EEG based on domain adversarial neural networks and domain self-attention

• Published in: Frontiers in neuroscience Vol. 17; p. 1143495
• Main Authors: Gao, Dong-Rui, Li, Jing, Wang, Man-Qing, Wang, Lu-Tao, Zhang, Yong-Qing
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 06.04.2023; Frontiers Media S.A
• Subjects: adversarial training; attention mechanism; automatic sleep staging; Automation; Boundaries; Classification; data augment frontiers; Datasets; Deep learning; EEG; EEG data; Electroencephalography; Eye movements; Network topologies; Neural networks; Neuroscience; Sleep; Sleep disorders; unsupervised domain adaptation; automatic sleep staging; EEG data; adversarial training; data augment frontiers; attention mechanism; unsupervised domain adaptation
• ISSN: 1662-4548; 1662-453X; 1662-453X
• DOI: 10.3389/fnins.2023.1143495

The diagnosis and management of sleep problems depend heavily on sleep staging. For autonomous sleep staging, many data-driven deep learning models have been presented by trying to construct a large-labeled auxiliary sleep dataset and test it by electroencephalograms on different subjects. These approaches suffer a significant setback cause it assumes the training and test data come from the same or similar distribution. However, this is almost impossible in scenario cross-dataset due to inherent domain shift between domains. Unsupervised domain adaption was recently created to address the domain shift issue. However, only a few customized UDA solutions for sleep staging due to two limitations in previous UDA methods. First, the domain classifier does not consider boundaries between classes. Second, they depend on a shared model to align the domain that could miss the information of domains when extracting features. Given those restrictions, we present a novel UDA approach that combines category decision boundaries and domain discriminator to align the distributions of source and target domains. Also, to keep the domain-specific features, we create an unshared attention method. In addition, we investigated effective data augmentation in cross-dataset sleep scenarios. The experimental results on three datasets validate the efficacy of our approach and show that the proposed method is superior to state-of-the-art UDA methods on accuracy and MF1-Score.