Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China.
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China; Personalized Management of Chronic Respiratory Disease, Chinese Academy of Medical Sciences, China.
Comput Biol Med. 2022 Oct;149:106044. doi: 10.1016/j.compbiomed.2022.106044. Epub 2022 Aug 27.
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.
自动睡眠分期分类是睡眠分期领域中一种有效的技术，相较于传统的人工视觉检查。近年来，已经提出了许多基于机器学习和单通道脑电图（EEG）的深度学习算法，然而，类别不平衡和跨主体差异仍然是限制现有方法准确性的主要因素。本研究提出了一种创新的端到端神经网络来解决这些问题，具体来说，设计了四种数据增强方法来消除类别不平衡，设计了域自适应模块来对齐边际分布、条件分布、特征图的通道和空间水平分布，以及使用转移注意力机制在特征图上捕获可转移区域。我们在两个公开可用的数据集（Sleep-EDF Database Expanded，2013 年和 2018 年版本）上进行了实验，在 Sleep-EDF-2013 数据集上实现了 Cohen 的 kappa 系数（k）为 0.77（Fpz-Cz）和 0.73（Pz-Oz），在 Sleep-EDF-2018 数据集上实现了 k 为 0.75（Fpz-Cz）和 0.68（Pz-Oz）。我们还在 2018 年 Physionet 挑战赛中包含睡眠障碍患者的数据集上进行了实验，发现性能仍有所提高。我们与类似研究的比较实验表明，我们的模型优于大多数其他研究，表明我们提出的 EEG 数据增强和基于域自适应的跨主体差异缓解方法能够有效提高自动睡眠分期的性能。
