DREAM: Domain Invariant and Contrastive Representation for Sleep Dynamics
DREAM: Domain Invariant and Contrastive Representation for Sleep Dynamics
复制标题
DOI：
10.1109/icdm54844.2022.00126
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Seungyeon Lee;Thai-Hoang Pham;Ping Zhang
中科院分区：
文献类型：
--
作者：
Seungyeon Lee;Thai-Hoang Pham;Ping Zhang
睡眠分期是诊断和治疗睡眠相关疾病的一个关键挑战，因为它劳动密集，耗时，昂贵且容易出错。随着大规模睡眠信号数据的可用性，许多深度学习方法被提出用于自动睡眠分期。然而，这些现有的方法面临着几个挑战，包括患者潜在健康状况的异质性和难以建模睡眠阶段之间的复杂相互作用。在本文中，我们提出了一个名为DREAM的神经网络架构来解决这些问题，用于自动睡眠分期。DREAM由（i）特征表示网络和（ii）睡眠阶段分类网络组成，该网络通过变分自动编码器框架和对比学习生成睡眠信号的鲁棒表示，该网络通过Transformer和条件随机场架构在特征表示和标签分类级别上显式地对顺序上下文中睡眠阶段之间的相互作用进行建模。我们的实验结果表明，DREAM显着优于现有的方法自动睡眠分期三个睡眠信号数据集。
Sleep staging is a key challenge in diagnosing and treating sleep-related diseases due to its labor-intensive, time-consuming, costly, and error-prone. With the availability of large-scale sleep signal data, many deep learning methods are proposed for automatic sleep staging. However, these existing methods face several challenges including the heterogeneity of patients’ underlying health conditions and the difficulty modeling complex interactions between sleep stages. In this paper, we propose a neural network architecture named DREAM to tackle these issues for automatic sleep staging. DREAM consists of (i) a feature representation network that generates robust representations for sleep signals via the variational auto-encoder framework and contrastive learning and (ii) a sleep stage classification network that explicitly models the interactions between sleep stages in the sequential context at both feature representation and label classification levels via Transformer and conditional random field architectures. Our experimental results indicate that DREAM significantly outperforms existing methods for automatic sleep staging on three sleep signal datasets.