An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG
An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG
复制标题
一种基于注意力的单通道脑电图睡眠阶段分类深度学习方法
DOI：
10.1109/tnsre.2021.3076234
复制
发表时间：
2021-01-01
影响因子：
4.9
通讯作者：
Guan, Cuntai
中科院分区：
文献类型：
--
作者：
Eldele, Emadeldeen;Chen, Zhenghua;Guan, Cuntai
自动睡眠阶段 mymargin 分类对于衡量睡眠质量非常重要。在本文中，我们提出了一种名为 AttnSleep 的新型基于注意力的深度学习架构，用于使用单通道脑电图信号对睡眠阶段进行分类。该架构从基于多分辨率卷积神经网络（MRCNN）和自适应特征重新校准（AFR）的特征提取模块开始。 MRCNN 可以提取低频和高频特征，AFR 能够通过对特征之间的相互依赖关系进行建模来提高提取特征的质量。第二个模块是时间上下文编码器（TCE），它利用多头注意力机制来捕获提取的特征之间的时间依赖性。特别是，多头注意力部署因果卷积来对输入特征中的时间关系进行建模。我们使用三个公共数据集评估我们提出的 AttnSleep 模型的性能。结果表明，我们的 AttnSleep 在不同的评估指标方面均优于最先进的技术。我们的源代码、实验数据和补充材料可在 https://github.com/emadeldeen24/AttnSleep 获取。
Automatic sleep stage mymargin classification is of great importance to measure sleep quality. In this paper, we propose a novel attention-based deep learning architecture called AttnSleep to classify sleep stages using single channel EEG signals. This architecture starts with the feature extraction module based on multi-resolution convolutional neural network (MRCNN) and adaptive feature recalibration (AFR). The MRCNN can extract low and high frequency features and the AFR is able to improve the quality of the extracted features by modeling the inter-dependencies between the features. The second module is the temporal context encoder (TCE) that leverages a multi-head attention mechanism to capture the temporal dependencies among the extracted features. Particularly, the multi-head attention deploys causal convolutions to model the temporal relations in the input features. We evaluate the performance of our proposed AttnSleep model using three public datasets. The results show that our AttnSleep outperforms state-of-the-art techniques in terms of different evaluation metrics. Our source codes, experimental data, and supplementary materials are available at https://github.com/emadeldeen24/AttnSleep.