Khalili Ebrahim, Mohammadzadeh Asl Babak
Department of Biomedical Engineering, Tarbiat Modares University, Tehran, Iran.
Department of Biomedical Engineering, Tarbiat Modares University, Tehran, Iran.
Comput Methods Programs Biomed. 2021 Jun;204:106063. doi: 10.1016/j.cmpb.2021.106063. Epub 2021 Mar 27.
This paper presents a new framework for automatic classification of sleep stages using a deep learning algorithm from single-channel EEG signals. Each segmented EEG signal appended with its label of stages is fed into a deep learning model to create an automatic sleep stage classification. This is one of the most important problems that is critical to the realization of monitoring patients with sleep disorder.
In the present study, a neural network architecture is introduced utilizing Convolutional Neural Networks (CNNs) to extract features, followed by Temporal Convolutional Neural Network to extract the temporal features from the extracted features vector of CNN. Finally, the performance of our model is improved by a Conditional Random Field layer. We also employed a new data augmentation technique to enhance the CNNs training which has auxiliary effects.
We evaluated our model by two different single-channel EEG signals (i.e., Fpz-Cz and Pz-Oz EEG channels) from two public sleep datasets, named Sleep-EDF-2013 and Sleep-EDF-2018. The evaluation results on both datasets showed that our model obtains the best total accuracy and kappa score (EDF-2013: 85.39%- 0.80, EDF-2018: 82.46%- 0.76) compared to the state-of-the-art methods.
This study will possibly allow us to have a wearable sleep monitoring system with a single-channel EEG. Also, unlike hand-crafted features methods, our model finds its own patterns through training epochs, and therefore, it may minimize engineering bias.
本文提出了一种使用深度学习算法从单通道脑电图（EEG）信号自动分类睡眠阶段的新框架。每个附加了睡眠阶段标签的分段EEG信号被输入到一个深度学习模型中，以创建自动睡眠阶段分类。这是实现睡眠障碍患者监测的最重要问题之一。
在本研究中，引入了一种神经网络架构，利用卷积神经网络（CNN）提取特征，随后使用时间卷积神经网络从CNN提取的特征向量中提取时间特征。最后，通过条件随机场层提高了我们模型的性能。我们还采用了一种新的数据增强技术来加强CNN的训练，该技术具有辅助作用。
我们使用来自两个公共睡眠数据集（即Sleep-EDF-2013和Sleep-EDF-2018）的两种不同的单通道EEG信号（即Fpz-Cz和Pz-Oz EEG通道）对我们的模型进行了评估。两个数据集的评估结果表明，与现有方法相比，我们的模型获得了最佳的总准确率和kappa分数（EDF-2013：85.39%-0.80，EDF-2018：82.46%-0.76）。
本研究可能使我们拥有一个基于单通道EEG的可穿戴睡眠监测系统。此外，与手工特征方法不同，我们的模型通过训练轮次找到自己的模式，因此，它可能会将工程偏差降至最低。
