DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG
DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG
复制标题
DOI：
10.1109/tnsre.2017.2721116
复制
发表时间：
2017-11-01
影响因子：
4.9
通讯作者：
Guo, Yike
中科院分区：
文献类型：
--
作者：
Supratak, Akara;Dong, Hao;Guo, Yike
本文提出了一种基于原始单通道EEG的深度学习模型DeepSleepNet，用于自动睡眠阶段评分。大多数现有的方法依赖于手工设计的功能，这需要睡眠分析的先验知识。只有少数编码的时间信息，如过渡规则，这是重要的识别下一个睡眠阶段，到提取的功能。在该模型中，我们利用卷积神经网络来提取时不变特征，并利用双向长短时记忆来自动从EEG时期学习睡眠阶段之间的过渡规则。我们实现了一个两步训练算法来有效地训练我们的模型。我们使用来自两个公共睡眠数据集的不同单通道EEG（F4-EOG（左），Fpz-Cz和Pz-Oz）评估了我们的模型，这些数据集具有不同的属性（例如，抽样率）和评分标准（AASM和R&K）。结果表明，与最先进的方法（MASS：85.9%-80.5，Sleep-EDF：78.9%-73.7）相比，我们的模型在两个数据集上实现了相似的总体准确性和宏观F1评分（MASS：86.2%-81.7，Sleep-EDF：82.0%-76.9）。这表明，在不改变模型架构和训练算法的情况下，我们的模型可以从不同数据集的不同原始单通道EEG中自动学习睡眠阶段评分的特征，而无需使用任何手工设计的特征。
This paper proposes a deep learning model, named DeepSleepNet, for automatic sleep stage scoring based on raw single-channel EEG. Most of the existing methods rely on hand-engineered features, which require prior knowledge of sleep analysis. Only a few of them encode the temporal information, such as transition rules, which is important for identifying the next sleep stages, into the extracted features. In the proposed model, we utilize convolutional neural networks to extract time-invariant features, and bidirectional-long short-term memory to learn transition rules among sleep stages automatically from EEG epochs. We implement a two-step training algorithm to train our model efficiently. We evaluated our model using different single-channel EEGs (F4-EOG (left), Fpz-Cz, and Pz-Oz) from two public sleep data sets, that have different properties (e.g., sampling rate) and scoring standards (AASM and R&K). The results showed that our model achieved similar overall accuracy and macro F1-score (MASS: 86.2%-81.7, Sleep-EDF: 82.0%-76.9) compared with the state-of-the-art methods (MASS: 85.9%-80.5, Sleep-EDF: 78.9%-73.7) on both data sets. This demonstrated that, without changing the model architecture and the training algorithm, our model could automatically learn features for sleep stage scoring from different raw single-channel EEGs from different data sets without utilizing any hand-engineered features.