端到端单通道睡眠EEG自动分期模型

End-to-End Single-channel Automatic Staging Model for Sleep EEG Signal

针对现阶段数据和特征决定自动睡眠分期模型的分类精度上限的问题,提出一种基于深度混合神经网络的自动睡眠分期模型。在模型主体构建方面,使用多尺度卷积神经网络自动学习高级时不变特征,使用双向门限循环单元构建的循环神经网络对时不变特征中的时间信息进行解码,并用残差连接实现时不变特征与时间信息特征的融合。在模型优化方面,将MSMOTE(Modified Synthetic Minority Oversampling Technique)重构后的数据集用于预训练,以减少类不平衡对少数类的分类效果的影响,应用Swish激活函数加速模型收敛。使用Sleep-EDF数据集中Fpz-Cz通道的原始EEG数据对模型进行15折交叉验证,得出OA(Overall Accuracy)和MF1(Macro-averaged F1-score)分别为86.85%和81.63%。提出的模型可避免特征选取的主观性以及类不平衡小数据集在深度学习中的局限性。

The classification accuracy of current automatic sleep staging is determined by the small data set of imba- lanced classes and hand-engineered features.Aiming at this problem,this paper proposed an automatic sleep staging model based on deep hybrid neural network.For the construction of model’s main structure,the multi-scale Convolutional Neural Networks are used to automatically learn the high-level time-invariant features,the Recurrent Neural Networks constructed by bidirectional Gated Recurrent Unit are used to decode the temporal information from the time invariant features,and the residual connection is used to fully combine the time invariant features with the time information features.For model optimization,in order to reduce the impact of the dataset of imbalanced class on the classification effect of minority class,the experimental data set reconstructed by MSMOTE (Modified Synthetic Minority Oversampling Technique) is used for pre-training.The Swish activation function is used to accelerate the training convergence rate.The experiment was set up on the initial single-channel EEG signal of Fpz-Cz in Sleep-EDF Database.The 15-fold cross-validation experiments show that the overall classification accuracy is 86.85% and the Macro-averaged F1-score is 81.63%.This model can effectively avoid the subjectivity of feature selection and the limitation of class imba- lanced small dataset of imbalanced class in deep learning.