基于深度强化学习的单通道EEG信号自动睡眠分期算法  

Single channel EEG signal automatic sleep staging algorithm based on deep reinforcement learning

作　　者：赵彦晶 周强[1,3] 刘鑫 李婉[2,3] 田蕴郅 Zhao Yanjing;Zhou Qiang;Liu Xin;Li Wan;Tian Yunzhi(School of Electrical&Control Engineering,Shaanxi University of Science&Technology,Xi’an 710021,China;School of Electronic Information&Artificial Intelligence,Shaanxi University of Science&Technology,Xi’an 710021,China;Shaanxi Artificial Intelligence Joint Laboratory,Xi’an 710021,China)

机构地区：[1]陕西科技大学电气与控制工程学院,西安710021 [2]陕西科技大学电子信息与人工智能学院,西安710021 [3]陕西省人工智能联合实验室,西安710021

出　　处：《计算机应用研究》2024年第9期2699-2704,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(62101312);陕西省科技厅工业项目(2024GX-YBXM-544)。

摘　　要：目前,基于脑电(EEG)信号的人体睡眠分期方法呈现出单通道和网络模型深度化的趋势,然而单通道信息采集使得EEG失去大脑区域的位置信息,EEG中表征睡眠阶段的特征因趋向稀疏化而难以提取,同时深度网络的共性问题——模型及其训练的超参数的人工设定使得训练过程盲目且低效,这些问题导致自动睡眠分期方法的准确率低。为此,提出利用密集连接网络(DenseNet)对模型层间特征重用功能,挖掘深藏于EEG信号中的睡眠状态信息,针对单通道EEG信号在频域上的低频特性以及时域上长程依赖特性,对DenseNet模型进行了改进,实现了人体睡眠的快速和精确分期;为进一步提升DenseNet性能,使用深度确定性策略梯度(DDPG)算法,在网络学习训练过程中利用强化学习思想对DenseNet关键超参数进行在线优化和自动调节。实验结果表明,该算法模型在Sleep-EDFx数据集上的分期准确率达到了89.23%,总体效果优于近年来其他先进分期算法,表现出良好的应用前景。Currently,human sleep staging methods based on electroencephalogram(EEG)signals show a trend towards single-channel and deep network models,however,single-channel information acquisition makes EEG lose the positional information of brain regions,and the features characterizing sleep stages in EEG tend to be sparse and thus difficult to extract,at the same time,the common problems of deep networks-the artificial setting of the model and its training hyperparameters make the training process blind and inefficient,and these problems lead to the low accuracy of automatic sleep staging methods.Therefore,this paper proposed to use the inter-layer feature reuse function of DenseNet to explore the sleep state information hidden in EEG signals,and improved the DenseNet model for the low-frequency characteristics of single-channel EEG signals in the frequency domain and the long-range dependence of single-channel EEG signals in the time domain,so as to achieve the fast and accurate sleep staging of the human body.In order to further improve the performance of DenseNet,it used a deep deterministic policy gradient(DDPG)algorithm to optimize and automatically adjust the key hyperparameters of DenseNet using the reinforcement learning idea during the network learning and training process.The experimental results show that the staging accuracy of the algorithm model on the Sleep-EDFx dataset reaches 89.23%,and the overall performance is better than other advanced staging algorithms in recent years,demonstrating good application prospects.

关 键 词：睡眠分期 密集连接网络 深度强化学习 超参数在线优化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]