基于迁移学习的随机深度残差网络自动睡眠分期算法  

Automatic sleep staging algorithm for stochastic depth residual networks based on transfer learning

作　　者：田蕴郅 周强[1,3] 李婉 TIAN Yunzhi;ZHOU Qiang;LI Wan(School of Electrical and Control Engineering,Shaanxi University of Science&Technology,Xi'an 710021,P.R.China;School of Electronic Information and Artificial Intelligence,Shaanxi University of Science&Technology,Xi'an 710021,P.R.China;Shaanxi Artificial Intelligence Joint Laboratory,Xi'an 710021,P.R.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：《生物医学工程学杂志》2023年第2期286-294,共9页Journal of Biomedical Engineering

基　　金：国家自然科学基金青年基金项目(62101312)。

摘　　要：现有自动睡眠分期算法存在模型参数量多、训练耗时长导致分期效率不佳的问题。本文使用单通道脑电信号,提出一种基于迁移学习(TL)的随机深度(SD)残差网络(ResNet)自动睡眠分期算法(TLSDResNet)。首先,选取16人共30条单通道(Fpz-Cz)脑电信号,在保留有效睡眠片段后,利用巴特沃斯滤波和连续小波变换对原始脑电信号进行预处理,得到包含其时-频联合特征的二维图像作为分期模型的输入数据。随后,构建经公开数据集——欧洲数据格式存储的睡眠数据库拓展版(Sleep-EDFx)训练的ResNet50预训练模型,使用随机深度策略并修改输出层以优化模型结构。最后,应用迁移学习对人体整夜睡眠过程进行自动分期。本文算法在进行了多次实验后,模型分期准确率达到87.95%。实验表明,TL-SDResNet50可完成少量脑电数据的快速训练,总体效果优于近年来其他分期算法与经典算法,具有一定的实用价值。The existing automatic sleep staging algorithms have the problems of too many model parameters and long training time,which in turn results in poor sleep staging efficiency.Using a single channel electroencephalogram(EEG)signal,this paper proposed an automatic sleep staging algorithm for stochastic depth residual networks based on transfer learning(TL-SDResNet).Firstly,a total of 30 single-channel(Fpz-Cz)EEG signals from 16 individuals were selected,and after preserving the effective sleep segments,the raw EEG signals were pre-processed using Butterworth filter and continuous wavelet transform to obtain two-dimensional images containing its time-frequency joint features as the input data for the staging model.Then,a ResNet50 pre-trained model trained on a publicly available dataset,the sleep database extension stored in European data format(Sleep-EDFx)was constructed,using a stochastic depth strategy and modifying the output layer to optimize the model structure.Finally,transfer learning was applied to the human sleep process throughout the night.The algorithm in this paper achieved a model staging accuracy of 87.95%after conducting several experiments.Experiments show that TL-SDResNet50 can accomplish fast training of a small amount of EEG data,and the overall effect is better than other staging algorithms and classical algorithms in recent years,which has certain practical value.

关 键 词：自动睡眠分期 随机深度 迁移学习 残差网络 连续小波变换 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TN911.7[自动化与计算机技术—控制科学与工程] R740[电子电信—通信与信息系统]