基于深度学习的跨对象脑电睡眠分期研究  

Sleep staging research of cross-subject EEG based on deep learning

作　　者：张金辉[1] 汪鹏[2] 李蕾[2] ZHANG Jinhui;WANG Peng;LI Lei(Equipment Support Room,Logistic Support Center,PLA General Hospital,Beijing 100853;School of Artificial Intelligence,Beijing University of Posts and Telecommunications,Beijing 100876)

机构地区：[1]解放军总医院服务保障中心装备保障室,北京100853 [2]北京邮电大学人工智能学院,北京100876

出　　处：《北京生物医学工程》2022年第4期399-404,共6页Beijing Biomedical Engineering

基　　金：军队装备综合研究项目(LB20201A010010)资助。

摘　　要：目的跨对象脑电睡眠分期是国际顶级会议NeurIPS 2021最新提出的一项挑战性任务,目的是解决当前脑电睡眠分期中主要存在的目标数据不足问题。本文基于深度学习方法对该任务进行了初步探索,通过对数据集的深入分析,结合深度学习AttnSleep(attention-based deep learning approach for sleep stage classification)模型,设计实现了一种基于类感知损失函数(class-aware loss function)的单通道脑电睡眠分期方法。方法实验数据来自NeurIPS 2021 BEETL Competition任务一官方所提供的跨对象数据集,首先对脑电数据进行标准化预处理,然后使用本文设计的方法进行睡眠分期,并对其结果进行检验。结果在数据集提供的2个不同年龄组别中,本文方法分别达到了67.33和66.68的任务指标,同时也验证了类感知损失函数的作用。结论使用基于类感知损失函数的单通道AttnSleep模型有助于在目标数据不足的情况下提升跨对象脑电睡眠分期的效果。文中所用的实验方法代码将发布于https://github.com/MatrixWP/EEG-sleep-stage-classification。Objective Cross-subject EEG sleep staging is a challenging task recently proposed by the international top conference NeurIPS 2021,which aims to solve the main problem of insufficient data of objects in the current EEG sleep staging.In this paper,a preliminary exploration of this task is carried out based on the deep learning method.Through thorough analysis of the data set,we design and implement a single-channel EEG sleep staging method based on the AttnSleep model with class-aware loss function.Methods The cross-subject experimental data comes from the official data set provided by the task one in NeurIPS 2021 BEETL Competition.First,the EEG data is standardized in preprocessing,and then the method designed in this paper is used and tested for sleep staging.Results In the two age groups provided by the data set,the method in this paper reaches the task indicators of 67.33 and 66.68,respectively.The effect of class-aware loss function is also verified.Conclusions The use of the single-channel AttnSleep model with the class-aware loss function can help to improve the effect of cross-subject EEG sleep staging in the case of lacking target data.The code will be available on https://github.com/MatrixWP/EEG-sleep-stage-classification.

关 键 词：跨对象睡眠分期 脑电 深度学习 AttnSleep模型 类感知损失函数 

分 类 号：R318.04[医药卫生—生物医学工程]