网站首页            期刊简介             编委会             投稿指南             期刊订阅             下载中心             在线留言            联系我们             English
  2025年4月5日 星期六  
文章快速检索
中国生物医学工程学报  2022, Vol. 41 Issue (6): 650-662    DOI: 10.3969/j.issn.0258-8021.2022.06.002
  论著 本期目录 | 过刊浏览 | 高级检索 |
基于多任务多注意力残差收缩卷积神经网络的可穿戴睡眠呼吸暂停检测方法
沈奇1,2,3, 魏克铭1,2,3, 刘官正1,2,3#*
1(中山大学生物医学工程学院,广东 深圳 518107)
2(广东省传感技术与生物医疗仪器重点实验室,广州 510006)
3(广东省便携式普及型先进实用医疗器械工程技术研究中心,广州 510006)
Wearable Sleep Apnea Detection Method Based on Multi-Task and Multi-AttentionResidualShrinkage Convolutional Neural Network
Shen Qi1,2,3, Wei Keming1,2,3, Liu Guanzheng1,2,3#*
1(School of Biomedical Engineering, Sun Yat-sen University, Shenzhen 518107, Guangdong, China)
2(Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, Guangzhou 510006, China)
3(Guangdong Provincial Engineering and Technology Centre of Advanced and Portable Medical Device, Guangzhou 510006, China)
全文: PDF (4293 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 睡眠呼吸暂停综合征(SAS)是常见的慢性呼吸障碍疾病,常伴随着多种并发症,严重困扰着人类健康。基于可穿戴设备的容积血流脉搏波(PPG)的SAS检测方法引起了广泛关注,具有低成本、低负荷、穿戴方便等优点。针对可穿戴PPG信号干扰更大的问题,提出一种多任务多注意力残差收缩卷积神经网络的睡眠呼吸暂停检测方法。首先,利用智能手环设备,收集了92例手腕部的PPG睡眠数据;其次,设计了一种残差多注意力机制卷积模块,高效地融合了网络在时间域与通道域的双重重要特征;然后,引入残差收缩卷积模块来抑制信号噪声以及网络的冗余特征。以这两种模块的结合构建了用于特征提取的骨干网络。结果表明,片段检测的准确率,敏感性以及特异性分别达到了81.82%,70.27%以及85.81%;个体检测的准确率,敏感性,特异性分别达到了95.65%,88.89%以及97.30%。所提出的模型具有优异的检测性能,有望嵌入到可穿戴设备中。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
沈奇
魏克铭
刘官正
关键词 睡眠呼吸暂停综合征可穿戴设备容积血流脉搏波卷积神经网络多任务学习    
Abstract:Sleep apnea syndrome (sleep apnea syndrome, SAS) is a common chronic respiratory disorder, often accompanied by a variety of complications, which seriously plagues human health. The SAS detection method of photoplethysmography (PPG) based on wearable devices has attracted extensive attention because of the advantages of low cost, low load and easy to wear. Aiming at the problem of greater interference of PPG signals based on wearable devices, a sleep apnea detection method based on multi-task multi-attention residual shrinkage convolutional neural network was proposed in this study. First of all, 92 wrist PPG sleep data were collected using smart bracelet devices. Next, a residual multi-attention mechanism convolution block was designed, which efficiently integrated the dual important features of the network in the time domain and the channel domain. Then, the residual shrinkage convolution block was introduced to suppress the signal noise and the redundant features of the network. Through the combination of these two blocks, a backbone network for feature extraction was constructed. The results showed that the accuracy, sensitivity, and specificity of the segment detection achieved 81.82%, 70.27%, and 85.81%, respectively; and the accuracy, sensitivity, and specificity of individual detection achieved 95.65%, 88.89%, and 97.30%, respectively. Compared with peers, the proposed method displayed better performance and was able to integrate to the wearable devices for sleep apnea syndrome detection.
Key wordssleep apnea syndrome    wearable device    photoplethysmography    convolutional neural network    multi-task learning
收稿日期: 2021-10-13     
PACS:  R318  
基金资助:广东省基础与应用基础研究基金(2020A1515010701);深圳市科技计划基础研究项目(JCYJ20180307153213863,JCY20190807162003696)
通讯作者: *E-mail: liugzh3@163.com   
作者简介: #中国生物医学工程学会会员
引用本文:   
沈奇, 魏克铭, 刘官正. 基于多任务多注意力残差收缩卷积神经网络的可穿戴睡眠呼吸暂停检测方法[J]. 中国生物医学工程学报, 2022, 41(6): 650-662.
Shen Qi, Wei Keming, Liu Guanzheng. Wearable Sleep Apnea Detection Method Based on Multi-Task and Multi-AttentionResidualShrinkage Convolutional Neural Network. Chinese Journal of Biomedical Engineering, 2022, 41(6): 650-662.
链接本文:  
http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2022.06.002     或     http://cjbme.csbme.org/CN/Y2022/V41/I6/650
版权所有 © 2015 《中国生物医学工程学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发