ZleepNet: A Deep Convolutional Neural Network Model for Predicting Sleep Apnea Using SpO2 Signal

IF 2.4 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Applied Computational Intelligence and Soft Computing Pub Date : 2023-09-19 DOI:10.1155/2023/8888004
Hnin Thiri Chaw, Thossaporn Kamolphiwong, Sinchai Kamolphiwong, Krongthong Tawaranurak, Rattachai Wongtanawijit
{"title":"ZleepNet: A Deep Convolutional Neural Network Model for Predicting Sleep Apnea Using SpO2 Signal","authors":"Hnin Thiri Chaw, Thossaporn Kamolphiwong, Sinchai Kamolphiwong, Krongthong Tawaranurak, Rattachai Wongtanawijit","doi":"10.1155/2023/8888004","DOIUrl":null,"url":null,"abstract":"Sleep apnea is one of the most common sleep disorders in the world. It is a common problem for patients to suffer from sleep disturbances. In this paper, we propose a deep convolutional neural network (CNN) model based on the oxygen saturation (SpO2) signal from a smart sensor. This is the reason why we called ZleepNet a network for sleep apnea detection. The proposed model includes three convolutional layers, which include ReLu activation function, 2 dense layers, and one dropout layer for predicting sleep apnea. In this proposed model, the use of signals for detecting the sleep apnea can be reduced from 25 sensors to 1 sensor. We conducted experiments to evaluate the performance of the proposed CNN using real patient data and compared them with traditional machine learning methods such as least discriminant analysis (LDA) and support vector machine (SVM), baggy representation tree, and artificial neural network (ANN) on publicly available sleep datasets using the same parameter setting. The results show that the proposed model outperformed the other methods with the accuracy of 91.30% with the split rate of 0.2% in which the training data are 20% and testing data are 80%. The accuracy of the proposed CNN is 90.33% when compared with the LDA which achieved 86.5% accuracy with the split rate of 0.5% in which training data are 50% and testing data are 50%. It achieved 91.56% accuracy when compared with the support vector machine (SVM) in which training data are 70% and testing data are 30%. The achieved accuracy of the proposed CNN is 91.89% when compared with bagging representation tree in which training data are 90% and testing data are 10%. The accuracy of the proposed CNN is 91.30% in which training data are 83% and testing data are 17% when compared with artificial neural networks (ANN).","PeriodicalId":44894,"journal":{"name":"Applied Computational Intelligence and Soft Computing","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Computational Intelligence and Soft Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1155/2023/8888004","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Sleep apnea is one of the most common sleep disorders in the world. It is a common problem for patients to suffer from sleep disturbances. In this paper, we propose a deep convolutional neural network (CNN) model based on the oxygen saturation (SpO2) signal from a smart sensor. This is the reason why we called ZleepNet a network for sleep apnea detection. The proposed model includes three convolutional layers, which include ReLu activation function, 2 dense layers, and one dropout layer for predicting sleep apnea. In this proposed model, the use of signals for detecting the sleep apnea can be reduced from 25 sensors to 1 sensor. We conducted experiments to evaluate the performance of the proposed CNN using real patient data and compared them with traditional machine learning methods such as least discriminant analysis (LDA) and support vector machine (SVM), baggy representation tree, and artificial neural network (ANN) on publicly available sleep datasets using the same parameter setting. The results show that the proposed model outperformed the other methods with the accuracy of 91.30% with the split rate of 0.2% in which the training data are 20% and testing data are 80%. The accuracy of the proposed CNN is 90.33% when compared with the LDA which achieved 86.5% accuracy with the split rate of 0.5% in which training data are 50% and testing data are 50%. It achieved 91.56% accuracy when compared with the support vector machine (SVM) in which training data are 70% and testing data are 30%. The achieved accuracy of the proposed CNN is 91.89% when compared with bagging representation tree in which training data are 90% and testing data are 10%. The accuracy of the proposed CNN is 91.30% in which training data are 83% and testing data are 17% when compared with artificial neural networks (ANN).
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于SpO2信号预测睡眠呼吸暂停的深度卷积神经网络模型
睡眠呼吸暂停是世界上最常见的睡眠障碍之一。睡眠障碍是病人普遍存在的问题。在本文中,我们提出了一个基于智能传感器的氧饱和度(SpO2)信号的深度卷积神经网络(CNN)模型。这就是为什么我们称ZleepNet为睡眠呼吸暂停检测网络的原因。该模型包括三个卷积层,其中包括ReLu激活函数,2个密集层和一个用于预测睡眠呼吸暂停的dropout层。在该模型中,用于检测睡眠呼吸暂停的信号可以从25个传感器减少到1个传感器。我们使用真实患者数据进行了实验,以评估所提出的CNN的性能,并将其与传统的机器学习方法(如最小判别分析(LDA)和支持向量机(SVM), baggy表示树和人工神经网络(ANN))在公开可用的睡眠数据集上使用相同的参数设置进行了比较。结果表明,在训练数据为20%,测试数据为80%的分割率为0.2%的情况下,该模型的准确率为91.30%,优于其他方法。在训练数据为50%,测试数据为50%的分割率为0.5%的情况下,LDA的准确率为86.5%,而本文提出的CNN准确率为90.33%。与训练数据占70%、测试数据占30%的支持向量机(SVM)相比,准确率达到了91.56%。与训练数据占90%、测试数据占10%的bagging表示树相比,本文提出的CNN的准确率为91.89%。与人工神经网络(ANN)相比,本文提出的CNN准确率为91.30%,其中训练数据准确率为83%,测试数据准确率为17%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Applied Computational Intelligence and Soft Computing
Applied Computational Intelligence and Soft Computing COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-
CiteScore
6.10
自引率
3.40%
发文量
59
审稿时长
21 weeks
期刊介绍: Applied Computational Intelligence and Soft Computing will focus on the disciplines of computer science, engineering, and mathematics. The scope of the journal includes developing applications related to all aspects of natural and social sciences by employing the technologies of computational intelligence and soft computing. The new applications of using computational intelligence and soft computing are still in development. Although computational intelligence and soft computing are established fields, the new applications of using computational intelligence and soft computing can be regarded as an emerging field, which is the focus of this journal.
期刊最新文献
Morphological Accuracy Data Clustering: A Novel Algorithm for Enhanced Cluster Analysis Indonesian Lip-Reading Detection and Recognition Based on Lip Shape Using Face Mesh and Long-Term Recurrent Convolutional Network A Novel Deep Learning-Based Data Analysis Model for Solar Photovoltaic Power Generation and Electrical Consumption Forecasting in the Smart Power Grid Emotion Modeling in Speech Signals: Discrete Wavelet Transform and Machine Learning Tools for Emotion Recognition System A Hybrid Expert System for Estimation of the Manufacturability of a Notional Design
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1