Modification of a Conventional Deep Learning Model to Classify Simulated Breathing Patterns: A Step toward Real-Time Monitoring of Patients with Respiratory Infectious Diseases.
Modification of a Conventional Deep Learning Model to Classify Simulated Breathing Patterns: A Step toward Real-Time Monitoring of Patients with Respiratory Infectious Diseases.
复制标题
DOI：
10.3390/s23125592
复制
发表时间：
2023-06-15
期刊：
影响因子：
--
通讯作者：
Gandjbakhche AH
中科院分区：
文献类型：
--
作者：
Park J;Mah AJ;Nguyen T;Park S;Ghazi Zadeh L;Shadgan B;Gandjbakhche AH
2019年全球冠状病毒大流行（COVID-19疾病）的出现，需要远程方法来检测和持续监测传染性呼吸道疾病患者。许多不同的设备，包括温度计、脉搏血氧仪、智能手表和戒指，被建议在家中监测感染者的症状。然而，这些消费级设备通常无法在白天和晚上进行自动监控。本研究旨在开发一种利用组织血流动力学反应和基于深度卷积神经网络（CNN）的分类算法对呼吸模式进行实时分类和监测的方法。使用可穿戴近红外光谱（NIRS）装置收集了21名健康志愿者在三种不同呼吸条件下胸骨柄处的组织血流动力学反应。我们开发了一种基于cnn的深度分类算法，用于实时分类和监测呼吸模式。该分类方法是通过改进和修改之前开发的用于二维图像分类的预激活残差网络（Pre-ResNet）而设计的。基于Pre-ResNet建立了三种不同的一维CNN （1D-CNN）分类模型。通过使用这些模型，我们能够获得平均分类准确率为88.79%（无Stage 1（数据大小减少卷积层）），90.58% （1 × 3 Stage 1）和91.77% （1 × 5 Stage 1）。
The emergence of the global coronavirus pandemic in 2019 (COVID-19 disease) created a need for remote methods to detect and continuously monitor patients with infectious respiratory diseases. Many different devices, including thermometers, pulse oximeters, smartwatches, and rings, were proposed to monitor the symptoms of infected individuals at home. However, these consumer-grade devices are typically not capable of automated monitoring during both day and night. This study aims to develop a method to classify and monitor breathing patterns in real-time using tissue hemodynamic responses and a deep convolutional neural network (CNN)-based classification algorithm. Tissue hemodynamic responses at the sternal manubrium were collected in 21 healthy volunteers using a wearable near-infrared spectroscopy (NIRS) device during three different breathing conditions. We developed a deep CNN-based classification algorithm to classify and monitor breathing patterns in real time. The classification method was designed by improving and modifying the pre-activation residual network (Pre-ResNet) previously developed to classify two-dimensional (2D) images. Three different one-dimensional CNN (1D-CNN) classification models based on Pre-ResNet were developed. By using these models, we were able to obtain an average classification accuracy of 88.79% (without Stage 1 (data size reducing convolutional layer)), 90.58% (with 1 × 3 Stage 1), and 91.77% (with 1 × 5 Stage 1).
登录
查看更多内容
影响因子：
14.9
作者：
Gurbuz, Sevgi Zubeyde;Amin, Moeness G.
通讯作者：
Amin, Moeness G.
影响因子：
46.9
作者：
Kim J;Campbell AS;de Ávila BE;Wang J
通讯作者：
Wang J
用于辅助生活传感的雷达信号处理：与实时实施新兴算法相关的挑战
影响因子：
14.9
作者：
Le Kernec, Julien;Fioranelli, Francesco;Romain, Olivier
通讯作者：
Romain, Olivier
影响因子：
3.6
作者：
Kim, Sungyeup;Rim, Beanbonyka;Choi, Seongjun;Lee, Ahyoung;Min, Sedong;Hong, Min
通讯作者：
Hong, Min
影响因子：
--
作者：
BENGIO, Y;SIMARD, P;FRASCONI, P
通讯作者：
FRASCONI, P