Real-time deep learning-assisted mechano-acoustic system for respiratory diagnosis and multifunctional classification

IF 12.3 1区材料科学 Q1 ENGINEERING, ELECTRICAL & ELECTRONIC

npj Flexible Electronics Pub Date : 2024-10-21 DOI:10.1038/s41528-024-00355-7

Hee Kyu Lee, Sang Uk Park, Sunga Kong, Heyin Ryu, Hyun Bin Kim, Sang Hoon Lee, Danbee Kang, Sun Hye Shin, Ki Jun Yu, Juhee Cho, Joohoon Kang, Il Yong Chun, Hye Yun Park, Sang Min Won

{"title":"Real-time deep learning-assisted mechano-acoustic system for respiratory diagnosis and multifunctional classification","authors":"Hee Kyu Lee, Sang Uk Park, Sunga Kong, Heyin Ryu, Hyun Bin Kim, Sang Hoon Lee, Danbee Kang, Sun Hye Shin, Ki Jun Yu, Juhee Cho, Joohoon Kang, Il Yong Chun, Hye Yun Park, Sang Min Won","doi":"10.1038/s41528-024-00355-7","DOIUrl":null,"url":null,"abstract":"Epidermally mounted sensors using triaxial accelerometers have been previously used to monitor physiological processes with the implementation of machine learning (ML) algorithm interfaces. The findings from these previous studies have established a strong foundation for the analysis of high-resolution, intricate signals, typically through frequency domain conversion. In this study we integrate a wireless mechano-acoustic sensor with a multi-modal deep learning system for the real-time analysis of signals emitted by the laryngeal prominence area of the thyroid cartilage at frequency ranges up to 1 kHz. This interface provides real-time data visualization and communication with the ML server, creating a system that assesses severity of chronic obstructive pulmonary disease and analyzes the user’s speech patterns.","PeriodicalId":48528,"journal":{"name":"npj Flexible Electronics","volume":" ","pages":"1-12"},"PeriodicalIF":12.3000,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41528-024-00355-7.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"npj Flexible Electronics","FirstCategoryId":"88","ListUrlMain":"https://www.nature.com/articles/s41528-024-00355-7","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

Epidermally mounted sensors using triaxial accelerometers have been previously used to monitor physiological processes with the implementation of machine learning (ML) algorithm interfaces. The findings from these previous studies have established a strong foundation for the analysis of high-resolution, intricate signals, typically through frequency domain conversion. In this study we integrate a wireless mechano-acoustic sensor with a multi-modal deep learning system for the real-time analysis of signals emitted by the laryngeal prominence area of the thyroid cartilage at frequency ranges up to 1 kHz. This interface provides real-time data visualization and communication with the ML server, creating a system that assesses severity of chronic obstructive pulmonary disease and analyzes the user’s speech patterns.

Abstract Image

查看原文本刊更多论文

用于呼吸诊断和多功能分类的实时深度学习辅助机械声学系统

使用三轴加速度计的表皮安装传感器以前曾被用于监测生理过程，并实施了机器学习（ML）算法接口。这些研究结果为分析高分辨率的复杂信号奠定了坚实的基础，通常是通过频域转换。在这项研究中，我们将无线机械声学传感器与多模态深度学习系统集成在一起，用于实时分析甲状软骨喉突出部位发出的频率范围高达 1 kHz 的信号。该接口可提供实时数据可视化并与 ML 服务器进行通信，从而创建一个可评估慢性阻塞性肺病严重程度并分析用户说话模式的系统。

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分钟内获得全文求助全文

来源期刊

npj Flexible Electronics Multiple-

CiteScore

17.10

自引率

4.80%

发文量

审稿时长

6 weeks

期刊介绍： npj Flexible Electronics is an online-only and open access journal, which publishes high-quality papers related to flexible electronic systems, including plastic electronics and emerging materials, new device design and fabrication technologies, and applications.