Article(id=1329460661983228734, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329460564176253901, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440386, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1717084800000, receivedDateStr=2024-05-31, revisedDate=1722268800000, revisedDateStr=2024-07-30, acceptedDate=null, acceptedDateStr=null, onlineDate=1794897722000, onlineDateStr=2026-11-17, pubDate=1730390400000, pubDateStr=2024-11-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794897722000, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794897722000, creator=13701087609, updateTime=1794897722000, updator=13701087609, issue=Issue{id=1329460564176253901, tenantId=1146029695717560320, journalId=1324759914146529478, year='2024', volume='61', issue='11', pageStart='2663', pageEnd='2936', issueExtLink='null', onlineDate='null', pubDate='1730390400000', pubDateStr='2024-11-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794897698682, creator='13701087609', updateTime=1794897698682, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=2721, endPage=2738, ext={EN=ArticleExt(id=1329460662188749631, articleId=1329460661983228734, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Human Fall Detection Method Beyond the Sensing Range of IR-UWB Using Ambient Vibration, columnId=1329460582316617822, journalTitle=Journal of Computer Research and Development, columnName=Special Issue on Advanced Technologies of Artificial Intelligence of Things, runingTitle=null, highlight=null, articleAbstract=

Fall detection is crucial in elderly healthcare, traditionally relying on wearable devices for sensing. To avoid the burden and discomfort caused by wearable devices, contact-free methods using radio frequency (RF) signals have emerged as a promising alternative due to their ubiquity and non-invasiveness. Existing contact-free methods predominantly extract physiological motion features, e.g., the speed and acceleration of human falls from RF signals and analyze the motion time series to determine if a fall event has occurred. While current methods achieve high detection accuracy in line-of-sight (LoS) scenarios, they still face limitations in sensing range and non-light-of-sight (NLoS). To address this, we propose a method using the commercial off-the-shelf (COTS) impulse radio-ultra wideband (IR-UWB) devices to detect human falls beyond the sensing range. The key insight of our method is identifying ambient vibration features induced by falls outside the sensing range to determine fall events. By developing the IQ entropy and farthest points-pair distance algorithm, signal features from subtle vibrations caused by falls are extracted. We implement a UWFall prototype system built on COTS IR-UWB devices and conduct extensive experimental evaluations under various environments. The results demonstrate that UWFall system achieves a recognition accuracy over 90% with one single transceiver. Furthermore, the detection accuracy for falls beyond 7 meters exceeds 86%, and this system maintains high robustness in NLoS scenarios.

, authors=Dongzi Wang1, Zhengxin Guo1, 2, Linqing Gui1, 2, Biyun Sheng1, 2, Hui Cai1, 2, Fu Xiao1, 2, *, authorsList=Dongzi Wang, Zhengxin Guo, Linqing Gui, Biyun Sheng, Hui Cai, Fu Xiao, authorCompany=null, correspAuthors=Fu Xiao, authorNote=

born in 1996. PhD candidate. Student member of CCF. His main research interest includes wireless sensing

born in 1993. PhD, lecturer. Member of CCF. His main research interests include wireless sensing and mobile computing

born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent perception and computing of the Internet of things, and Internet of things security

born in 1989. PhD, associate professor, master supervisor. Member of CCF. Her main research interests include human behavior recognition, identity authentication, deep learning, and cross domain sensing

born in 1993. PhD, lecturer, master supervisor. Member of CCF. Her main research interests include privacy and security, federated learning, data science and big data computing, mobile crowd-sensing networks, and game theory

born in 1980. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include IoT sensing, IoT security technologies, and data center networks

, correspAuthorsNote=null, copyrightStatement=Copyright © 2024 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1329460668727669625, articleId=1329460661983228734, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=基于环境振动的IR-UWB超感知范围人体跌倒检测方法, columnId=1329460582484389984, journalTitle=计算机研究与发展, columnName=智能物联网前沿技术专题, runingTitle=null, highlight=null, articleAbstract=

跌倒检测在老年人医疗保健中至关重要,传统方案主要依赖于可穿戴设备进行感知. 为了避免可穿戴设备带来的负担和不适,采用射频(radio frequency, RF)的非接触式方法因其具有的普适性和非侵入性,逐渐成为一种有前景的替代方案. 现有的非接触式方法主要从无线射频信号中提取人体跌倒产生的速度和加速度等运动生理特征,通过分析运动时间序列来判断目标是否发生跌倒行为. 虽然目前的方法可以在视距状态下获取较高的检测精度,但是其在感知范围和非视距路径下的感知效果仍存在局限性. 为解决以上问题,提出了利用最先进的商用IR-UWB设备来识别超感知范围外的人体跌倒检测方法. 该方法的关键是通过识别感知范围外人体跌倒引发的环境振动特征来判断是否发生跌倒事件,并通过设计IQ熵和最远点对距离算法从微小振动中提取人体跌倒产生的信号特征. 通过在商用IR-UWB设备上搭建UWFall原型系统并在各种环境下开展大量的实验测试,结果表明,单台收发器的UWFall系统识别准确率超过90%. 同时,UWFall系统对7 m范围外的目标跌倒检测准确率超过86%,且在非视距场景下依然保持高鲁棒性.

, authors=王冬子1, 郭政鑫1, 2, 桂林卿1, 2, 盛碧云1, 2, 蔡惠1, 2, 肖甫1, 2, *, authorsList=王冬子, 郭政鑫, 桂林卿, 盛碧云, 蔡惠, 肖甫, authorCompany=null, correspAuthors=肖甫, authorNote=

1996年生. 博士研究生. CCF学生会员. 主要研究方向为无线传感

1993年生. 博士,讲师. CCF会员. 主要研究方向为无线传感、移动计算

1984年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为物联网智能感知与计算、物联网安全

1989年生. 博士,副教授,硕士生导师. CCF会员. 主要研究方向为人体行为识别、身份认证、深度学习、跨域感知

1993年生. 博士,讲师,硕士生导师. CCF会员. 主要研究方向为隐私安全、联邦学习、数据科学与大数据计算、移动群智感知网络、博弈论

1980年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为物联网感知、物联网安全技术、数据中心网络

, correspAuthorsNote=
肖甫()
, copyrightStatement=版权所有 © 2024 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Dx5yhq9+VCPWCOCdcnBYxA==, magXml=fouwdueW0ySeKuIPWuMRjA==, pdfUrl=null, pdf=mwL0mzlW2A0EDtp1O5fHQg==, pdfFileSize=4176653, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=jmYsWdcv0LmnjJn2m/36DA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=KCSz48oiDF3jZkye+s93lw==, mapNumber=null, fund=null)}, authors=[Author(id=1329460670665438081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2023040504@njupt.edu.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460670740935555, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460670665438081, language=EN, stringName=Dongzi Wang, firstName=Dongzi, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023, bio={"content":"

born in 1996. PhD candidate. Student member of CCF. His main research interest includes wireless sensing

"}, bioImg=null, bioContent=

born in 1996. PhD candidate. Student member of CCF. His main research interest includes wireless sensing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460670833210244, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460670665438081, language=CN, stringName=王冬子, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023, bio={"img":"KgEIMn7cddfAT9+3H97vQg==","content":"

1996年生. 博士研究生. CCF学生会员. 主要研究方向为无线传感

"}, bioImg=KgEIMn7cddfAT9+3H97vQg==, bioContent=

1996年生. 博士研究生. CCF学生会员. 主要研究方向为无线传感

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)])]), Author(id=1329460670900319110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460671026148233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460670900319110, language=EN, stringName=Zhengxin Guo, firstName=Zhengxin, middleName=null, lastName=Guo, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1993. PhD, lecturer. Member of CCF. His main research interests include wireless sensing and mobile computing

"}, bioImg=null, bioContent=

born in 1993. PhD, lecturer. Member of CCF. His main research interests include wireless sensing and mobile computing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460671093257098, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460670900319110, language=CN, stringName=郭政鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"QMoVw2q4kFFBSGx6uUJ8dg==","content":"

1993年生. 博士,讲师. CCF会员. 主要研究方向为无线传感、移动计算

"}, bioImg=QMoVw2q4kFFBSGx6uUJ8dg==, bioContent=

1993年生. 博士,讲师. CCF会员. 主要研究方向为无线传感、移动计算

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])]), Author(id=1329460671172948876, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460671256834959, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671172948876, language=EN, stringName=Linqing Gui, firstName=Linqing, middleName=null, lastName=Gui, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent perception and computing of the Internet of things, and Internet of things security

"}, bioImg=null, bioContent=

born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent perception and computing of the Internet of things, and Internet of things security

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460671344915344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671172948876, language=CN, stringName=桂林卿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"6ccsqVh3JA3/jxnYdnoVRw==","content":"

1984年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为物联网智能感知与计算、物联网安全

"}, bioImg=6ccsqVh3JA3/jxnYdnoVRw==, bioContent=

1984年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为物联网智能感知与计算、物联网安全

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])]), Author(id=1329460671424607122, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460671495910293, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671424607122, language=EN, stringName=Biyun Sheng, firstName=Biyun, middleName=null, lastName=Sheng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1989. PhD, associate professor, master supervisor. Member of CCF. Her main research interests include human behavior recognition, identity authentication, deep learning, and cross domain sensing

"}, bioImg=null, bioContent=

born in 1989. PhD, associate professor, master supervisor. Member of CCF. Her main research interests include human behavior recognition, identity authentication, deep learning, and cross domain sensing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460671575602070, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671424607122, language=CN, stringName=盛碧云, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"b0mawSz4vIegot5Ovrequw==","content":"

1989年生. 博士,副教授,硕士生导师. CCF会员. 主要研究方向为人体行为识别、身份认证、深度学习、跨域感知

"}, bioImg=b0mawSz4vIegot5Ovrequw==, bioContent=

1989年生. 博士,副教授,硕士生导师. CCF会员. 主要研究方向为人体行为识别、身份认证、深度学习、跨域感知

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])]), Author(id=1329460671642710936, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460671718208411, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671642710936, language=EN, stringName=Hui Cai, firstName=Hui, middleName=null, lastName=Cai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1993. PhD, lecturer, master supervisor. Member of CCF. Her main research interests include privacy and security, federated learning, data science and big data computing, mobile crowd-sensing networks, and game theory

"}, bioImg=null, bioContent=

born in 1993. PhD, lecturer, master supervisor. Member of CCF. Her main research interests include privacy and security, federated learning, data science and big data computing, mobile crowd-sensing networks, and game theory

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460671785317276, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671642710936, language=CN, stringName=蔡惠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"UOd0BbBqj6c6cIVOAVUd2A==","content":"

1993年生. 博士,讲师,硕士生导师. CCF会员. 主要研究方向为隐私安全、联邦学习、数据科学与大数据计算、移动群智感知网络、博弈论

"}, bioImg=UOd0BbBqj6c6cIVOAVUd2A==, bioContent=

1993年生. 博士,讲师,硕士生导师. CCF会员. 主要研究方向为隐私安全、联邦学习、数据科学与大数据计算、移动群智感知网络、博弈论

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])]), Author(id=1329460671852426142, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xiaof@njupt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329460671944700833, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671852426142, language=EN, stringName=Fu Xiao, firstName=Fu, middleName=null, lastName=Xiao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1980. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include IoT sensing, IoT security technologies, and data center networks

"}, bioImg=null, bioContent=

born in 1980. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include IoT sensing, IoT security technologies, and data center networks

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460672011809698, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671852426142, language=CN, stringName=肖甫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"gDggFjw0fC26P3QigS9ykw==","content":"

1980年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为物联网感知、物联网安全技术、数据中心网络

"}, bioImg=gDggFjw0fC26P3QigS9ykw==, bioContent=

1980年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为物联网感知、物联网安全技术、数据中心网络

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])])], keywords=[Keyword(id=1329460672108278691, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, orderNo=1, keyword=fall detection), Keyword(id=1329460672175387556, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, orderNo=2, keyword=radio frequency sensing), Keyword(id=1329460672234107813, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, orderNo=3, keyword=Internet of things), Keyword(id=1329460672301216678, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, orderNo=4, keyword=IR-UWB radar), Keyword(id=1329460672359936935, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, orderNo=5, keyword=wireless sensing), Keyword(id=1329460672418657192, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, orderNo=1, keyword=跌倒检测), Keyword(id=1329460672473183145, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, orderNo=2, keyword=射频感知), Keyword(id=1329460672548680618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, orderNo=3, keyword=物联网), Keyword(id=1329460672607400875, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, orderNo=4, keyword=IR-UWB雷达), Keyword(id=1329460672670315436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, orderNo=5, keyword=无线感知)], refs=[Reference(id=1329460679641248735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Zhe, Zheng Tianyue, Cai Chao, et al. Wider is better? contact-free vibration sensing via different COTS-RF technologies[C]//Proc of the IEEE Conf on Computer Communications. Piscataway, NJ: IEEE, 2023: 1−10, articleTitle=null, refAbstract=null), Reference(id=1329460679725134816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Siwadamrongpong W, Chinrungrueng J, Hasegawa S, et al. Fall detection and prediction based on IMU and EMG sensors for elders[C]//Proc of the 19th Int Joint Conf on Computer Science and Software Engineering. Piscataway, NJ: IEEE, 2022: 1−6, articleTitle=null, refAbstract=null), Reference(id=1329460679792243681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Mohamed H H, Siti H Y, Anis N I, et al. Wearable smart phone sensor fall detection system[J]. International Journal of Interactive Mobile Technologies, 2022, 16(12): 72−93, articleTitle=null, refAbstract=null), Reference(id=1329460679859352546, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Yi, Xiao Fu, Huan Haiping, et al. RF-IDH: An intelligent fall detection system for hemodialysis patients via COTS RFID[J]. Future Generation Computer Systems, 2020, 113: 13−24, articleTitle=null, refAbstract=null), Reference(id=1329460679918072803, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Kottari K N, Delibasis K K, Maglogiannis I G. Real-time fall detection using uncalibrated Fisheye cameras[J]. IEEE Transactions on Cognitive and Developmental Systems, 2020, 12(3): 588−600, articleTitle=null, refAbstract=null), Reference(id=1329460680006153188, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Lian Jie, Yuan Xu, Li Ming, et al. Fall detection via inaudible acoustic sensing[J]. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, 2021, 5(3): 1−21, articleTitle=null, refAbstract=null), Reference(id=1329460680098427877, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Yuqian, Zhang Feng, Wu Chenshu, et al. DeFall: Environment-independent passive fall detection using WiFi[J]. IEEE Internet of Things Journal, 2022, 9(11): 8515−8530, articleTitle=null, refAbstract=null), Reference(id=1329460680173925350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Jin Feng, Sengupta A, Cao Siyang. mmFall: Fall detection using 4-D mmWave radar and a hybrid variational RNN autoEncoder[J]. IEEE Transactions on Automation Science and Engineering, 2022, 19(23): 1245−1257, articleTitle=null, refAbstract=null), Reference(id=1329460680257811431, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Sanaz K, Stefano S, Federico V, et al. Device-free RF human body fall detection and localization in industrial workplaces[J]. IEEE Internet of Things Journal, 2017, 4(2): 351−362, articleTitle=null, refAbstract=null), Reference(id=1329460680345891816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Takashi N, Mondher B, Kohei Y, et al. Wi-Fi-based fall detection using spectrogram image of channel state information[J]. IEEE Internet of Things Journal, 2022, 9(18): 17220−17234, articleTitle=null, refAbstract=null), Reference(id=1329460680413000681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Wenxuan, Zhang Dongheng, Li Yadong, et al. Real-time fall detection using mmwave radar[C]//Proc of the 2022 IEEE Int Conf on Acoustics, Speech and Signal Processing. Piscataway, NJ: IEEE, 2022: 16−20, articleTitle=null, refAbstract=null), Reference(id=1329460680480109546, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Guiping, Men Jing, Lin Enmin, et al. Peak amplitude curve based arm motion recognition using IR-UWB radar[C]//Proc of the 98th Vehicular Technology Conf. Piscataway, NJ: IEEE, 2023: 1−6, articleTitle=null, refAbstract=null), Reference(id=1329460680568189931, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Taekjin H, Wonho K, Gyunghyun C. IR-UWB sensor based fall detection method using CNN algorithm[J]. Sensors, 2020, 20(20): 5948−5969, articleTitle=null, refAbstract=null), Reference(id=1329460680664658924, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Ding Rong, Jin Haiming, Xiang Dong, et al. Soil moisture sensing with UAV-Mounted IR-UWB radar and deep learning[C]//Proc of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. New York: ACM, 2023, 7(1): 1−25, articleTitle=null, refAbstract=null), Reference(id=1329460680769516525, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Xikang, Lin Zhang, Lei Li. Multi-task learning radar transformer (MLRT): A personal identification and fall detection network based on IR-UWB radar[J]. Sensors, 2023, 23(12): 5632−5643, articleTitle=null, refAbstract=null), Reference(id=1329460680836625390, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Di, Xiong Gang, Wang Lizhe, et al. Variable length sequential iterable convolutional recurrent network for UWB-IR vehicle target recognition[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1−11, articleTitle=null, refAbstract=null), Reference(id=1329460680912122863, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Dang Xiaochao, Zhang Jinlong, Hao Zhanjun. A non-contact detection method for multi-person vital signs based on IR-UWB radar[J]. Sensors, 2022, 22(16): 6116−6136, articleTitle=null, refAbstract=null), Reference(id=1329460681000203248, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Khan F, Azou S, Youssef R, et al. An IR-UWB multi-sensor approach for collision avoidance in indoor environments[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1−13, articleTitle=null, refAbstract=null), Reference(id=1329460681075700721, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Kwon H B, Choi S H, Lee D, et al. Attention-based LSTM for non-contact sleep stage classification using IR-UWB radar[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(10): 3844−3853, articleTitle=null, refAbstract=null), Reference(id=1329460681138615282, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Ali K, Liu A X. Fine-grained vibration based sensing using a smartphone[J]. IEEE Transactions on Mobile Computing, 2022, 21(11): 3971−3985, articleTitle=null, refAbstract=null), Reference(id=1329460681197335539, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Fagert J, Bonde A, Srinidhi S, et al. Clean Vibes: Hand washing monitoring using structural vibration sensing[J]. ACM Transactions on Computing for Healthcare, 2022, 3(3): 1−25, articleTitle=null, refAbstract=null), Reference(id=1329460681277027316, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Yuanhao, Zhang Youwei, Yang Panlong. RF-Ear+: A mechanical identification and troubleshooting system based on contactless vibration sensing[J]. IEEE Transactions on Mobile Computing, 2023, 22(12): 7310−7326, articleTitle=null, refAbstract=null), Reference(id=1329460681348330485, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Xin, Yang Song, Liu Jian. Enabling finger-touch-based mobile user authentication via physical vibrations on IoT devices[J]. IEEE Transactions on Mobile Computing, 2022, 21(10): 3565−3580, articleTitle=null, refAbstract=null), Reference(id=1329460681415439350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Maria V, Li Fangyu, Zhao Liang, et al. Vibration sensing-based human and infrastructure safety/health monitoring: A survey[J]. Digital Signal Processing, 2022, 125: 103572−103585, articleTitle=null, refAbstract=null), Reference(id=1329460681486742519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Ziqi, Chen Zhe, Singh A D. UWHear: Through-wall extraction and separation of audio vibrations using wireless signals[C]//Proc of the 18th Conf on Embedded Networked Sensor Systems. New York: ACM, 2020: 1−14, articleTitle=null, refAbstract=null), Reference(id=1329460681570628600, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Maître J, Bouchard K, Gaboury S. et al. Fall detection with UWB radars and CNN-LSTM architecture[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(4): 1273−1283, articleTitle=null, refAbstract=null), Reference(id=1329460681679680505, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Kaishun, Huang Yandao, Qiu Minghui, et al. Toward device-free and user-independent fall detection using floor vibration[J]. ACM Transactions on Sensor Networks, 2023, 19(1): 1550−1859, articleTitle=null, refAbstract=null), Reference(id=1329460681750983674, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Zhengxin, Wang Dongzi, Gui Linqing, et al. UWTracking: Passive human tracking under LOS/NLOS scenarios using IR-UWB radar[J]. IEEE Transactions on Mobile Computing, 2024, 5(1): 1−17, articleTitle=null, refAbstract=null), Reference(id=1329460681813898235, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Fusang, Xiong Jie, Chang Zhaoxin, et al. Mobi2Sense: Empowering wireless sensing with mobility[C]//Proc of the 28th Annual Int Conf on Mobile Computing and Networking. New York: ACM, 2022: 268−281, articleTitle=null, refAbstract=null), Reference(id=1329460681889395708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Sadreazami H, Bolic M, Rajan S. et al. Fall detection using Standoff radar-based sensing and deep convolutional neural network[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2020, 67(1): 197−201, articleTitle=null, refAbstract=null), Reference(id=1329460681969087485, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Xikang, Zhang Jinhui, Zhang Lin. FedRadar: Federated multi-task transfer learning for radar-based Internet of medical things[J]. IEEE Transactions on Network and Service Management, 2023, 20(2): 1459−1469, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])], figs=[ArticleFig(id=1329460672770978733, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 1, caption=System prototype of UWFall, figureFileSmall=b6mHyBvushCloaLOdupbzQ==, figureFileBig=jmYsWdcv0LmnjJn2m/36DA==, tableContent=null), ArticleFig(id=1329460672825504686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图1, caption=UWFall的系统原型, figureFileSmall=b6mHyBvushCloaLOdupbzQ==, figureFileBig=jmYsWdcv0LmnjJn2m/36DA==, tableContent=null), ArticleFig(id=1329460673093940143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 2, caption=An IR-UWB radar system in equivalent base-band representation, figureFileSmall=wSdyIbJ8ABV57KW8zA4Qnw==, figureFileBig=vU2Yhfh21Sts3wSPbFX8tw==, tableContent=null), ArticleFig(id=1329460673161049008, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图2, caption=IR-UWB雷达系统的等效基带图, figureFileSmall=wSdyIbJ8ABV57KW8zA4Qnw==, figureFileBig=vU2Yhfh21Sts3wSPbFX8tw==, tableContent=null), ArticleFig(id=1329460674763273138, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 3, caption=Fast-slow time matrix, figureFileSmall=P93QjfZpJ/IWs/kYO5hTGw==, figureFileBig=fFl3ad32iD1RRwPcynviwQ==, tableContent=null), ArticleFig(id=1329460674859742131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图3, caption=快慢时间矩阵, figureFileSmall=P93QjfZpJ/IWs/kYO5hTGw==, figureFileBig=fFl3ad32iD1RRwPcynviwQ==, tableContent=null), ArticleFig(id=1329460674939433908, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 4, caption=Practical example of fast-slow time matrix, figureFileSmall=klP8e2JQHTSBE+Q9JFE4Sg==, figureFileBig=QgU5ABQhGkNZ5tQKYYKE1w==, tableContent=null), ArticleFig(id=1329460674998154165, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图4, caption=快慢时间矩阵实例, figureFileSmall=klP8e2JQHTSBE+Q9JFE4Sg==, figureFileBig=QgU5ABQhGkNZ5tQKYYKE1w==, tableContent=null), ArticleFig(id=1329460675061068726, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 5, caption=Practical slow time sequences of adjacent fast time bins, figureFileSmall=EzZo8ysA3HKhWeRYuUxctw==, figureFileBig=/pbYrOoKutv4PdtgnhuwTg==, tableContent=null), ArticleFig(id=1329460675128177591, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图5, caption=相邻快时间仓中实例的慢时间序列, figureFileSmall=EzZo8ysA3HKhWeRYuUxctw==, figureFileBig=/pbYrOoKutv4PdtgnhuwTg==, tableContent=null), ArticleFig(id=1329460675203675064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 6, caption=System workflow of UWFall, figureFileSmall=Vf1KGZuDhmBQ6F90Hl9bQA==, figureFileBig=Oy69vbF7Kc5LbaFOBeV2Bw==, tableContent=null), ArticleFig(id=1329460675266589625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图6, caption=UWFall的系统工作流程, figureFileSmall=Vf1KGZuDhmBQ6F90Hl9bQA==, figureFileBig=Oy69vbF7Kc5LbaFOBeV2Bw==, tableContent=null), ArticleFig(id=1329460675337892794, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 7, caption=Different types of signal variation in a single fast-time bin, figureFileSmall=w0PQ4bHjJl2de2JIJZkPow==, figureFileBig=yWjWhOHKxmvjIe29TeuqNw==, tableContent=null), ArticleFig(id=1329460675409195963, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图7, caption=单个快速时间仓中不同类型的信号分量, figureFileSmall=w0PQ4bHjJl2de2JIJZkPow==, figureFileBig=yWjWhOHKxmvjIe29TeuqNw==, tableContent=null), ArticleFig(id=1329460675484693436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 8, caption=Different types of signal variation, figureFileSmall=rolSridpROOvfYj42aPRTw==, figureFileBig=AtrnuchEcQfgQ89Vm/93RQ==, tableContent=null), ArticleFig(id=1329460675627299773, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图8, caption=不同类型的信号分量, figureFileSmall=rolSridpROOvfYj42aPRTw==, figureFileBig=AtrnuchEcQfgQ89Vm/93RQ==, tableContent=null), ArticleFig(id=1329460675803460542, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 9, caption=Phase variation in a single fast-time bin, figureFileSmall=LduItSnSeIEuTmfJeoHKww==, figureFileBig=oAwD6cl/fNtebxmMr5wj1Q==, tableContent=null), ArticleFig(id=1329460675887346623, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图9, caption=单个快速时间仓的相位变化, figureFileSmall=LduItSnSeIEuTmfJeoHKww==, figureFileBig=oAwD6cl/fNtebxmMr5wj1Q==, tableContent=null), ArticleFig(id=1329460675941872576, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 10, caption=Signal distribution in IQ plane with/without FBR, figureFileSmall=zXwBKdVry/+Hj8d6xNM4Ng==, figureFileBig=HemInATWMpnNh6fuMPYEXg==, tableContent=null), ArticleFig(id=1329460675996398529, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图10, caption=有/无FBR的IQ空间信号分布, figureFileSmall=zXwBKdVry/+Hj8d6xNM4Ng==, figureFileBig=HemInATWMpnNh6fuMPYEXg==, tableContent=null), ArticleFig(id=1329460676063507394, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 11, caption=Comparison between DTW and Dual-DTW in inter-bins component extracting, figureFileSmall=hgOa3s2XPUJ8Q0xfmUVYSw==, figureFileBig=9dPt3YbgipTa/oMiCDnq/g==, tableContent=null), ArticleFig(id=1329460676130616259, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图11, caption=比较DTW和Dual DTW提取仓间动态分量的效果, figureFileSmall=hgOa3s2XPUJ8Q0xfmUVYSw==, figureFileBig=9dPt3YbgipTa/oMiCDnq/g==, tableContent=null), ArticleFig(id=1329460676201919428, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 12, caption=Phase inflection points counting algorithm, figureFileSmall=+8nonuVPErDWqdM4+D6bsg==, figureFileBig=Fb1P6/eAtsK2M1QQfOLy+A==, tableContent=null), ArticleFig(id=1329460676260639685, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图12, caption=相位拐点计数算法, figureFileSmall=+8nonuVPErDWqdM4+D6bsg==, figureFileBig=Fb1P6/eAtsK2M1QQfOLy+A==, tableContent=null), ArticleFig(id=1329460676315165638, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 13, caption=Farthest point distance of static component and vibration component, figureFileSmall=ToqWG7Nb3JzHk6g7V3gr4g==, figureFileBig=b4+SyFyGSsEEDCkReIwvdA==, tableContent=null), ArticleFig(id=1329460676369691591, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图13, caption=静态信号和振动信号的最远点距离, figureFileSmall=ToqWG7Nb3JzHk6g7V3gr4g==, figureFileBig=b4+SyFyGSsEEDCkReIwvdA==, tableContent=null), ArticleFig(id=1329460676424217544, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 14, caption=Example of farthest points pair distance, figureFileSmall=5Xh3BPBhR/zDc9DjIrCcbw==, figureFileBig=w2xPLMX+GgrnIsBRecfAmA==, tableContent=null), ArticleFig(id=1329460676487132105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图14, caption=最远点对距离的样例, figureFileSmall=5Xh3BPBhR/zDc9DjIrCcbw==, figureFileBig=w2xPLMX+GgrnIsBRecfAmA==, tableContent=null), ArticleFig(id=1329460676550046666, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 15, caption=Experimental setting for UWFall, figureFileSmall=f9Ex92qib1wRuJrytwBapA==, figureFileBig=pv2765BMdkkYcRiqBvGNCA==, tableContent=null), ArticleFig(id=1329460676608766923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图15, caption=UWFall的实验设置, figureFileSmall=f9Ex92qib1wRuJrytwBapA==, figureFileBig=pv2765BMdkkYcRiqBvGNCA==, tableContent=null), ArticleFig(id=1329460676667487180, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 16, caption=Impact of different distances on performance, figureFileSmall=I4CN84usqVjnk2MRzMrUdw==, figureFileBig=7pZdvundXKPYDDLIEwz9AQ==, tableContent=null), ArticleFig(id=1329460676726207437, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图16, caption=不同距离对性能的影响, figureFileSmall=I4CN84usqVjnk2MRzMrUdw==, figureFileBig=7pZdvundXKPYDDLIEwz9AQ==, tableContent=null), ArticleFig(id=1329460676793316302, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 17, caption=Impact of different azimuths on performance, figureFileSmall=cnMzUYhApMkvRUbRWQ+CBg==, figureFileBig=8ec7NHS3TTaPdAKPoBaBqg==, tableContent=null), ArticleFig(id=1329460676864619471, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图17, caption=不同方位角对性能的影响, figureFileSmall=cnMzUYhApMkvRUbRWQ+CBg==, figureFileBig=8ec7NHS3TTaPdAKPoBaBqg==, tableContent=null), ArticleFig(id=1329460676940116944, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 18, caption=Impact of different elevation angles on performance, figureFileSmall=zZoWLy/Qng0m5m2tKB7G/w==, figureFileBig=Shrlp29aOKtyYbF981/Q8A==, tableContent=null), ArticleFig(id=1329460677007225809, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图18, caption=不同俯仰角对性能的影响, figureFileSmall=zZoWLy/Qng0m5m2tKB7G/w==, figureFileBig=Shrlp29aOKtyYbF981/Q8A==, tableContent=null), ArticleFig(id=1329460677074334674, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 19, caption=Impact of different heights on performance, figureFileSmall=ya1dndqAQV++W9MTeuJUFg==, figureFileBig=pB0YQxDnOreRK2BnjSgYLw==, tableContent=null), ArticleFig(id=1329460677145637843, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图19, caption=不同高度对性能的影响, figureFileSmall=ya1dndqAQV++W9MTeuJUFg==, figureFileBig=pB0YQxDnOreRK2BnjSgYLw==, tableContent=null), ArticleFig(id=1329460677221135317, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 20, caption=Impact of NLoS and multipath on performance, figureFileSmall=0KvW1emTc0p0PXhUQECivg==, figureFileBig=8i0R7o2oqr2sCGbk7m1rGQ==, tableContent=null), ArticleFig(id=1329460677288244182, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图20, caption=非视距和多径对性能的影响, figureFileSmall=0KvW1emTc0p0PXhUQECivg==, figureFileBig=8i0R7o2oqr2sCGbk7m1rGQ==, tableContent=null), ArticleFig(id=1329460677359547351, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 21, caption=Impact of different environments and different humans on performance, figureFileSmall=xrUvJlqdcP4SaWCxMsvOAA==, figureFileBig=3H8VDIxIIJa2GNbjPpF6SA==, tableContent=null), ArticleFig(id=1329460677430850520, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图21, caption=不同环境和不同用户对性能的影响, figureFileSmall=xrUvJlqdcP4SaWCxMsvOAA==, figureFileBig=3H8VDIxIIJa2GNbjPpF6SA==, tableContent=null), ArticleFig(id=1329460677502153689, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Figure 22, caption=Evaluation of fall-like activities, figureFileSmall=C1sZayNbDan16gSlqqhsfA==, figureFileBig=lP8SXEdddkwbClfjq4iNdg==, tableContent=null), ArticleFig(id=1329460677573456858, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=图22, caption=类跌倒活动评估, figureFileSmall=C1sZayNbDan16gSlqqhsfA==, figureFileBig=lP8SXEdddkwbClfjq4iNdg==, tableContent=null), ArticleFig(id=1329460679263761371, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Table 1, caption=

Performance Comparison of Fall Detection Tasks

, figureFileSmall=null, figureFileBig=null, tableContent=
方法雷达数量准确率/%极限感知距离/m
文献[26]方法3945
文献[30]方法1915
文献[31]方法1935
本文方法1917
), ArticleFig(id=1329460679393784796, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=表1, caption=

处理跌倒检测任务的性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
方法雷达数量准确率/%极限感知距离/m
文献[26]方法3945
文献[30]方法1915
文献[31]方法1935
本文方法1917
), ArticleFig(id=1329460679490253789, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=EN, label=Table 2, caption=

Experimenter Settings

, figureFileSmall=null, figureFileBig=null, tableContent=
志愿者性别年龄身高∕cm体重∕kg
U1男2518075
U2女2716055
U3男2717570
U4女5117060
U5男5217585
), ArticleFig(id=1329460679553168350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, language=CN, label=表2, caption=

实验人员设置

, figureFileSmall=null, figureFileBig=null, tableContent=
志愿者性别年龄身高∕cm体重∕kg
U1男2518075
U2女2716055
U3男2717570
U4女5117060
U5男5217585
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202440386, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440386, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440386, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440386, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1730390400000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于环境振动的IR-UWB超感知范围人体跌倒检测方法
王冬子 1 , 郭政鑫 1, 2 , 桂林卿 1, 2 , 盛碧云 1, 2 , 蔡惠 1, 2 , 肖甫 1, 2, *
计算机研究与发展 | 智能物联网前沿技术专题 2024,61(11): 2721-2738
收起
收藏切换
计算机研究与发展 |智能物联网前沿技术专题 2024 , 61 (11) : 2721 -2738
基于环境振动的IR-UWB超感知范围人体跌倒检测方法
全屏
[Author(id=1329460670665438081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2023040504@njupt.edu.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460670740935555, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460670665438081, language=EN, stringName=Dongzi Wang, firstName=Dongzi, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023, bio={"content":"

born in 1996. PhD candidate. Student member of CCF. His main research interest includes wireless sensing

"}, bioImg=null, bioContent=

born in 1996. PhD candidate. Student member of CCF. His main research interest includes wireless sensing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460670833210244, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460670665438081, language=CN, stringName=王冬子, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023, bio={"img":"KgEIMn7cddfAT9+3H97vQg==","content":"

1996年生. 博士研究生. CCF学生会员. 主要研究方向为无线传感

"}, bioImg=KgEIMn7cddfAT9+3H97vQg==, bioContent=

1996年生. 博士研究生. CCF学生会员. 主要研究方向为无线传感

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)])]), Author(id=1329460670900319110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460671026148233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460670900319110, language=EN, stringName=Zhengxin Guo, firstName=Zhengxin, middleName=null, lastName=Guo, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1993. PhD, lecturer. Member of CCF. His main research interests include wireless sensing and mobile computing

"}, bioImg=null, bioContent=

born in 1993. PhD, lecturer. Member of CCF. His main research interests include wireless sensing and mobile computing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460671093257098, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460670900319110, language=CN, stringName=郭政鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"QMoVw2q4kFFBSGx6uUJ8dg==","content":"

1993年生. 博士,讲师. CCF会员. 主要研究方向为无线传感、移动计算

"}, bioImg=QMoVw2q4kFFBSGx6uUJ8dg==, bioContent=

1993年生. 博士,讲师. CCF会员. 主要研究方向为无线传感、移动计算

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])]), Author(id=1329460671172948876, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460671256834959, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671172948876, language=EN, stringName=Linqing Gui, firstName=Linqing, middleName=null, lastName=Gui, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent perception and computing of the Internet of things, and Internet of things security

"}, bioImg=null, bioContent=

born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent perception and computing of the Internet of things, and Internet of things security

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460671344915344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671172948876, language=CN, stringName=桂林卿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"6ccsqVh3JA3/jxnYdnoVRw==","content":"

1984年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为物联网智能感知与计算、物联网安全

"}, bioImg=6ccsqVh3JA3/jxnYdnoVRw==, bioContent=

1984年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为物联网智能感知与计算、物联网安全

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])]), Author(id=1329460671424607122, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460671495910293, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671424607122, language=EN, stringName=Biyun Sheng, firstName=Biyun, middleName=null, lastName=Sheng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1989. PhD, associate professor, master supervisor. Member of CCF. Her main research interests include human behavior recognition, identity authentication, deep learning, and cross domain sensing

"}, bioImg=null, bioContent=

born in 1989. PhD, associate professor, master supervisor. Member of CCF. Her main research interests include human behavior recognition, identity authentication, deep learning, and cross domain sensing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460671575602070, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671424607122, language=CN, stringName=盛碧云, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"b0mawSz4vIegot5Ovrequw==","content":"

1989年生. 博士,副教授,硕士生导师. CCF会员. 主要研究方向为人体行为识别、身份认证、深度学习、跨域感知

"}, bioImg=b0mawSz4vIegot5Ovrequw==, bioContent=

1989年生. 博士,副教授,硕士生导师. CCF会员. 主要研究方向为人体行为识别、身份认证、深度学习、跨域感知

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])]), Author(id=1329460671642710936, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329460671718208411, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671642710936, language=EN, stringName=Hui Cai, firstName=Hui, middleName=null, lastName=Cai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1993. PhD, lecturer, master supervisor. Member of CCF. Her main research interests include privacy and security, federated learning, data science and big data computing, mobile crowd-sensing networks, and game theory

"}, bioImg=null, bioContent=

born in 1993. PhD, lecturer, master supervisor. Member of CCF. Her main research interests include privacy and security, federated learning, data science and big data computing, mobile crowd-sensing networks, and game theory

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460671785317276, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671642710936, language=CN, stringName=蔡惠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"UOd0BbBqj6c6cIVOAVUd2A==","content":"

1993年生. 博士,讲师,硕士生导师. CCF会员. 主要研究方向为隐私安全、联邦学习、数据科学与大数据计算、移动群智感知网络、博弈论

"}, bioImg=UOd0BbBqj6c6cIVOAVUd2A==, bioContent=

1993年生. 博士,讲师,硕士生导师. CCF会员. 主要研究方向为隐私安全、联邦学习、数据科学与大数据计算、移动群智感知网络、博弈论

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])]), Author(id=1329460671852426142, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xiaof@njupt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329460671944700833, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671852426142, language=EN, stringName=Fu Xiao, firstName=Fu, middleName=null, lastName=Xiao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023, bio={"content":"

born in 1980. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include IoT sensing, IoT security technologies, and data center networks

"}, bioImg=null, bioContent=

born in 1980. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include IoT sensing, IoT security technologies, and data center networks

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329460672011809698, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, authorId=1329460671852426142, language=CN, stringName=肖甫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023, bio={"img":"gDggFjw0fC26P3QigS9ykw==","content":"

1980年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为物联网感知、物联网安全技术、数据中心网络

"}, bioImg=gDggFjw0fC26P3QigS9ykw==, bioContent=

1980年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为物联网感知、物联网安全技术、数据中心网络

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329460670506054522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=1, ext=[AuthorCompanyExt(id=1329460670514443131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023), AuthorCompanyExt(id=1329460670518637436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670506054522, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023)]), AuthorCompany(id=1329460670589940605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, xref=2, ext=[AuthorCompanyExt(id=1329460670594134910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023), AuthorCompanyExt(id=1329460670602523519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460661983228734, companyId=1329460670589940605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023)])])]
王冬子1 , 郭政鑫1, 2, 桂林卿1, 2, 盛碧云1, 2, 蔡惠1, 2, 肖甫1, 2, *
作者信息
  • 1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
  • 2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023
通讯作者:
肖甫()
作者简介:

1996年生. 博士研究生. CCF学生会员. 主要研究方向为无线传感

1993年生. 博士,讲师. CCF会员. 主要研究方向为无线传感、移动计算

1984年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为物联网智能感知与计算、物联网安全

1989年生. 博士,副教授,硕士生导师. CCF会员. 主要研究方向为人体行为识别、身份认证、深度学习、跨域感知

1993年生. 博士,讲师,硕士生导师. CCF会员. 主要研究方向为隐私安全、联邦学习、数据科学与大数据计算、移动群智感知网络、博弈论

1980年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为物联网感知、物联网安全技术、数据中心网络

Human Fall Detection Method Beyond the Sensing Range of IR-UWB Using Ambient Vibration
Dongzi Wang1 , Zhengxin Guo1, 2, Linqing Gui1, 2, Biyun Sheng1, 2, Hui Cai1, 2, Fu Xiao1, 2, *
Affiliations
  • 1School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
  • 2Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023
  • born in 1996. PhD candidate. Student member of CCF. His main research interest includes wireless sensing

    born in 1993. PhD, lecturer. Member of CCF. His main research interests include wireless sensing and mobile computing

    born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent perception and computing of the Internet of things, and Internet of things security

    born in 1989. PhD, associate professor, master supervisor. Member of CCF. Her main research interests include human behavior recognition, identity authentication, deep learning, and cross domain sensing

    born in 1993. PhD, lecturer, master supervisor. Member of CCF. Her main research interests include privacy and security, federated learning, data science and big data computing, mobile crowd-sensing networks, and game theory

    born in 1980. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include IoT sensing, IoT security technologies, and data center networks

出版时间: 2024-11-01 doi: 10.7544/issn1000-1239.202440386
文章导航
收藏切换

跌倒检测在老年人医疗保健中至关重要,传统方案主要依赖于可穿戴设备进行感知. 为了避免可穿戴设备带来的负担和不适,采用射频(radio frequency, RF)的非接触式方法因其具有的普适性和非侵入性,逐渐成为一种有前景的替代方案. 现有的非接触式方法主要从无线射频信号中提取人体跌倒产生的速度和加速度等运动生理特征,通过分析运动时间序列来判断目标是否发生跌倒行为. 虽然目前的方法可以在视距状态下获取较高的检测精度,但是其在感知范围和非视距路径下的感知效果仍存在局限性. 为解决以上问题,提出了利用最先进的商用IR-UWB设备来识别超感知范围外的人体跌倒检测方法. 该方法的关键是通过识别感知范围外人体跌倒引发的环境振动特征来判断是否发生跌倒事件,并通过设计IQ熵和最远点对距离算法从微小振动中提取人体跌倒产生的信号特征. 通过在商用IR-UWB设备上搭建UWFall原型系统并在各种环境下开展大量的实验测试,结果表明,单台收发器的UWFall系统识别准确率超过90%. 同时,UWFall系统对7 m范围外的目标跌倒检测准确率超过86%,且在非视距场景下依然保持高鲁棒性.

跌倒检测  /  射频感知  /  物联网  /  IR-UWB雷达  /  无线感知

Fall detection is crucial in elderly healthcare, traditionally relying on wearable devices for sensing. To avoid the burden and discomfort caused by wearable devices, contact-free methods using radio frequency (RF) signals have emerged as a promising alternative due to their ubiquity and non-invasiveness. Existing contact-free methods predominantly extract physiological motion features, e.g., the speed and acceleration of human falls from RF signals and analyze the motion time series to determine if a fall event has occurred. While current methods achieve high detection accuracy in line-of-sight (LoS) scenarios, they still face limitations in sensing range and non-light-of-sight (NLoS). To address this, we propose a method using the commercial off-the-shelf (COTS) impulse radio-ultra wideband (IR-UWB) devices to detect human falls beyond the sensing range. The key insight of our method is identifying ambient vibration features induced by falls outside the sensing range to determine fall events. By developing the IQ entropy and farthest points-pair distance algorithm, signal features from subtle vibrations caused by falls are extracted. We implement a UWFall prototype system built on COTS IR-UWB devices and conduct extensive experimental evaluations under various environments. The results demonstrate that UWFall system achieves a recognition accuracy over 90% with one single transceiver. Furthermore, the detection accuracy for falls beyond 7 meters exceeds 86%, and this system maintains high robustness in NLoS scenarios.

fall detection  /  radio frequency sensing  /  Internet of things  /  IR-UWB radar  /  wireless sensing
王冬子, 郭政鑫, 桂林卿, 盛碧云, 蔡惠, 肖甫. 基于环境振动的IR-UWB超感知范围人体跌倒检测方法. 计算机研究与发展, 2024 , 61 (11) : 2721 -2738 . DOI: 10.7544/issn1000-1239.202440386
Dongzi Wang, Zhengxin Guo, Linqing Gui, Biyun Sheng, Hui Cai, Fu Xiao. Human Fall Detection Method Beyond the Sensing Range of IR-UWB Using Ambient Vibration[J]. Journal of Computer Research and Development, 2024 , 61 (11) : 2721 -2738 . DOI: 10.7544/issn1000-1239.202440386
随着全球老龄化趋势的加剧,社会需要满足老年人日益紧迫的医疗需求. 根据世界卫生组织的报告,20%~30%的老年人在跌倒后受到中度伤害或面临死亡风险. 值得注意的是,在全球范围内跌倒导致的死亡率在60岁及以上的人群中最为明显. 此外,跌倒的影响不仅限于直接的身体伤害,还包括由于缺乏及时援助而造成的各种不利后果,特别是对独居老人而言. 因此,迫切需要一个实时室内跌倒检测功能的系统,可以自动及时发出警报,增加挽救生命的可能并提供迅速的救援.
跌倒检测的重要性促进了各种解决方案的发展,现有的工作主要分为2类:接触式系统和非接触式系统. 接触式系统要求用户佩戴专用的可穿戴设备进行身体运动的监测,包括心电图传感器、压力传感器、加速度计、陀螺仪和智能手机等. 然而,老年人持续佩戴专用传感器在现实情况下是繁重且不切实际的. 为了克服这些缺陷,利用相机和射频(radio frequency, RF)信号的非接触式解决方案广受关注. 在传统非接触式系统中,基于视觉的方法最为普遍,通常需要部署相机、红外传感器或Kinect等深度相机来监测指定区域. 虽然这些系统可以实现高精度的跌倒检测效果,但由于存在隐私泄露的隐患,使其无法在日常居家环境中进行广泛部署,尤其是在浴室和卧室等私密环境中.
与视觉方案相比,基于射频的解决方案不会引起隐私问题,使得其在居家场景中进行跌倒检测具有良好的应用前景. 基于射频的跌倒检测系统的基本原理是,人体跌倒影响反射信号的传播路径,进而表现出不同的信号变化特征. 研究人员利用这些特征来检测跌倒事件,采用毫米波雷达和WiFi等射频信号设计了不同的感知技术. 目前基于射频信号的跌倒方法主要关注于识别运动的姿态或瞬时速度,其约束目标在感测范围内. 然而在现实场景中,由于非视距路径(non-light-of-sight, NLoS)情况和设备感知距离的限制,会对系统带来严重影响. 此外,基于学习模型的跌倒检测通常需要大量的训练样本,使其难以适配复杂多变的现实环境.
最近研究[1]表明先进商用(commercial off-the-shelf, COTS)的脉冲超宽带射频(impulse radio-ultra wideband, IR-UWB)设备相较于其他RF感知设备在感知方面具有卓越性能. 虽然IR-UWB设备可以实现高精度的感知,但是仍然存在RF设备中普遍存在的感知距离约束. 由于感知距离限制,传统采用目标身体姿势、瞬时速度和加速度等传统运动特征的方法都会失效. 然而对于感知距离外的目标而言,人体跌倒会导致地面振动,随着振动波的传播,会使感知范围内物品振动,通过检测感知范围内的环境振动,为实现超远距离感知奠定基础.
虽然使用IR-UWB设备感知振动具有实现远距离跌倒检测的可行性,但是识别振动特征存在2方面的挑战. 一方面,提取振动特征需要感知信号相位变化,而IR-UWB雷达中的硬件缺陷会引入明显的相位偏移,这会显著影响系统的准确性. 另一方面,空间中存在大量干扰,如个人的日常活动和日常家用电器的振动干扰. 其中人类运动引起的信号变化超过了振动导致的信号变化,这使得提取与振动相关的信号特征变得异常困难. 此外,振动引起的信号变化也容易被环境范围高斯噪声所淹没.
为解决上述挑战,本文提出了一种基于环境振动的超感知范围人体跌倒检测方法,并在商用IR-UWB设备上搭建了UWFall原型系统,系统原型如图1所示. UWFall设备仅使用了单个IR-UWB设备实现了跌倒检测. IR-UWB雷达生成一系列超宽带脉冲,通过发射天线传输到空间中,再由接收天线捕获来自各种物体的反射信号. 在室内环境中存在跌倒行为的情况下,坠落时对地面的冲击会产生相应的振动,这些振动由坠落位置向外延伸,沿着固体结构传播到整个空间中. 因此,UWFall在整个空间域上捕获并分析这些振动信号来进行跌倒检测. 重要的是,当跌倒发生在感知区域外时,振动信号仍然可以传播到感知区域内,并被IR-UWB设备捕获. 因此,UWFall可以实现在感知范围外的目标跌倒检测.
然而在实际运用中,接收信号的变化不仅包含由跌倒触发的振动,还包括人类其他活动或物体的反射信号. 因此,需要对信号进行全面的建模和处理来提取与振动相关的特征,确保系统能够准确可靠地识别复杂环境中的跌倒事件. 具体来说,UWFall首先利用快时间仓中的信号连续性设计首仓比值(first bin ratio, FBR)算法,用来消除由硬件缺陷引起的相位偏移. 随后,对快慢时间矩阵设计掩码矩阵,实现不同信号分量的自适应识别和分离,用以减少来自各种因素的干扰,从而提取出仅与振动相关的信号频谱. 然后,在IQ平面上结合熵和最远点对距离(farthest points-pair distance, FPD)算法,从接收到信号的时间序列中提取出微弱的振动特征. 最后,采用多径振动融合(multipaths vibration merge, MVM)算法来增强信号特征,并采用模式匹配算法来实现鲁棒的跌倒检测. 这一系列信号分析和处理方法使得UWFall系统即使在复杂环境中也能准确鲁棒地检测跌倒行为.
为了评估UWFall的性能,分别要求参与者在视距和非视距条件下进行跌倒模拟,并在不同的室内环境中进行了大量的测试实验. 实验结果表明,与现有方案相比,UWFall在准确性和鲁棒性方面表现出卓越的性能,成为室内跌倒检测的可靠有效解决方案,在感知极限距离5 m内的准确率均超过90%,在感知扩展距离7 m内的准确率均超过86%.
本文的主要贡献包括3个方面:
1)通过感知环境范围内的振动特征实现对于商用IR-UWB设备的超感知距离的目标跌倒检测方法,并开发了UWFall系统.
2)设计了IQ熵和最远点对距离算法,从而可以精准提取时域信号中的振动特征,提升了跌倒感知精度.
3)通过大量实验测试表明,UWFall系统仅使用单个IR-UWB设备在视距、非视距以及超远感知距离场景下实现高精度的跌倒检测.
我们的工作与2个方向密切相关:1)跌倒检测;2)振动感知. 本节全面回顾了这些领域的最新研究成果.
跌倒检测可以分为:接触式和非接触式两类.
接触式解决方案通常依赖于包含惯性测量单元(inertial measurement unit, IMU)和陀螺仪等可穿戴传感器的设备,包括智能手机[2]、智能手环 [3-4]等,其需要用户佩戴传感设备来检测跌倒行为. 然而,老年人记忆功能的下降会导致经常忘记佩戴这些设备. 此外,引入额外硬件会给老年人的日常生活带来不必要的负担. 因此,基于可穿戴的解决方案难以在现实场景中广泛部署.
为了解决接触式方案的局限性,出现了非接触式跌倒检测方案. 这些解决方案包括基于相机的方法[5]、基于声学的方法[6]、基于WiFi的方法[7]和基于毫米波的方法[8]. 基于摄像头的跌倒检测系统利用摄像头捕捉人类活动的图像或视频序列,通过计算机视觉识别方案识别跌倒动作. 然而,基于摄像头的解决方案涉及到严重的隐私问题,给家庭生活场景中的设备部署带来了困难. 此外,在NLoS场景中,基于相机的方法可能表现出较低的精度并产生较高的计算成本,这使得它们在非接触式跌倒检测系统中不太可取. 基于声学的跌倒检测解决方案不断涌现,提取跌倒事件产生的独特的声学特征,并使用机器学习算法进行处理. 然而,现实世界场景中的高噪声和声学信号的高衰减特性使这些解决方案只适用于短程场景. 基于射频的非接触式解决方案相关中,基于WiFi的跌倒检测已经引起了人们的关注,基于RSSI的解决方案[9]高度依赖于环境模式,这使得它更适合实验室设置,在实际中实现鲁棒性跌倒变得很有挑战性. 近年来提出的基于CSI的解决方案[10],仍然容易受到环境干扰,并且占用了通信信道,从而对家庭WiFi通信造成干扰. 基于毫米波雷达[11]的方法通过利用多普勒频率直接测量目标运动速度. 然而,实现远距离高分辨率需要在更大带宽下运行专用射频电路,这导致硬件成本的上升.
近年来,基于IR-UWB的跌倒检测解决方案[12]引起了学术界和工业界的关注. IR-UWB技术的优点在于低功耗、低成本和远距离高分辨率,使得基于IR-UWB的跌倒检测解决方案[13]能够获得优异的性能.IR-UWB被广泛应用于低功耗通信系统,也被应用于成像、定位、跟踪、材料识别和生命体征检测. SoilId[14]将无人机与COTS IR-UWB集成在一起,用于大面积土壤湿度感知,消除了对需要电池供电的地面设备的依赖. MLRT[15]结合了使用注意力机制的Transformer,提取雷达的时间序列信号特征,用于身份识别和跌倒检测. Chen等人[16]提出的变长序列迭代卷积递归网络增强了IR-UWB在车辆目标识别中的性能. Dang等人[17]提出了一种基于IR-UWB 雷达的非接触式多人生命体征检测方法,有效地分离和提取了呼吸和心跳信号. Khan等人[18]利用IR-UWB技术开发了一种可靠的人员室内检测和定位方法,以降低工业场景中人机混合环境下的碰撞风险,从而提高安全性. Kwon等人[19]介绍了一种基于注意力的双向长短期记忆(Attention Bi-LSTM)模型,用于使用IR-UWB进行自动睡眠阶段评分,展示了其远程检测生命体征的能力. 这些研究共同揭示了IR-UWB技术在各个领域的潜力,包括高距离分辨率和低功耗,使其成为一种具有广泛应用的强大工具.
近年来,研究人员提出了基于振动的智能感知系统在各种应用中的进展. VibroTag[20]通过提取微弱的振动特征来实现对不同物体表面的识别,表现出对环境噪声和硬件的鲁棒性. Clean Vibes[21]引入了一种新型的洗手检测方法,测量洗手活动引起的水槽结构振动特征. RF-Ear+[22]可以准确监测多个设备的机械振动,而无需在每个设备上贴标签. Yang等人[23]提出的系统将手指输入认证扩展到触摸屏之外的物联网(Internet of things , IoT)设备的任何固体表面. 此外,Maria等人[24]对基于振动的感知系统进行了全面总结,该系统广泛应用于各个领域,包括评估人类健康、识别个人行为、推断事故信息、评估人身安全和监测基础设施健康. 这些创新系统集中展示了基于振动的传感在不同领域的潜力和多功能性.
本节深入研究了IR-UWB雷达的感知原理和振动信号建模.
IR-UWB雷达的等效基带模型如图2所示. 如UWHear[25]中所建议的,使用高斯脉冲$ g(t) $的基带信号可以表示为:
$ g\left({t}\right)={{V}}_{\mathrm{T}\mathrm{X}}{\rm{exp}}\left(-\frac{{{t}}^{2}}{2{\mathrm{\tau }}^{2}}\right)={{V}}_{\mathrm{T}\mathrm{X}}{\rm{exp}}\left(-2{\text{π}}^{2}{{f}}_{\mathrm{b}}^{2}{\rm{lg}}\left({\rm e}\right){t}^{2}\right), $
其中$ {V}_{\rm{TX}} $表示高斯脉冲包络,$ {f}_{\rm b} $表示$ -10\ {\rm{dB}} $带宽. IR-UWB雷达以载波频率$ {f}_{\rm c} $对高斯脉冲$ g\left(t\right) $进行上变频,发射信号可以表示为:
$ x\left({t}\right)=g\left({t}\right)\mathrm{cos}\left(2{\text{π}}{{f}}_{\mathrm{c}}{t}\right) .$
在空间域中存在多径反射,信道状态描述为:
$ h\left(t\right)=\sum _{p=1}^{P}{\mathrm{\alpha }}_{p}\mathrm{\delta }\left(t-{\mathrm{\tau }}_{p}\right). $
IR-UWB 雷达接收到的信号经由空间反射后可以表示为:
$ y\left(t\right)=x\left(t\right)* h\left(t\right)+n\left(t\right). $
代入信道状态,式(4)可以修改为:
$\begin{split} y\left(t\right)=&g\left(t\right)\mathrm{cos}\left(2{\text{π}} {f}_{\rm c}t\right)*\sum _{p=1}^{P}{\mathrm{\alpha }}_{p}\mathrm{\delta }\left(t-{\mathrm{\tau }}_{p}\right)+n\left(t\right) =\\&\sum _{p=1}^{P}{\alpha }_{p}g\left(t-{\tau }_{p}\right)\times \mathrm{cos}\left(2{\text{π}} {f}_{\rm c}\left(t-{\tau }_{p}\right)\right)+n\left(t\right) \end{split}.$
使用低通滤波器进行下变频,可以获得基带信号的同相分量$ {r}_{\rm In}\left(t\right) $:
$ \begin{split}&{r}_{\rm In}\left(t\right) =LPF\left[y\left(t\right)\cdot \mathrm{cos}\left(2{\text{π}}{f}_{\rm c}t\right)\right] =\\&LPF\Bigg[\sum_{p=1}^{P}{\mathrm{\alpha }}_{p}g(t-{\mathrm{\tau }}_{p})\times \mathrm{c}\mathrm{o}\mathrm{s}(2{\text{π}}{f}_{\rm c}(t-{\mathrm{\tau }}_{p}))\times\\&\quad \mathrm{cos}\left(2{\text{π}}{f}_{\rm c}t\right)+n\left(t\right)\Bigg] =\\&LPF\Bigg[\sum_{p=1}^{P}{\mathrm{\alpha }}_{p}g\left(t-{\mathrm{\tau }}_{p}\right)\times \frac{1}{2}\Bigg(\mathrm{c}\mathrm{o}\mathrm{s}(2{\text{π}} {f}_{\rm c}(2t-{\tau }_{p}))+\\&\quad \mathrm{c}\mathrm{o}\mathrm{s}(2{\text{π}} {f}_{\rm c}{\tau }_{p})\Bigg)+n\left(t\right)\Bigg] =\\&\frac{1}{2}\sum_{p=1}^{P}{\mathrm{\alpha }}_{p}g(t-{\mathrm{\tau }}_{p})\times \mathrm{cos}\left(2{\text{π}}{f}_{\rm c}{\mathrm{\tau }}_{p}\right)+n\left(t\right) \end{split}$.
同理可以获得基带信号的正交分量$ {r}_{\rm Qu}\left(t\right) $. 最后,通过重新组合基带信号的同相和正交分量,可以获得最终的反射信号:
$ r\left(t\right)={r}_{\rm In}\left(t\right)+i{r}_{\rm Qu}\left(t\right) $
IR-UWB雷达在空间中以特定的脉冲重复频率(pulse repetition frequency, PRF)$ {f}_{\rm s} $广播脉冲信号. 然后对每个帧的接收信号进行叠加以形成慢时间维度数据. 在每一帧中,IR-UWB雷达样本在快时间维度上具有固定的时间间隔$ {T}_{\rm s} $. 然后,对每个仓采样的信号进行叠加,以形成快时间维度,从而获得快慢时间矩阵$ {\boldsymbol R}_{t,\mathrm{\tau }} $,如图3所示.
然而,由于带宽限制,即$ {f}_{\rm s}=B $,IR-UWB雷达的距离分辨率$ {\Delta }D=\dfrac{c{T}_{\rm s}}{2}=\dfrac{c}{2B} $. 在实际应用中,快慢时间矩阵的形式如图4所示. 由于不同距离的物体具有不同的反射信号路径长度,因此在快时间维度采样中,它们落入不同的仓中. 如图4所示,红色矩形框中存在动态目标,而黑色矩形框中存在静态目标.
图5可以看到来自动态目标的信号在相邻的距离仓之间变化,而来自静态目标的信号保持在相同的距离仓中.
快慢时间矩阵中的每个元素都是由快时间$ \mathrm{\tau } $和慢时间$ t $决定的函数,反映了空间中物体到雷达设备的距离:
$ {R}_{t,\mathrm{\tau }}={\mathrm{\alpha }}_{t,\mathrm{\tau }}{\rm e}^{-j2{\text{π}}{f}_{\rm c}\mathrm{\tau }}\cdot s\left(t-\mathrm{\tau }\right)+n\left(t\right) \text{,} $
其中,$ \alpha $表示信号的振幅,$ \mathrm{\tau } $ 表示由信号反射引起的时间延迟,$\tau $决定了信号的相位.
本节全面介绍了基于IR-UWB的跌倒检测系统,首先通过IR-UWB发射连续脉冲,并捕获来自周围物体的反射信号,然后从反射信号中提取振动特征,最终实现跌倒检测的目标. 在系统设计过程中,面临以下技术挑战:
1)如何有效地从反射信号中提取特征对于识别跌倒至关重要. 由于跌倒行为的多样性,坠落会以不同的姿势和方向发生,导致了不同的信号变化模式. 如何提取鲁棒的特征来表示信号变化模式是一项具有挑战性的任务. 因此,UWFall创新性地捕捉跌倒引起的环境振动,这使得信号变化模式不再与人类的运动特征,如姿势和方向相关联.
2) 接收信号容易受到来自物体反射、多径效应和系统缺陷的强干扰. 这些干扰会使源自人类跌倒的振动信号显著失真,干扰通常超过振动信号的能级. 因此,必须设计一系列消除这些干扰的解决方案,确保提取到仅由坠落产生的振动信号.
3) 尽管减轻了上述干扰,但源自振动引起的信号变化仍然异常微弱,如何准确地将振动信号与高斯噪声分离也是一个挑战.
因此,通过坠落引起的振动信号变化准确识别出跌倒事件仍然是一项复杂的任务.
UWFall由4个核心模块组成:信号建模和预处理模块、信号分量分离模块、振动特征提取模块和跌倒识别模块. 系统工作流程如图6所示,在信号建模和预处理模块中,采用FBR算法来解决硬件缺陷引起的相移问题. 在信号分量分离模块中,引入了掩码矩阵来有效地处理不同类型的反射信号,从而提取出仅与振动相关的信号矩阵. 振动特征提取模块集成了熵和FPD算法来提取细微的振动特征. 跌倒识别模块结合多径融合和模式匹配算法,其作用是从不同距离仓中提取与跌倒相关的振动特征进行合并与增强.
IR-UWB以等间隔发射相同的脉冲信号,这些脉冲信号经过环境中各种物体反射会到接收终端,因此接收信号中包含了感知范围内各个物体的相关信息. 传统跌倒检测方法[26]将接收信号划分为动态分量和静态分量,通过检测人员姿态和动作来识别跌倒行为. 此类信号建模方法可以识别分米级的人员姿态和动作,而由于人员跌倒引起的物体振动信号为亚毫米级[27],因此传统方法无法满足捕捉跌倒相关的振动信号所需要的精度. 因此,基于信号相位在快速时间维度上的变化趋势,进一步将动态信号细分为仓间分量和仓内分量. 这种细分的标准是基于空间中动态物体的速度是否超过额定阈值$ {v}_{0} $,表示为$ {v}_{0}=\dfrac{{d}_{\rm{bin}}}{{t}_{\rm{frame}}} $,其中$ {d}_{\rm{bin}} $表示单个距离仓的宽度,$ {t}_{\rm{frame}} $表示单个帧的时间长度. $ {v}_{0} $的物理意义在于确定空间中的动态对象是否可以影响多个距离仓的信号变化. 这2类动态信号分量如图7所示.
在图7中,蓝色矢量表示运动物体反射的信号. 可以看到即使物体没有发生位移,由于高斯噪声的存在,静态分量在IQ空间中仍存在微弱的信号变化,如图7(a)中的绿色采样点所示. 然而,这种变化相对集中在IQ空间的某个点上. 当物体运动且其速度小于$ {v}_{0} $时,导致相邻的慢时间维度上的信号样本落入相同的快时间仓中,如图7(a)中的红色向量所示. 这使得在分析同一快时间仓中的信号时观察到相位连续性. 接收信号是物体反射的静态分量和动态分量的矢量和,如蓝色矢量所示. 这类由空间中的小幅运动引起的信号分量被定义为Sintra-bin,它们的相位变化是连续的. 然而,当物体位移的幅度和速度超过临界值$ {v}_{0} $时,同一运动物体的相邻慢时间维度的信号样本会落入2个不同的快时间仓中,导致在分析同一仓中的信号时发生混沌的相位变化,如图7(b)中的蓝色向量所示. 在图7(b)中,当分析同一个仓中的信号变化时,运动物体反射的不同动态分量存在于同一仓中,如红色矢量所示. 由于运动物体引起的变化幅度不同,同一个仓中的蓝色矢量显得混乱无序. 这种类型的运动引起的接收信号分量被定义为Sinter-bins.
在实验中使用了100 Hz的慢时帧采样率,导致临界速度$ {v}_{0}=\dfrac{{d}_{\rm{bin}}}{{t}_{\rm{frame}}}=\dfrac{0.05\ {\rm m}}{0.01\ {\rm s}}=5\ {\rm m}/{\rm s} $. 然而,由于信号处理对样本数量有一定的需求,实际临界速度远小于$ {v}_{0} $. 图8分别展示出了快慢时间矩阵和IQ空间中的3种类型的信号分量,即$ {S}_{\rm{static}} $、Sinter-bins和Sintra-bin. 图8(b)中的绿色样本展示了IQ空间中的静态分量,这些分量在图8(a)的绿色矩形框中保持相对稳定. 黄色和红色矩形框中的信号分量在传统分类方法下被定义为空间中的动态分量,可以看到它们之间存在显著差异. 红色矩形中的动态分量是由IQ空间中物体的大幅移动引起的,在整个快慢时间矩阵中显示出连续性,对应如图8(b)中蓝色样本点所示,在IQ空间中分析单个快时间仓时缺乏相位连续性,显得混乱无序. 即使在$ 0.2\ {\rm{m/s}} $的实际运动速度下,同一仓中的Sintra-bin仍然表现出相位不连续性. 相反,图8(a)中黄色矩形框中的动态分量是由物体在空间中的轻微运动引起的,对应图8(b)中所示的黄色样本点,在单个快速时间仓内的IQ空间中表现出较强的相位连续性. 由于我们需要在单个快时间仓内分析振动信号,因此必须对这2种类型的动态信号进行独立建模和分析.
在人类跌倒检测的背景下,接收信号$ r(t) $可以被建模为多种信号分量的线性组合,包括$ {S}_{\rm{static}} $、Sinter-bins、Sintra-bin和噪声. 接收信号可以表示为:
$ r\left(t\right)={S}_{\rm{static}}\left(t\right)+{S}_{\rm{inter{\text -}bins}}\left(t\right)+{S}_{\rm{intra{\text -}bin}}\left(t\right)+n\left(t\right). $
根据IQ空间中的信号在快速时间仓中的相位连续性对Sintra-bin进行了细分,分为小幅位移、微弱振动和高斯白噪声. 图9展示了IQ空间中这2种信号类型之间的区别. 图9(a)显示了由小幅位移引起的信号变化,其中位移引起的信号幅值变化远大于高斯噪声. 因此,以位移为主的信号变化呈现出明显的方向性趋势. 在足够的时间窗口内,可以观察到由小幅位移引起的周期性信号变化,如图9(a)中的圆形信号轨迹所示. 相反,由振动引起的信号变化幅值非常微弱,这使得在相邻采样间隔内消除高斯噪声的干扰具有挑战性,如图9(b)所示. 在这种情况下,无论时间窗口的大小如何,振动信号都不会表现出规则的周期性变化,因为它们无法克服高斯噪声的干扰. 虽然振动不会引起周期性的信号变化,但仍然会在振动方向上引入偏移,即本应呈现圆形高斯分布的信号在某个方向上延伸,如图9(b)所示.
由于Sintra-bin包括小幅位移$ {S}_{\rm d} $、微弱振动信号$ {S}_{\rm v} $和高斯白噪声,因此单个慢时间仓中的信号可以建模为3个信号的总和:$ {S}_{\rm{inter{\text -}bins}}={S}_{\rm d}+{S}_{\rm v}+n(\mathrm{\tau }) $. 考虑到振动的存在,物体与IR-UWB雷达之间的距离$ d(t) $可以表示为:
$ d\left(t\right)={d}_{0}+{d}_{\rm v}\left(t\right)\text{,} $
其中,$ {d}_{0} $表示移动物体和IR-UWB收发器之间的静态距离,而$ {d}_{\rm v}(t) $表示由振动引起的距离变化. 将式(10)代入式(8)得到:
$ r\left(t\right)={\mathrm{\alpha }}_{t}{\rm e}^{j2{\text{π}}{f}_{\rm c}\frac{2d\left(t\right)}{c}}x\left(t-\frac{2d\left(t\right)}{c}\right)+n\left(t\right) . $
由于振动信号对相位变化的高灵敏度,必须减轻信号中的相位偏移. 传统方法不需要这种精确的相位感知,因此忽略了这些偏移. 当仅考虑单个信号仓之间的信号变化时,IR-UWB和WiFi信号表现出一些相似性,在信号相位中具有随机时变相移. 这些变化主要源于硬件缺陷. 由于RF振荡器不能确保绝对的相位精度,在每个信号帧的生成过程中存在固定的相移. 在基于相位的感知方法中,这种相移可能导致显著的感知误差. 为了有效地消除相移,我们设计了FBR算法,第$ i $个快时间仓中的接收信号可以表示为:
$ {r}_{i}\left(t\right)={\mathrm{\alpha }}_{i}\left(t\right){\rm e}^{j2{\text{π}}{f}_{\rm c}\tfrac{2{d}_{i}\left(t\right)}{c}+{{\theta }}_{o}\left(t\right)}x\left(t-\frac{2{d}_{i}\left(t\right)}{c}\right) \text{,} $
其中,$ {\mathrm{\alpha }}_{i}(t) $表示第$ i $个快时间仓中的信号衰减,$ {f}_{\rm c} $表示脉冲信号的载波频率,$ {d}_{i}(t) $表示运动物体和雷达设备之间的距离,$ c $表示脉冲信号的传播速度. 由于脉冲信号在每个慢时间帧中的相移是固定的,可以获得慢时间帧的每个仓中的信号与第1个快时间仓中信号的比值:
$\begin{split}\frac{{r}_{i}\left(t\right)}{{r}_{1}\left(t\right)}=&\dfrac{{\mathrm{\alpha }}_{i}\left(t\right){\rm e}^{j2{\text{π}}{f}_{\rm c}\tfrac{2{d}_{i}\left(t\right)}{c}+{\mathrm{\theta }}_{o}\left(t\right)}x\left(t-\dfrac{2{d}_{i}\left(t\right)}{c}\right)}{{\mathrm{\alpha }}_{1}\left(t\right){\rm e}^{j2{\text{π}}{f}_{\rm c}\tfrac{2{d}_{1}\left(t\right)}{c}+{\mathrm{\theta }}_{o}\left(t\right)}x\left(t-\dfrac{2{d}_{1}\left(t\right)}{c}\right)} =\\&\frac{{\mathrm{\alpha }}_{i}\left(t\right){\rm e}^{j2{\text{π}}{f}_{\rm c}\tfrac{2{d}_{i}\left(t\right)}{c}}x\left(t-\dfrac{2{d}_{i}\left(t\right)}{c}\right)}{{\mathrm{\alpha }}_{1}\left(t\right){\rm e}^{j2{\text{π}}{f}_{\rm c}\tfrac{2{d}_{1}\left(t\right)}{c}}x\left(t-\dfrac{2{d}_{1}\left(t\right)}{c}\right)} . \end{split}$
第1个仓比值算法的有效性如图10所示,其中明显消除了硬件缺陷引起的相移. 选择第1个快时间仓是由于其受干扰较低,几乎可以忽略来自物体反射的信号干扰,同时在第1个快时间仓中的直流分量有较高的占比. 此外,跌倒产生的振动信号通常会持续一段时间而不是立即消失. 因此,我们使用了一个滑动窗口来感知持续时间内的信号.
在真实环境中,运动物体的位置变化不可避免地会对感知信号的振动特征造成干扰,使相位变化变得难以察觉. 此外,由于这种运动引起额外的多径干扰,使得振动信号更加难以被准确感知. 因此,区分快慢时间矩阵中不同类型的信号并提供相应的去噪方法至关重要. 我们设计了掩码矩阵算法来自适应识别和处理快慢时间矩阵中的不同信号分量.
在真实的室内环境中,存在大量的静态物体,并且由这些物体引起的反射信号的幅度远大于振动信号的幅度,导致振动信号被淹没在静态信号$ {R}_{\rm{static}} $中. 为了消除这部分静态信号,可以采用静态杂波抑制[28],抑制后的信号矩阵可以表示为:
$ \left({\widehat{R}}_{t,\mathrm{\tau }}\right)=\beta \left[{R}_{t,\mathrm{\tau }}-\left({\widehat{R}}_{t-1,\mathrm{\tau }}\right)\right] \text{,} $
其中,$ t $和$ \tau $分别表示信号矩阵的慢时间维度和快时间维度中的索引. $ {R}_{t,\mathrm{\tau }} $是原始信号矩阵中的一个元素,并且$ \beta \in (\mathrm{0.95,1}) $. 在这种情况下,信号矩阵$ \widehat{\boldsymbol R} $中的静态反射信号已经被有效地消除,只留下包含振动特征的动态信号.
经过静态杂波抑制的信号矩阵$ \widehat{\boldsymbol R} $仍然包含2种类型的信号干扰,即$ {R}_{\rm{inter{\text -}bins}} $和$ {R}_{\rm{intra{\text -}bin}} $. 我们观察到仓间动态分量$ {R}_{\rm{inter{\text -}bins}} $是由空间中的大幅运动引起的,会导致非线性的信号变化. 如图11所示,尽管这些信号变化在相邻的快时间仓中表现出相似性,但它们的持续时间变化往往不同. 现有方法中的动态时间规整(dynamic time warping, DTW)是一种有效的时间序列对齐算法,能够处理不同长度的时间序列,对噪声和误差具有良好的适应性,这使得它成为在空间中识别仓间信号的理想选择. 然而,传统的DTW算法不能直接应用于IR-UWB信号处理. 如图11(a)所示,DTW算法在识别仓间信号上并不理想. 这主要是因为相同运动引起的相邻快速时间仓中的信号变化可能相似或相反. 在不失一般性的情况下,假设空间中的物体从第$ i $个快时间仓移动到第$ j $个快时间仓,从第$ i $个快时间仓开始,空间中反射信号的强度逐渐降低. 同时,从第$ j $个快时间仓开始,由于动态物体的进入,空间中的反射信号由弱变强. 因此,同一物体的运动可能在不同的快时间仓中产生完全相反的信号变化. 基于这一观察,本文创新性地设计了一种仓间信号定位算法Dual-DTW,其通过计算相邻快时间仓之间的相似性来提取$ {R}_{\rm{inter{\text -}bins}} $.
首先从$ \widehat{\boldsymbol R} $中提取信号幅度矩阵$ {\boldsymbol A} $,如式(15)所示.
$\begin{split} {\boldsymbol{A}} = abs{\boldsymbol \left({\widehat{{\boldsymbol{R}}}}\right)} = &\left( \begin{array}{cc}\begin{array}{cc}{a}_{\mathrm{1,1}}& {a}_{\mathrm{1,2}}\\[-2pt] {a}_{\mathrm{2,1}}& {a}_{\mathrm{2,2}}\end{array}& \begin{array}{ccc}{a}_{\mathrm{1,3}}& … & {a}_{1,n}\\ {a}_{\mathrm{2,3}}& … & {a}_{2,n}\end{array} \\ \begin{array}{cc}{a}_{\mathrm{3,1}}& {a}_{\mathrm{3,2}}\\ \vdots & \vdots\\ {a}_{m,1}& {a}_{m,2}\end{array}& \begin{array}{ccc}{a}_{\mathrm{3,3}}& … & {a}_{3,n}\\ \vdots& \ddots &\vdots\\ {a}_{m,3}& … & {a}_{m,n}\end{array}\end{array} \right) =\\& \quad \left(\begin{array}{cc}\begin{array}{cc}{{\boldsymbol{a}}}_{1}& {{\boldsymbol{a}}}_{2}\end{array}& \begin{array}{ccc}{{\boldsymbol{a}}}_{3}& \cdots & {{\boldsymbol{a}}}_{n}\end{array}\end{array}\right).\end{split} $
随后,计算相邻快时间仓的信号相似性,构建式(16)中的正向原始距离矩阵$ \boldsymbol M $:
$ M\left(i,j\right)=\left|{a}_{k}\left(i\right)-{a}_{k+1}\left(j\right)\right|,\left(1 < i,j < n\right) \text{,} $
其中$ {a}_{k}(i) $表示在第$ k $个快时间仓的第$ i $个慢时间帧中接收的信号强度. 然后计算累积距离矩阵$ {\boldsymbol D} $:
$\begin{split}D\left(i,j\right)=&M\left(i,j\right) +{\rm{min}}\{{D}_{\rm{min}}\left(i,j-1\right),{D}_{\rm{min}}\left(i-1,j\right),\\&{D}_{\rm{min}}\left(i-1,j-1\right)\} .\end{split} $
本文将$ D(i,j) $定义为快时间仓中2个相邻慢时间序列之间的累积距离,$ M(i,j) $表示第$ k $个快时间仓的第$ i $个慢时间帧与第$ k+1$个快时间仓的第$ j $个慢时间帧之间的幅度差. 正向距离$ d=d(n,n) $表示2个相邻快时间仓的累积距离. 为了建立反向原始距离矩阵,引入$ \overline{M}(i,j)=\left|{a}_{k}(i)+{a}_{k+1}(j)\right| $,并计算其累积距离$ \overline{D}(i,j) $以及2个快时间仓的时间序列之间的反向距离$ \overline{D}=\overline{D}(n,n) $. 最后,将相邻快时间仓的相似性定义为正向距离和反向距离的最小值,即$ {d}_{\rm{min}}=\mathrm{min}(d,\overline{d}) $. 较小的$ {d}_{\rm{min}} $值表示2个时间序列之间的距离较小,反映了它们的高度相似性. 在实验中,观察到由$ {R}_{\rm{inter{\text -}bins}} $引起的相邻快时间仓的距离远小于由其他信号分量引起的相邻快时间仓的距离. 为了防止2个静态仓中的信号具有高度相似性,在计算相邻快时间仓的距离之前引入了人工添加的高斯噪声. 如图11(b)所示,Dual-DTW算法准确地识别了仓间动态分量. 这些分量不仅影响局部快时间仓,而且会显著干扰后续几个快时间仓的反射路径. 因此,在随后的距离仓中引入衰减函数$ w(d) $来消除这些干扰. 根据Friis公式,信号衰减与传播距离的平方成正比,由式(18)给出.
$ {P}_{r}=\frac{{P}_{t}{G}_{t}{G}_{r}{c}^{2}}{{\left(4{\text{π}}df\right)}^{2}} . $
因此,衰减函数被设置为距离相关函数:
$ {w}\left(d\right)=\frac{{\mathrm{\omega }}_{1}{{\mathrm{e}}}^{-{\mathrm{\omega }}_{2}{d}^{2}}}{1+{{\mathrm{e}}}^{-{\omega }_{2}{d}^{2}}} \text{,} $
其中,$ {\omega }_{1}  $和$ {\omega }_{2} $为常数.
为了解决由小幅位移引起的仓内动态信号带来信号干扰,这些信号在快时间仓内表现出相位连续性,因此本文提出一种相位拐点计数算法. 图12展示了该算法在识别仓内动态信号方面的有效性.
在图12(a)中,小幅运动的信号能级明显高于高斯噪声的能级. 因此,当前快时间仓中的时间序列由于小幅移动而表现出相位连续性. 然而,在图12(b)中,尽管存在振动分量,但振动的能级太低而无法主导当前快时间仓中的时间序列,这导致在由高斯噪声主导的时间序列中缺乏相位连续性. 为了定量描述时间序列的相位连续性,采用了拐点计数法. 首先,计算时间序列$ {s}_{k} $中拐点的充分条件:
$ {s}''\left({t}_{i}\right)=0 . $
接下来,计算拐点的必要条件:
$ {s}''\left({t}_{i-\mathrm{\delta }}\right)\cdot {s}''\left({t}_{i+\mathrm{\delta }}\right) < 0 . $
如图12所示,由小幅运动引起的时间序列中的拐点数量明显少于仅包含振动分量的时间序列. 通过拐点计数算法可以自适应地分离出仓内动态分量,为了消除其对于振动信号的干扰,在掩码矩阵中将对应的信号样本索引的权重设置为0.
在掩码矩阵的处理后,接收信号的快慢时间矩阵中只包含振动分量. 为了最大化提取振动分量的特征,传统方法采用最优观测点选择算法将微弱运动的振动信号变化近似为圆形,优化过程为:
$ \left({e}^{*},{r}^{*}\right)=\mathop{\rm{arg\;min}}\limits_{e,r}\sum _{x\in X}{\left(\Vert x-e\Vert-r\right)}^{2} . $
该优化方法主要用于找到圆心位置$ e$,进而将其确定为信号变化的最佳观测点,以实现信号增强效果. 研究表明,采用圆形拟合方法可以极大增强射频反射信号[29]. 然而在振动感知过程中,由于振动导致的信号幅值变化较为微弱,目标信号趋势没有呈现出显著的周期性变化,进而导致基于圆形拟合方法失效. 如图13所示,当空间中没有振动信号时,接收到的信号以高斯白噪声的形式分布在理论值附近的圆形区域中. 尽管在单个周期内IQ空间中的信号变化没有明显的趋势,但来自多个周期的振动信号不可避免地导致在振动方向上的信号产生偏移.
综上所述,本文使用熵和最远点对距离的组合来提取振动信号,其首先计算短时间窗口内信号的熵,以对空间中的事件(如静态事件和动态事件)进行粗粒度分类. 识别为动态事件后,然后计算特征的最远点距离,以此进一步区分日常活动和跌倒事件.
在实验过程中,我们注意到感知空间中振动信号的存在会导致IR-UWB的反射信号在IQ空间中沿着振动方向发生偏移,如图13所示. 虽然这种变化是微弱的,但它增加了IQ空间中信号的无序性. 因此,自然考虑利用熵在粗粒度水平上估计IQ域中信号的无序性,并将其用作激活细粒度最远点距离算法的条件. 首先,在整个时间序列上使用动态滑动窗口来提取离散点集$ P $,该点集包括IQ域中的$ n $个样本用于熵计算. 然后确定当前时间窗口内IQ空间中离散信号的中心点$ {p}_{\rm c}=({I}_{0},{Q}_{0}) $. 考虑到目标信号在计算时间窗口内存在无序性,且在空间中噪声遵循高斯分布的条件下,可以假设在整个持续时间内信号均遵循高斯分布. 为了减轻异常噪声和信号偏移的影响,并增强信号的中心趋势,采用二维高斯拟合方法在当前时间窗口内选择信号的中心点.
$ f\left(I,Q\right)=\alpha {\rm e}^{-\tfrac{{\left(I-{I}_{0}\right)}^{2}}{2{\mathrm{\sigma }}_{I}^{2}}-\tfrac{{\left(Q-{Q}_{0}\right)}^{2}}{2{\mathrm{\sigma }}_{Q}^{2}}} \text{,} $
其中$ \alpha $、$ {I}_{0} $、$ {Q}_{0} $、$ {\mathrm{\sigma }}_{I} $和$ {\mathrm{\sigma }}_{Q} $是高斯拟合的系数. 对式(23)两边取对数:
$ \begin{split}& \mathrm{ln}\left(f\right)= \mathrm{ln}\left(\mathrm{\alpha }\right)-\frac{{\left(I-{I}_{0}\right)}^{2}}{2{\mathrm{\sigma }}_{I}^{2}}-\frac{{\left(Q-{Q}_{0}\right)}^{2}}{2{\mathrm{\sigma }}_{Q}^{2}} =\\&\;\;\mathrm{ln}\left(\mathrm{\alpha }\right)-\frac{{I}^{2}}{2{\mathrm{\sigma }}_{I}^{2}}+\frac{{I}_{0}I}{{\mathrm{\sigma }}_{I}^{2}}-\frac{{I}_{0}^{2}}{2{\mathrm{\sigma }}_{I}^{2}}-\frac{{Q}^{2}}{2{\mathrm{\sigma }}_{Q}^{2}}+\frac{{Q}_{0}Q}{{\mathrm{\sigma }}_{Q}^{2}}-\frac{{Q}_{0}^{2}}{2{\mathrm{\sigma }}_{Q}^{2}}\end{split}. $
为了确定系数,采用了最小二乘法.
$\begin{split}&\mathrm{min}\sum \left(\mathrm{ln}\left(\mathrm{\alpha }\right)-\frac{{I}^{2}}{2{\mathrm{\sigma }}_{I}^{2}}+\frac{{I}_{0}I}{{\mathrm{\sigma }}_{I}^{2}}-\frac{{I}_{0}^{2}}{2{\mathrm{\sigma }}_{I}^{2}}-\frac{{Q}^{2}}{2{\mathrm{\sigma }}_{Q}^{2}}+\right.\\&\quad\quad \left. \frac{{Q}_{0}Q}{{\mathrm{\sigma }}_{Q}^{2}}-\frac{{Q}_{0}^{2}}{2{\mathrm{\sigma }}_{Q}^{2}}-\mathrm{ln}\left(f\right)\right)^{2}. \end{split}$
在获得IQ空间中的中心点$ {p}_{\rm c} $之后,计算距离矩阵$ {\boldsymbol D} $,其中$ {D}_{i,j}=dist({p}_{i,j}-{p}_{\rm c}) $. 然后,将IQ空间划分为$ N=\dfrac{{D}_{\rm{max}}-{D}_{\rm{min}}}{L} $个同心圆,以$ {p}_{c} $为中心,其中$ L=1{\rm E}-4 $表示每个圆形区域的宽度. 对于每个点$ {P}_{i} $,落入第$ k $个圆形区域的概率为$ {P}_{k}=\dfrac{\sum\limits_{i=k-1}^{k}{P}_{i}}{\sum\limits_{i=1}^{N}{P}_{i}} $. 然后计算每个区域的信息量$ {e}_{k}=-p-k\mathrm{log}{p}_{k} $. 最后,计算整个IQ域的熵$ E $:
$ E=-\sum _{k=1}^{N}{p}_{k}\mathrm{log}{p}_{k} . $
首先,在当前慢时间窗口下获得快时间仓内脉冲信号IQ空间中的点集$ P=\left\{{p}_{1},{p}_{2},… ,{p}_{n}\right\} $. 然后,从点集中选择Q维中具有最小值的点作为基准点$ {p}_{0} $,并计算其相对于坐标原点的偏移$ {\boldsymbol Z}_{\rm{offset}}= \overrightarrow{{p}_{0}} $. 接下来,建立一个新的坐标系并平移空间中的所有点$ {P}'=P+ {\boldsymbol Z}_{\rm{offset}}$. 接着,计算点集在新坐标系中的相位角$ \phi= {\rm{arctan}}\dfrac{{P}_{Q}}{{P}_{I}} $,并按升序排列点集$ P'' $. 在相位角相同的情况下,优先考虑更靠近原点的点. 根据基本几何原理,可以推断$ {p}_{0}' $、$ {p}_{1}' $和$ {p}_{n}' $是凸包上的点. 接下来的目标是确定集合中的其他点是否也在凸包上. 为了实现这一点,首先将$ {p}_{0}' $、$ {p}_{1}' $和$ {p}_{2}' $放入栈中,以存储在凸包上. 随后,在栈顶使用第一和第二元素来构建一条线.
$ ({Q}_{2}-{Q}_{1})I+({I}_{1}-{I}_{2})Q+({I}_{2}{Q}_{1}-{I}_{1}{Q}_{2})=0 . $
然后,通过计算$ {D}_{k} $来确定点$ {p}_{k}' $位于直线的哪一侧:
$ {D}_{k}=\left({Q}_{2}-{Q}_{1}\right){I}_{k}+\left({I}_{1}-{I}_{2}\right){Q}_{k}+\left({I}_{2}{Q}_{1}-{I}_{1}{Q}_{2}\right) , $
如果$ {D}_{k} > 0 $,则表示点$ {p}_{k}' $位于线的右侧,表示栈顶的点不在凸包上. 因此,从栈顶弹出元素,并将当前点压入栈,如果$ {D}_{k} < 0 $,则表示点$ {p}_{k}' $位于线的左侧,表示栈顶的点位于凸包上. 在这种情况下,直接将当前点压入栈,以这种方式处理集合中的所有点. 在获得凸包$ V $之后,计算凸包上最远点对之间的距离. 在凸包上,被一对平行切线精确包围的点称为对跖点. 跖点数不超过$ 3n/2 $意味着计算对跖点的时间复杂度为$ O(n) $. 这种关于对跖点数量的保证增加了解决问题的时间复杂性.
步骤1:通过在Q方向上计算凸包上与极值$ {Q}_{\rm{min}} $相对应的点$ {v}_{i}({I}_{i},{Q}_{i}) $和与$ {Q}_{\rm{max}} $相对应的点$ {v}_{j}(I_j,{Q}_{j}) $.
步骤2:利用点$ {v}_{i} $和$ {v}_{j} $继续构建2条水平切线:
$ \frac{Q-{Q}_{i}}{{Q}_{j}-{Q}_{i}}=\frac{I-{I}_{i}}{{I}_{j}-{I}_{i}} . $
由于这些点已经形成一对对跖点,计算它们之间的距离并保持当前的最大值. 然后,假设$ {\boldsymbol A}= ({x}_{1},{y}_{1},{z}_{1}) $和$ {\boldsymbol B}=({x}_{2},{y}_{2},{z}_{2}) $.
$ \begin{split}{\boldsymbol A}\times {\boldsymbol B}=&\left(\begin{array}{ccc}i& j& k\\ {x}_{1}& {y}_{1}& {z}_{1}\\ {x}_{2}& {y}_{2}& {z}_{2}\end{array}\right) =\\&\left|\begin{array}{cc}{y}_{1}& {z}_{1}\\ {y}_{2}& {z}_{2}\end{array}\right|i-\left|\begin{array}{cc}{x}_{1}& {z}_{1}\\ {x}_{2}& {z}_{2}\end{array}\right|j-\left|\begin{array}{cc}{x}_{1}& {y}_{1}\\ {x}_{2}& {y}_{2}\end{array}\right|k =\\&\left({y}_{1}{z}_{2}-{z}_{1}{x}_{2}\right)i-\left({x}_{1}{z}_{2}-{z}_{1}{x}_{2}\right)j+\left({x}_{1}{y}_{2}-{y}_{1}{x}_{2}\right)k .\end{split} $
IQ平面是二维空间(设$ z=0 $),则重新定义$ {\boldsymbol a}= ({x}_{1},{y}_{1},0) $和$ {\boldsymbol B}=({x}_{2},{y}_{2},0) $. IQ空间中的叉积大小表示由2个矢量形成的平行四边形的有向面积.
$ \left|{{\boldsymbol{A}}}\times {{\boldsymbol{B}}}\right|=\left|{{\boldsymbol{A}}}\right|\times \left|{{\boldsymbol{B}}}\right|\mathrm{sin}\mathrm{\theta }={x}_{1}{y}_{2}-{x}_{2}{y}_{1} . $
经过比较,确定对跖点对之间距离的最大值是该IQ平面中2点之间的最大距离. 因此,计算:
$ {D}_{i,j}=\left({I}_{i}{Q}_{j}-{I}_{j}{Q}_{i}\right). $
步骤3:同时旋转2条切线,使其中一条与凸包的一条边对齐.
$ \frac{Q-{Q}_{i}}{{Q}_{j+1}-{Q}_{i}}=\frac{I-{I}_{i}}{{I}_{j+1}-{I}_{i}}. $
步骤4:在这个阶段,生成一对新的对跖点,并计算距离.
$ {D}_{i,j+1}=\left({I}_{i}{Q}_{j+1}-{I}_{j+1}{Q}_{i}\right) .$
将其与当前最大值进行比较,如果超过现有最大值则进行更新.
$ {D}_{\rm{max}}={\rm{max}}\{{D}_{\rm{max}},{D}_{i,j+1}\}. $
步骤5:重复步骤3和步骤4的过程,直到再次生成一对新的对跖点.
步骤6:输出具有最大直径的对跖点对,表示当前时间窗口内的距离.
计算单个凸包的最大距离时的时间复杂度为$ O(n) $. 考虑到凸包计算通常是该步骤的先决条件,而凸包计算的时间复杂度为$ O(n\mathrm{l}\mathrm{o}\mathrm{g}n) $,计算已知点集中最大距离的总时间复杂度为$ O(n\mathrm{l}\mathrm{o}\mathrm{g}n) $. 此外,凸包上的点与其对应边之间的距离变化为单峰函数,距离在增加到最高点后持续减少. 因此,在确定对跖点的过程中,直接采用枚举策略,并利用了单峰函数的性质,即当到下一个点的距离小于前一个点时停止枚举. 如图14所示,FPD可以有效区分跌倒和非跌倒事件,其中橙色曲线表示时间序列中的距离值,绿色曲线表示用以区分空间中的活动是动态事件还是静态事件的阈值,蓝色曲线表示用以区分动态事件是日常活动还是跌倒事件.
跌倒识别模块由2部分组成:多径融合和模式匹配.
利用最远点对距离可以有效识别跌倒,但考虑到振动信号极其微弱,融合多径以增强系统的鲁棒性是至关重要的. 因此,本文考虑了整个空间中所有快时间仓的振动信号. 首先对每个快时间仓中的信号进行归一化,然后计算整个帧上最远点距离的总和.
$ {D}_{\rm{sum}}=\sum_{i=1}^{N}\frac{{D}_{i}-{D}_{\rm{min}}}{{D}_{\rm{max}}-{D}_{\rm{min}}}. $
通过3.3节的信号处理,可以将空间内的活动分为3类:静态、动态和跌倒. 考虑到在现实世界场景中跌倒往往在进行活动时发生,本文将活动—跌倒—静态这样的组合识别为跌倒事件. 首先计算事件序列$ E $的长度$ n $,以及跌倒模式$ F $的长度$ m $. 然后,对跌倒模式$ F $进行预处理,生成事件移位表$ T $,将跌倒模式$ F $的起点与事件序列$ E $对齐,将$ i $设置为事件序列的开始位置,即$ i=0 $,将$ j $设置为跌倒模式的结束位置,即$ j=m-1 $. 然后,从跌倒模式末尾开始进行比较. 如果事件序列中相应位置的事件$ E[i+j] $与跌倒模式中的事件$ F[j] $相同,则继续比较前面的事件. 如果整个跌倒模式匹配成功,则返回事件序列中跌倒模式$ F $的起始位置$ i $. 如果事件序列中相应位置的事件$ T[i+j] $与跌倒模式中的事件$ F[j] $不同,则使用不匹配事件移位表$ T $和事件序列中跌倒模式结束位置对应的事件$ T[i+1] $来计算移位距离. 根据计算的偏移距离相应地移动跌倒模式. 如果移动到最后没有导致匹配,则识别出空间中不存在跌倒.
本文使用IR-UWB有效地实现了非接触式跌倒检测系统,并在不同房间中进行性能评估实验. 本节验证了系统的准确性和鲁棒性,并分析了不同因素对UWFall性能的影响.
硬件原型使用IR-UWB芯片X4M05,如图15(a)所示,采样率设置为$ 100\ \mathrm{H}\mathrm{z} $. 传输带宽为1.4 GHz的基带信号,并将信号进一步调制到7.29 GHz的载波上. IR-UWB通过串行接口连接到芯片上,用于发送和接收用于振动的RF信号. 数据采集模块使用Python 3.7实现,跌倒检测模块使用MATLAB R2021b实现. 所有代码都将在配备RTX 3060 GPU和AMD 5800H CPU的联想笔记本电脑上执行.
实验招募了5名不同身高、体重、年龄和性别的参与者. 考虑了多种常见的活动,包括跌倒、弯腰、跳跃、躺下、站起来、坐下、走路和闲逛等日常动作. 实验环境是一间5 m×8 m的卧室,配有木地板和家具,如图15(b)所示. 只有一台IR-UWB雷达被放置在角落,射程限制为5 m. 通过将IR-UWB雷达布置在2种不同的场景中,对应不同的多径条件,并改变参数和环境,来研究不同因素的影响.
本文引入了4个关键指标来评估UWFall的性能.
1)准确率($ Accuracy $). 表示正确检测到的动作所占百分比. $ Accuracy=\dfrac{TP+TN}{TP+FP+TN+FN} $.
2)精确率($ Precision. $)表示所有检测到的跌倒行为中正确检测到的跌倒动作所占百分比.
$ Precision=\frac{TP}{TP+FP} . $
3)召回率(Recall). 表示所有实际跌倒行为中正确检测到的跌倒动作所占百分比.
$ Recall=\frac{TP}{TP+FN} . $
4)F1分数(F1-score). 提供系统性能的总体衡量标准.
$ F1{\text -}score=\frac{2\times Recall \times Precision}{Recall+Precision} . $
其中$ TP $表示真阳性数,即实际跌倒正确识别为跌倒;$ FP $表示假阳性数,即非跌倒错误识别为跌倒;$ FN $表示假阴性数,即跌倒错误识别为非跌倒;$ TN $表示真阴性数,即实际非跌倒正确识别成非跌倒.
本文提出的UWFall利用人员跌倒引起的振动特征实现了与人员动作和姿势无关的跌倒检测任务,同时扩展了现有商用设备的感知极限距离. 为了对比本文所提方法和其他方法的性能,本文在商用X4M05设备上测试了其他3种跌倒检测方法. 其中,Maitre等人[26]通过使用UWB雷达和CNN-LSTM架构来检测室内环境中发生的跌倒事件. Sadreazami等人[30]通过从雷达信号矩阵中导出时间序列并将其送到深度卷积网络,从中自动学习多级特征,从而实现跌倒检测任务. Jiang等人[31]使用基于Transformer的MLRT模型实现室内环境中目标的跌倒检测. 与以上工作相比,UWFall主要基于目标跌倒所引起的环境物体振动现象来实现非接触式跌倒感知,不依赖于感知目标自身的行为活动所反射的信号,利用振动波的传播可以实现感知范围外的跌倒行为识别. 本文将平均识别准确率作为评价4种方法的指标,具体结果如表1所示.
观察表1可得,UWFall可以仅使用单个IR-UWB雷达实现和其他3种方法相似的跌倒识别准确率,均在90%以上. 更重要的是,UWFall可以有效地扩展感知范围,将感知距离提升到7 m. 综上所述,UWFall适用于大多数室内环境中的人员跌倒检测任务,并具有高精确的识别率与强鲁棒性特性.
在实验中,参与者在距离雷达设备不同处进行跌倒和非跌倒活动来评估系统在不同工作距离上的性能. 在1 m、2 m、3 m、4 m、5 m、6 m和7 m的距离上,共收集了350次跌倒和350次非跌倒,每个距离点记录了50次跌倒和50次非跌倒. 图16展示了系统在不同距离上的准确率、精确率、召回率和F1-score. 结果表明,当跌倒人员与雷达设备之间的距离在1~3 m范围内时,该系统的性能有所提高. 经过分析,在近距离(如1 m),将步行活动错误识别为跌倒的可能性更高. 然而,在3~7 m时,由于振动信号的衰减,系统性能有所下降. 较长的距离导致更低的信噪比,检测微弱的振动信号更加困难. 值得注意的是,在5 m的距离上,该系统保持了90%以上的准确率. 传统的依靠识别动作的跌倒检测系统的感知范围有限,只有5 m. 相比之下,利用振动特征可以将感知距离扩展到7 m,将感知范围扩展了40%. 即使在7 m的距离上,该系统的准确率也始终保持在86%以上. 性能超越了传统的解决方案,使本文能够实现超出感知距离极限的跌倒检测. 对于后续的实验,距离设置为5 m,这是传统方案的极限距离,确保本文方案与传统解决方案的兼容性,同时展示本文方法提供感知范围的扩展效果.
为了评估系统在不同水平角下的性能,将雷达设备部署在不同角度,包括$ -\dfrac{{\text{π}} }{2} $、$ -\dfrac{{\text{π}} }{3} $、$ -\dfrac{{\text{π}} }{6} $、$ 0 $、$ \dfrac{{\text{π}} }{6} $、$ \dfrac{{\text{π}} }{3} $和$ \dfrac{\text{π}}{2} $. 每个角度表示一个不同的方向,其中$ 0 $表示雷达设备直接面向参与者,$ -\dfrac{\text{π}}{2} $和$ \dfrac{\text{π}}{2} $分别表示参与者在雷达设备的左侧和右侧. 总共进行了280次测量,包括每个角度的20次跌倒和20次非跌倒行为. 图17显示了系统在这些实验中的准确率、精确率、召回率和F1-score方面的性能. 在水平维度的$ 0 $度方向上观察到最佳性能,实现了95%的准确率、90.5%的精确率、92.5%的召回率和92.7%的F1-score. 这种高性能归功于雷达设备的感知野,能够准确检测其覆盖范围内的跌倒引起的振动信号. 然而,当雷达设备与实验者跌倒位置之间的水平角为$ \pm \dfrac{\text{π}}{2} $时,跌倒产生的主要振动分量超出了感知野. 因此,在这些角度下,系统性能显著下降.
为了评估系统在不同俯仰角下的性能,将雷达设备的俯仰角更改为$ -\dfrac{\text{π}}{2} $、$ -\dfrac{\text{π}}{3} $、$ -\dfrac{\text{π}}{6} $、$ 0 $、$ \dfrac{\text{π}}{6} $、$ \dfrac{\text{π}}{3} $和$ \dfrac{\text{π}}{2} $. 每个角度代表一个不同的俯仰方向,其中0表示雷达设备正对参与者,$ -\dfrac{\text{π}}{2} $表示设备面向天花板,$ \dfrac{\text{π}}{2} $表示设备面向地面. 共进行了280次测量,包括每个角度的20次跌倒和20次非跌倒行为. 图18展示了系统在这些实验中的准确率、精确率、召回率和F1-score方面的性能. 在垂直维度的0度方向上观察到最佳性能,实现了95%的准确率、90.5%的精确率、92.5%的召回率和92.7%的F1-score. 值得注意的是,当雷达设备面向天花板时性能显著下降,而面向地面时性能保持在80%以上. 这一观察结果归因于跌倒引起的振动信号主要通过空间中的物理实体传播,如地面和家具. 当设备面向天花板时,雷达感应范围内包含振动信号的实体会减少,导致系统性能下降. 相反,当设备面向地面时,仍有足够多的实体具有雷达感应范围内的振动信号,不会导致系统性能显著下降.
为了评估系统在不同雷达高度下的性能,进行了检测参与者跌倒和非跌倒活动的实验. 在每个高度:40 cm、80 cm、120 cm、160 cm和200 cm,总共收集了200次跌倒和非跌倒行为的测量结果,对每个雷达高度的跌倒和非跌倒活动分别进行了20次测量. 图19显示了系统在不同雷达高度的性能指标,包括准确率、精确率、召回率和F1-score. 在120 cm的高度观察到最佳性能,其中该系统实现了90%的准确率、94.7%的精确率、92.5%的召回率和92.3%的F1-score. 这种在120 cm处的最佳性能是因为在该高度包含振动信号的实体数量最多. 在该高度以下,空间中物体引起的遮挡会导致感知范围内包含振动信号的实体被遮挡,从而导致系统性能降低. 考虑到IR-UWB雷达的放置位置将会直接影响其有效的感知区域,结合对于雷达放置位置的不同距离、角度和高度等实验分析,UWFall中雷达的最佳放置位置为房间边缘位置,且雷达中心正对房间中心,同时保持雷达高度为120 cm.
在实验中发现振动特征并不取决于跌倒物体反射的信号变化,这使得UWFall在非视距场景以及具有复杂多径的环境中优于传统方法. 为了全面评估该系统在这些场景中的性能,设计了一组不同环境的实验:
1)实验者在没有障碍物阻挡的人与雷达设备之间视距的情况下摔倒. 同时最大限度地减少了桌子和地面上的障碍,以保持简单的多径传播场景.
2)实验者在没有障碍物阻挡的人与雷达设备之间视距的情况下摔倒. 同时桌子和地面上有更多杂物,以模拟具有复杂多径传播的场景.
3)实验者在跌倒时与雷达设备之间存在障碍物,即非视距路径. 同时最大限度地减少了桌子和地面上的混乱,以维持简单的多径传播场景.
4) 非视距和复杂多径场景.
图20显示了这4个实验的对比结果,显示了在复杂多径传播的情况下,系统的性能得到了提升. 同时,非视距场景几乎不会对系统性能产生影响.
为了评估系统在环境和用户下的性能,实验设置2个不同环境的:书房(E1)和卧室(E2). 考虑到不同的实验环境、实验人员以及不同的跌倒姿势都会对跌倒检测产生影响,为了测试系统的鲁棒性,本文设置了多组对比试验,实验邀请了5名志愿者(3男2女)来采集跌倒信息,如表2所示.
UWFall在不同的场景中表现出了类似的性能,如图21所示. 在书房中准确率为93%,精确率为92%,召回率为93%,F1-score为93%. 在卧室中系统的准确率为94%,精确率为92%,召回率为93%,F1-score为93%. 这些结果表示了UWFall在不同环境中的鲁棒性. UWFall使用人员跌倒时与地面碰撞所产生的振动特征,使系统对人员跌倒时动作和姿态的差异性具有鲁棒性,所以在实验中我们对志愿者的跌倒行为不做任何限定,每名志愿者的每次跌倒都存在差异性. 此外,UWFall需要尽可能地模拟真实跌倒场景,志愿者在跌倒时仅采取了必要的保护措施,如配备防护垫. 同时由于振动特征与人员跌倒的姿态和动作无关,使得UWFall不受限于跌倒人员的类型,即使年轻用户和老年用户的跌倒动作存在较大的差异性,UWFall依旧可以有效识别老年人的跌倒行为. 为了避免可能的危险,实验中志愿者的年龄选择青年和中年2个不同的年龄段,如表2所示. 实验结果如图21所示,系统在不同用户之间保持准确性和鲁棒性.
本文通过实验检测不同类型的类跌倒活动对性能的影响. 对3种类型的活动进行实验:1)日常活动(即散步、空闲和阅读);2) 类似跌倒的活动(如坐下、躺下和深蹲);3)跳跃. 对于每种活动类型收集50个样本和50个跌倒活动. 对比结果如图22所示,UWFall可以有效区分日常活动和类跌倒活动,所有指标都大于$ 90\% $. 相比之下,跳跃活动会显著降低系统性能. 原因是UWFall利用人摔倒产生的振动来识别跌倒,而不是依赖于姿势信息. 这意味着传统的跌倒行为对系统性能的影响最小. 相反,跳跃等非跌倒行为会显著降低系统的性能,因为跳跃也会产生类似于跌倒的振动. 对于老年人住在家中进行康复和护理的场景而言,跳跃不是一种合理的日常行为. 因此,其负面影响可以忽略不计.
鉴于系统的实时跌倒检测的目标,通过实验量化了系统中每个主要算法的处理时间. 增加时间窗口长度会提高系统性能,同时也会增加计算负担. 为了保证系统的实时性需求,UWFall设置了固定时长为3 s的IR-UWB信号进行跌倒检测. 此时,主要的计算成本在于第一距离仓比值算法、掩码矩阵、熵、最远点距离算法和多径融合算法,其时间分别为0.8 ms、9.2 ms、9.4 ms、6.1 ms和1.1 ms. 其他组成部分产生的性能消耗可以忽略不计. 因此,每个时间窗口的信号处理时间总计仅为26.6 ms,远低于样本时间窗口的0.1 s移动步长. 该实验证明了系统在跌倒检测中的实时处理能力.
本文成功地设计并实现了基于IR-UWB的非接触式跌倒检测系统UWFall,该系统扩展了感知极限距离,利用单个IR-UWB雷达,捕捉跌倒引起的空间振动信号. 设计了包括信号建模和处理、分量分离、特征提取和跌倒识别在内的算法,系统能够鲁棒地识别跌倒事件模式,并准确地将其与其他正常活动区分开来. 通过大量实验表明,UWFall在跌倒事件中的准确率超过90%,在超出感知极限距离和非视距情况下的准确率均在80%以上.
作者贡献声明:王冬子负责实验设计,完成实验和论文攥写;郭政鑫对论文内容进行指导及修订,对实验提出了指导建议;桂林卿、盛碧云、蔡惠给予了基础理论支持和实验建议,并监督实验;肖甫确定论文思路.

参考文献 引证文献
排序方式:
1
Chen Zhe, Zheng Tianyue, Cai Chao, et al. Wider is better? contact-free vibration sensing via different COTS-RF technologies[C]//Proc of the IEEE Conf on Computer Communications. Piscataway, NJ: IEEE, 2023: 1−10
2
Siwadamrongpong W, Chinrungrueng J, Hasegawa S, et al. Fall detection and prediction based on IMU and EMG sensors for elders[C]//Proc of the 19th Int Joint Conf on Computer Science and Software Engineering. Piscataway, NJ: IEEE, 2022: 1−6
3
Mohamed H H, Siti H Y, Anis N I, et al. Wearable smart phone sensor fall detection system[J]. International Journal of Interactive Mobile Technologies, 2022, 16(12): 72−93
4
Chen Yi, Xiao Fu, Huan Haiping, et al. RF-IDH: An intelligent fall detection system for hemodialysis patients via COTS RFID[J]. Future Generation Computer Systems, 2020, 113: 13−24
5
Kottari K N, Delibasis K K, Maglogiannis I G. Real-time fall detection using uncalibrated Fisheye cameras[J]. IEEE Transactions on Cognitive and Developmental Systems, 2020, 12(3): 588−600
6
Lian Jie, Yuan Xu, Li Ming, et al. Fall detection via inaudible acoustic sensing[J]. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, 2021, 5(3): 1−21
7
Hu Yuqian, Zhang Feng, Wu Chenshu, et al. DeFall: Environment-independent passive fall detection using WiFi[J]. IEEE Internet of Things Journal, 2022, 9(11): 8515−8530
8
Jin Feng, Sengupta A, Cao Siyang. mmFall: Fall detection using 4-D mmWave radar and a hybrid variational RNN autoEncoder[J]. IEEE Transactions on Automation Science and Engineering, 2022, 19(23): 1245−1257
9
Sanaz K, Stefano S, Federico V, et al. Device-free RF human body fall detection and localization in industrial workplaces[J]. IEEE Internet of Things Journal, 2017, 4(2): 351−362
10
Takashi N, Mondher B, Kohei Y, et al. Wi-Fi-based fall detection using spectrogram image of channel state information[J]. IEEE Internet of Things Journal, 2022, 9(18): 17220−17234
11
Li Wenxuan, Zhang Dongheng, Li Yadong, et al. Real-time fall detection using mmwave radar[C]//Proc of the 2022 IEEE Int Conf on Acoustics, Speech and Signal Processing. Piscataway, NJ: IEEE, 2022: 16−20
12
Lin Guiping, Men Jing, Lin Enmin, et al. Peak amplitude curve based arm motion recognition using IR-UWB radar[C]//Proc of the 98th Vehicular Technology Conf. Piscataway, NJ: IEEE, 2023: 1−6
13
Taekjin H, Wonho K, Gyunghyun C. IR-UWB sensor based fall detection method using CNN algorithm[J]. Sensors, 2020, 20(20): 5948−5969
14
Ding Rong, Jin Haiming, Xiang Dong, et al. Soil moisture sensing with UAV-Mounted IR-UWB radar and deep learning[C]//Proc of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. New York: ACM, 2023, 7(1): 1−25
15
Jiang Xikang, Lin Zhang, Lei Li. Multi-task learning radar transformer (MLRT): A personal identification and fall detection network based on IR-UWB radar[J]. Sensors, 2023, 23(12): 5632−5643
16
Chen Di, Xiong Gang, Wang Lizhe, et al. Variable length sequential iterable convolutional recurrent network for UWB-IR vehicle target recognition[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1−11
17
Dang Xiaochao, Zhang Jinlong, Hao Zhanjun. A non-contact detection method for multi-person vital signs based on IR-UWB radar[J]. Sensors, 2022, 22(16): 6116−6136
18
Khan F, Azou S, Youssef R, et al. An IR-UWB multi-sensor approach for collision avoidance in indoor environments[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1−13
19
Kwon H B, Choi S H, Lee D, et al. Attention-based LSTM for non-contact sleep stage classification using IR-UWB radar[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(10): 3844−3853
20
Ali K, Liu A X. Fine-grained vibration based sensing using a smartphone[J]. IEEE Transactions on Mobile Computing, 2022, 21(11): 3971−3985
21
Fagert J, Bonde A, Srinidhi S, et al. Clean Vibes: Hand washing monitoring using structural vibration sensing[J]. ACM Transactions on Computing for Healthcare, 2022, 3(3): 1−25
22
Feng Yuanhao, Zhang Youwei, Yang Panlong. RF-Ear+: A mechanical identification and troubleshooting system based on contactless vibration sensing[J]. IEEE Transactions on Mobile Computing, 2023, 22(12): 7310−7326
23
Yang Xin, Yang Song, Liu Jian. Enabling finger-touch-based mobile user authentication via physical vibrations on IoT devices[J]. IEEE Transactions on Mobile Computing, 2022, 21(10): 3565−3580
24
Maria V, Li Fangyu, Zhao Liang, et al. Vibration sensing-based human and infrastructure safety/health monitoring: A survey[J]. Digital Signal Processing, 2022, 125: 103572−103585
25
Wang Ziqi, Chen Zhe, Singh A D. UWHear: Through-wall extraction and separation of audio vibrations using wireless signals[C]//Proc of the 18th Conf on Embedded Networked Sensor Systems. New York: ACM, 2020: 1−14
26
Maître J, Bouchard K, Gaboury S. et al. Fall detection with UWB radars and CNN-LSTM architecture[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(4): 1273−1283
27
Wu Kaishun, Huang Yandao, Qiu Minghui, et al. Toward device-free and user-independent fall detection using floor vibration[J]. ACM Transactions on Sensor Networks, 2023, 19(1): 1550−1859
28
Guo Zhengxin, Wang Dongzi, Gui Linqing, et al. UWTracking: Passive human tracking under LOS/NLOS scenarios using IR-UWB radar[J]. IEEE Transactions on Mobile Computing, 2024, 5(1): 1−17
29
Zhang Fusang, Xiong Jie, Chang Zhaoxin, et al. Mobi2Sense: Empowering wireless sensing with mobility[C]//Proc of the 28th Annual Int Conf on Mobile Computing and Networking. New York: ACM, 2022: 268−281
30
Sadreazami H, Bolic M, Rajan S. et al. Fall detection using Standoff radar-based sensing and deep convolutional neural network[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2020, 67(1): 197−201
31
Jiang Xikang, Zhang Jinhui, Zhang Lin. FedRadar: Federated multi-task transfer learning for radar-based Internet of medical things[J]. IEEE Transactions on Network and Service Management, 2023, 20(2): 1459−1469
2024年第61卷第11期
93
45
0
引用本文
BibTeX
文章信息
doi: 10.7544/issn1000-1239.202440386
  • 接收时间:2024-05-31
  • 首发时间:2026-11-17
  • 出版时间:2024-11-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-05-31
  • 修回日期:2024-07-30
基金
作者信息
    1南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
    2江苏省无线传感网高技术研究重点实验室(南京邮电大学) 南京 210023

通讯作者:

肖甫()
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202440386
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏