Article(id=1327012568088031305, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327012311115608215, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202330882, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1698681600000, receivedDateStr=2023-10-31, revisedDate=1714060800000, revisedDateStr=2024-04-26, acceptedDate=1716480000000, acceptedDateStr=2024-05-24, onlineDate=1794314050932, onlineDateStr=2026-11-10, pubDate=1738339200000, pubDateStr=2025-02-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794314050932, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794314050932, creator=13701087609, updateTime=1794314050932, updator=13701087609, issue=Issue{id=1327012311115608215, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='2', pageStart='285', pageEnd='541', issueExtLink='null', onlineDate='null', pubDate='1738339200000', pubDateStr='2025-02-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794313989665, creator='13701087609', updateTime=1794376696965, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327275325060395748, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327012311115608215, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327275325060395749, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327012311115608215, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=488, endPage=502, ext={EN=ArticleExt(id=1327012568322912330, articleId=1327012568088031305, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=A Near-Ultrasonic Robust Indoor Localization Method Based on Stacking Ensemble Learning, columnId=1325493671541474142, journalTitle=Journal of Computer Research and Development, columnName=Network and Information Security, runingTitle=null, highlight=null, articleAbstract=

Recent economic advancements have significantly supported the popularity of indoor positioning systems (IPS) and indoor localization-based services (ILBS). This trend is particularly obvious as global navigation satellite systems (GNSS) are ineffective in indoor environments. Traditional IPS, such as WIFI and Bluetooth positioning, face challenges like low accuracy and are prone to non-line-of-sight (NLOS) and noise interference. In response to this issue, we propose a novel near-ultrasonic robust indoor localization method based on the stacking ensemble model. Initially, the method employs an optimized enhanced cross-correlation technique to effectively mitigate multipath interference in acoustic ranging. Compared with the conventional methods based on peak extraction or fixed thresholding, this approach significantly improves ranging accuracy in reverberant environments. Subsequently, time difference of arrival (TDOA) is extracted as a feature. Finally, we utilize a stacking ensemble learning model, incorporating optimized machine learning models, to train a pre-set dataset. This method, integrating the extracted feature, enables to achieve correct localization results in NLOS and large ranging error. Numerical simulations, ray-tracing acoustic analyses, and empirical validations suggest that our approach notably mitigates errors prevalent in NLOS and acoustically noisy indoor environments and yielding localization accuracy significantly exceeds current methods by 50%−90%. The core dataset available at https://github.com/ChirsJia/JSJYF.

, authors=Naizheng Jia, Can Xue, Liu Yang, Zhi Wang*, authorsList=Naizheng Jia, Can Xue, Liu Yang, Zhi Wang, authorCompany=null, correspAuthors=Zhi Wang, authorNote=

born in 1998. PhD candidate. His main research interests include signal processing and acoustic signal localization

born in 1997. PhD candidate. His main research interests include embedded system and acoustic signal localization

born in 2000. PhD candidate. His main research interests include acoustic signal processing and robot localization

born in 1967. PhD, associate professor. Member of CCF. His main research interests include signal processing and acoustic signal sensing, and robot navigation

, correspAuthorsNote=null, copyrightStatement=Copyright © 2025 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=1327012573871976569, articleId=1327012568088031305, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=基于融合集成学习的鲁棒近超声室内定位方法, columnId=1325493672690713440, journalTitle=计算机研究与发展, columnName=网络与信息安全, runingTitle=null, highlight=null, articleAbstract=

近年来随着经济的发展,室内定位系统的需求越来越迫切. 传统的室内定位系统如WIFI定位和蓝牙定位面临着定位精度低、易受非视距(non-line-of-sight,NLOS)和噪声干扰等挑战. 针对这些问题,提出了一种基于融合集成学习的近超声室内定位方法. 首先,使用优化的增强互相关方法有效地抵消多径干扰. 与传统基于峰值提取或固定阈值的方法相比,此法在混响环境中明显提升了测距的精度. 然后,利用到达时间差(time difference of arrival,TDOA)作为特征进行提取. 最终,采用了融合集成学习模型,对设定好的训练集进行交叉融合训练,并输入特征,从而得到修正的定位结果. 仿真和实验测试结果表明,所提出的方法可以在室内NLOS和噪声干扰的情况下克服较大误差实现精确定位,并且精度优于对比方法50%~90%. 本文核心数据公布在https://github.com/ChirsJia/JSJYF上.

, authors=贾乃征, 薛灿, 杨骝, 王智*, authorsList=贾乃征, 薛灿, 杨骝, 王智, authorCompany=null, correspAuthors=王智, authorNote=

1998年生. 博士研究生. 主要研究方向为信号处理、声信号定位

1997年生. 博士研究生. 主要研究方向为嵌入式系统开发、声信号定位

2000年生. 博士研究生. 主要研究方向为声信号处理、机器人定位

1967年生. 博士,副教授. CCF会员. 主要研究方向为信号处理、声波感知、机器人导航

, correspAuthorsNote=
王智()
, copyrightStatement=版权所有 © 2025 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=BdG17Hx8L7KBIFYHeIUeyw==, magXml=yID44Zih2gv7lMP5QktHyA==, pdfUrl=null, pdf=cl3YqBlUnYe6LLJh7bO2Dw==, pdfFileSize=2524707, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=ecpVQ02OSSACQIdVKhPDPA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=8eXSrWTGVdaIzYbAG0Uz0g==, mapNumber=null, fund=null)}, authors=[Author(id=1327012574266241151, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=naizheng.jia@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327012574350127233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574266241151, language=EN, stringName=Naizheng Jia, firstName=Naizheng, middleName=null, lastName=Jia, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 1998. PhD candidate. His main research interests include signal processing and acoustic signal localization

"}, bioImg=null, bioContent=

born in 1998. PhD candidate. His main research interests include signal processing and acoustic signal localization

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012574425624707, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574266241151, language=CN, stringName=贾乃征, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学控制科学与工程学院 杭州 310013, bio={"img":"4HvXn0p0W60BjfkoKJo1Qg==","content":"

1998年生. 博士研究生. 主要研究方向为信号处理、声信号定位

"}, bioImg=4HvXn0p0W60BjfkoKJo1Qg==, bioContent=

1998年生. 博士研究生. 主要研究方向为信号处理、声信号定位

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012574169772155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, xref=null, ext=[AuthorCompanyExt(id=1327012574178160764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1327012574186549373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学控制科学与工程学院 杭州 310013)])]), Author(id=1327012574496927877, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, 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=1327012574656311431, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574496927877, language=EN, stringName=Can Xue, firstName=Can, middleName=null, lastName=Xue, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 1997. PhD candidate. His main research interests include embedded system and acoustic signal localization

"}, bioImg=null, bioContent=

born in 1997. PhD candidate. His main research interests include embedded system and acoustic signal localization

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012574719225992, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574496927877, language=CN, stringName=薛灿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学控制科学与工程学院 杭州 310013, bio={"img":"KKwwNArx8EPg9LGzeVxl5A==","content":"

1997年生. 博士研究生. 主要研究方向为嵌入式系统开发、声信号定位

"}, bioImg=KKwwNArx8EPg9LGzeVxl5A==, bioContent=

1997年生. 博士研究生. 主要研究方向为嵌入式系统开发、声信号定位

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012574169772155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, xref=null, ext=[AuthorCompanyExt(id=1327012574178160764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1327012574186549373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学控制科学与工程学院 杭州 310013)])]), Author(id=1327012574819889290, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, 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=1327012574945718412, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574819889290, language=EN, stringName=Liu Yang, firstName=Liu, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 2000. PhD candidate. His main research interests include acoustic signal processing and robot localization

"}, bioImg=null, bioContent=

born in 2000. PhD candidate. His main research interests include acoustic signal processing and robot localization

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012575029604493, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574819889290, language=CN, stringName=杨骝, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学控制科学与工程学院 杭州 310013, bio={"img":"q5RNDj/GvJUK4Q5LfDYxGA==","content":"

2000年生. 博士研究生. 主要研究方向为声信号处理、机器人定位

"}, bioImg=q5RNDj/GvJUK4Q5LfDYxGA==, bioContent=

2000年生. 博士研究生. 主要研究方向为声信号处理、机器人定位

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012574169772155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, xref=null, ext=[AuthorCompanyExt(id=1327012574178160764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1327012574186549373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学控制科学与工程学院 杭州 310013)])]), Author(id=1327012576703131791, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zjuwangzhi@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327012576791212178, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012576703131791, language=EN, stringName=Zhi Wang, firstName=Zhi, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 1967. PhD, associate professor. Member of CCF. His main research interests include signal processing and acoustic signal sensing, and robot navigation

"}, bioImg=null, bioContent=

born in 1967. PhD, associate professor. Member of CCF. His main research interests include signal processing and acoustic signal sensing, and robot navigation

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012576858321043, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012576703131791, language=CN, stringName=王智, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=浙江大学控制科学与工程学院 杭州 310013, bio={"img":"+jn5V0dEhW0qnO8862+Ryw==","content":"

1967年生. 博士,副教授. CCF会员. 主要研究方向为信号处理、声波感知、机器人导航

"}, bioImg=+jn5V0dEhW0qnO8862+Ryw==, bioContent=

1967年生. 博士,副教授. CCF会员. 主要研究方向为信号处理、声波感知、机器人导航

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012574169772155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, xref=null, ext=[AuthorCompanyExt(id=1327012574178160764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1327012574186549373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学控制科学与工程学院 杭州 310013)])])], keywords=[Keyword(id=1327012576963178644, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, orderNo=1, keyword=indoor positioning), Keyword(id=1327012577139339413, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, orderNo=2, keyword=near-ultrasonic localization), Keyword(id=1327012577206448278, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, orderNo=3, keyword=signal processing), Keyword(id=1327012577269362839, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, orderNo=4, keyword=machine learning), Keyword(id=1327012577336471704, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, orderNo=5, keyword=TDOA), Keyword(id=1327012577403580569, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, orderNo=1, keyword=室内定位), Keyword(id=1327012577470689434, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, orderNo=2, keyword=近超声定位), Keyword(id=1327012577554575515, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, orderNo=3, keyword=信号处理), Keyword(id=1327012577638461596, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, orderNo=4, keyword=机器学习), Keyword(id=1327012577747513501, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, orderNo=5, keyword=到达时间差)], refs=[Reference(id=1327012583795699917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, 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=Obeidat H, Shuaieb W, Obeidat O, et al. A review of indoor localization techniques and wireless technologies[J]. Wireless Personal Communications, 2021, 119: 289−327, articleTitle=null, refAbstract=null), Reference(id=1327012583867003086, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, 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=Zhang Lan, Liu Kebin, Jiang Yonghang, et al. Montage: Combine frames with movement continuity for realtime multi-user tracking[J]. IEEE Transactions on Mobile Computing, 2017, 16(4): 1019−1031, articleTitle=null, refAbstract=null), Reference(id=1327012583959277775, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, 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=薛灿,韩强,王智. 基于信号统计模型的变电站半遮挡融合定位方法[J]. 电力工程技术,2023,42(1):185−192, articleTitle=null, refAbstract=null), Reference(id=1327012584034775248, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Xue Can, Han Qiang, Wang Zhi. Semi-occlusion substation fusion positioning method based on multi-sensor signal statistical model[J]. Electric Power Engineering Technology, 2023, 42(1): 185−192 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012585716691154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng Sisi, Wang Feng, Li Guangcai, et al. Single-frequency multi-GNSS PPP-RTK for smartphone rapid centimeter-level positioning[J]. IEEE Sensors Journal, 2023, 23(18): 21553−21561, articleTitle=null, refAbstract=null), Reference(id=1327012585787994323, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Jia Naizheng, Shu Haoran, Wang Xinheng, et al. Smartphone-based social distance detection technology with near-ultrasonic signal[J]. Sensors, 2022, 22(19): 7345−7375, articleTitle=null, refAbstract=null), Reference(id=1327012585863491796, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Zou Han, Zhou Yuxun, Yang Jianfei, et al. Unsupervised WIFI-enabled IOT device-user association for personalized location-based service[J]. IEEE Internet of Things Journal, 2019, 6(1): 1238−1245, articleTitle=null, refAbstract=null), Reference(id=1327012585951572181, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Lina, Shi Dayu, Zhang Xun, et al. 5G Internet of radio light positioning system for indoor broadcasting service[J]. IEEE Transactions on Broadcasting, 2020, 66(2): 534−544, articleTitle=null, refAbstract=null), Reference(id=1327012586069012694, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=AlHory O, Shoushara O, Al Suri H, et al. 5G mmwave indoor location identification using beamforming and RSSI[C]//Proc of the 11th Int Conf on Information and Communication Systems (ICICS). Piscataway, NJ: IEEE, 2020: 91−95, articleTitle=null, refAbstract=null), Reference(id=1327012586157093079, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Deng Zhongliang, Zheng Xinyu, Zhang Chongyu, et al. A TDOA and PDR fusion method for 5G indoor localization based on virtual base stations in unknown areas[J]. IEEE Access, 2020, 8: 225123−225133, articleTitle=null, refAbstract=null), Reference(id=1327012586232590552, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Yue, Chen Ruizhi, Chen Liang, et al. A novel 3-D indoor localization algorithm based on BLE and multiple sensors[J]. IEEE Internet of Things Journal, 2021, 8(11): 9359−9372, articleTitle=null, refAbstract=null), Reference(id=1327012586320670937, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=You Yuan, Wu Chang. Hybrid indoor positioning system for pedestrians with swinging arms based on smartphone IMU and RSSI of BLE[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1−15, articleTitle=null, refAbstract=null), Reference(id=1327012586446500058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Rahman M, Haider A, Naghshvarianjahromi M. A systematic methodology for the time-domain ringing reduction in UWB band-notched antennas[J]. IEEE Antennas and Wireless Propagation Letters, 2020, 19(3): 482−486, articleTitle=null, refAbstract=null), Reference(id=1327012586551357659, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Bao Dongxuan, Zou Zhuo, Nejad M, et al. A wirelessly powered UWB RFID sensor tag with time-domain analog-to-information interface[J]. IEEE Journal of Solid-State Circuits, 2018, 53(8): 2227−2239, articleTitle=null, refAbstract=null), Reference(id=1327012586618466524, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Sharma S, Deka K, Mandloi M. Deep learning noncoherent UWB receiver design[J]. IEEE Sensors Letters, 2021, 5(6): 1−4, articleTitle=null, refAbstract=null), Reference(id=1327012586769461469, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Manni, Cheng Linsong, Qian Kun, et al. Indoor acoustic localization: A survey[J]. Human-centric Computing and Information Sciences, 2020, 10(1): 1−24, articleTitle=null, refAbstract=null), Reference(id=1327012586849153246, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Albuquerque D, Vieira J, Lopes S, et al. Indoor acoustic simulator for ultrasonic broadband signals with doppler effect[J]. Applied Acoustics, 2015, 97: 140−151, articleTitle=null, refAbstract=null), Reference(id=1327012586933039327, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Gualda D, Perez-Rubio M, Urena J, et al. Locate-us: Indoor positioning for mobile devices using encoded ultrasonic signals, inertial sensors and graph-matching[J]. Sensors, 2021, 21(6): 1950−1973, articleTitle=null, refAbstract=null), Reference(id=1327012587008536800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Dubey A, Sood P, Santos J, et al. An enhanced approach to imaging the indoor environment using WIFI RSSI measurements[J]. IEEE Transactions on Vehicular Technology, 2021, 70(9): 8415−8430, articleTitle=null, refAbstract=null), Reference(id=1327012587084034273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Zafari F, Gkelias A, Leung K. A survey of indoor localization systems and technologies[J]. IEEE Communications Surveys & Tutorials, 2019, 21(3): 2568−2599, articleTitle=null, refAbstract=null), Reference(id=1327012587163726050, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Ji, Singh S. Loam: Lidar odometry and mapping in real-time[J]. Robotics: Science and Systems, 2014, 2(9): 1−9, articleTitle=null, refAbstract=null), Reference(id=1327012587247612131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Chao, Hu Menglan, Cao Doudou, et al. Self-deployable indoor localization with acoustic-enabled IoT devices exploiting participatory sensing[J]. IEEE Internet of Things Journal, 2019, 6(3): 5297−5311, articleTitle=null, refAbstract=null), Reference(id=1327012587344081124, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Wenchao, Xiong Yan, Li Xiangyang, et al. Swadloon: Direction finding and indoor localization using acoustic signal by shaking smartphones[J]. IEEE Transactions on Mobile Computing, 2014, 14(10): 2145−2157, articleTitle=null, refAbstract=null), Reference(id=1327012587419578597, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Lingyu, Feng Xiaoke, Zhang Jing, et al. Multi-ray modeling of ultrasonic sensors and application for micro-UAV localization in indoor environments[J]. Sensors, 2019, 19(8): 1770−1787, articleTitle=null, refAbstract=null), Reference(id=1327012587553796326, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Höflinger F, Zhang Rui, Hoppe J, et al. Acoustic self-calibrating system for indoor smartphone tracking (ASSIST)[C/OL]//Proc of the 1st Int Conf on Indoor Positioning and Indoor Navigation (IPIN). Piscataway, NJ: IEEE, 2012 [2024-04-22]. https://ieeexplore.ieee.org/document/6418877, articleTitle=null, refAbstract=null), Reference(id=1327012587633488103, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Höflinger F, Bordoy J, Simon N, et al. Indoor-localization system for smart phones[C/OL]//Proc of the 3rd IEEE Int Workshop on Measurements & Networking (M&N). Piscataway, NJ: IEEE, 2015 [2024-04-22]. https://ieeexplore.ieee.org/document/7322974/, articleTitle=null, refAbstract=null), Reference(id=1327012587729957096, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Prieto J, Jiménez A, Guevara J, et al. Performance evaluation of 3D-locus advanced acoustic LPS[J]. IEEE Transactions on Instrumentation and Measurement, 2009, 58(8): 2385−2395, articleTitle=null, refAbstract=null), Reference(id=1327012587801260265, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Sertatıl C, Altınkaya M, Raoof K. A novel acoustic indoor localization system employing CDMA[J]. Digital Signal Processing, 2012, 22(3): 506−517, articleTitle=null, refAbstract=null), Reference(id=1327012587897729258, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Kaikai, Liu Xinxin, Li Xiaolin. Guoguo: Enabling fine-grained smartphone localization via acoustic anchors[J]. IEEE Transactions on Mobile Computing, 2016, 15(5): 1144−1156, articleTitle=null, refAbstract=null), Reference(id=1327012588019364075, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zuoya, Chen Ruizhi, Ye Feng, et al. Improved TOA estimation method for acoustic ranging in a reverberant environment[J]. IEEE Sensors Journal, 2020, 22(6): 4844−4852, articleTitle=null, refAbstract=null), Reference(id=1327012588111638764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Shuai, Chen Xiang, Zhang Xu, et al. Effective audio signal arrival time detection algorithm for realization of robust acoustic indoor positioning[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(10): 7341−7352, articleTitle=null, refAbstract=null), Reference(id=1327012588195524845, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Chunyi, Shen Guobin, Zhang Yongguang. Beepbeep: A high-accuracy acoustic-based system for ranging and localization using cots devices[J]. ACM Transactions on Embedded Computing Systems, 2012, 11(1): 1−29, articleTitle=null, refAbstract=null), Reference(id=1327012588338131182, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Lei, Chen Minlin, Wang Xinheng, et al. TOA estimation of chirp signal in dense multipath environment for low-cost acoustic ranging[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 68(2): 355−367, articleTitle=null, refAbstract=null), Reference(id=1327012588447183087, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Mao Wenguang, He Jian, Qiu Lili. Cat: High-precision acoustic motion tracking[C]//Proc of the 22nd Annual Int Conf on Mobile Computing and Networking. New York: ACM, 2016: 69−81, articleTitle=null, refAbstract=null), Reference(id=1327012590150070512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yunhao, Wang Jiliang, Zhang Yunting, et al. Vernier: Accurate and fast acoustic motion tracking using mobile devices[J]. IEEE Transactions on Mobile Computing, 2019, 20(2): 754−764, articleTitle=null, refAbstract=null), Reference(id=1327012590246539505, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Wei, Liu A, Sun Ke. Device-free gesture tracking using acoustic signals[C]//Proc of the 22nd Annual Int Conf on Mobile Computing and Networking. New York: ACM, 2016: 82−94, articleTitle=null, refAbstract=null), Reference(id=1327012590317842674, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Xinchuang, Chen Ruizhi, Huang Lixiong, et al. Chirptracker: A precise-location-aware system for acoustic tag using single smartphone[J]. IEEE Internet of Things Journal, 2023, 11(1): 848−862, articleTitle=null, refAbstract=null), Reference(id=1327012590519169267, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Hucheng, Xue Can, Wang Zhi, et al. Smartphone-based pedestrian NLOS positioning based on acoustics and IMU parameter estimation[J]. IEEE Sensors Journal, 2022, 22(23): 23095−23108, articleTitle=null, refAbstract=null), Reference(id=1327012590607249652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Hucheng, Wang Zhi, Zhang Lei, et al. A highly stable fusion positioning system of smartphone under NLOS acoustic indoor environment[J]. ACM Transactions on Internet Technology, 2023, 23(2): 1−19, articleTitle=null, refAbstract=null), Reference(id=1327012590691135733, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Chao, Zheng Rong, Li Jun, et al. Asynchronous acoustic localization and tracking for mobile targets[J]. IEEE Internet of Things Journal, 2020, 7(2): 830−845, articleTitle=null, refAbstract=null), Reference(id=1327012590762438902, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Cheng, Chen Minlin, Sun Peng, et al. An encoding and decoding scheme for long-distance ultrasonic localization[C]//Proc of the 39th Chinese Control Conf (CCC). Piscataway, NJ: IEEE, 2020: 5247−5252, articleTitle=null, refAbstract=null), Reference(id=1327012590863102199, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zheng, Chen Ruizhi, Guo Guangyi, et al. Dual-step acoustic chirp signals detection using pervasive smartphones in multipath and NLOS indoor environments[J]. IEEE Internet of Things Journal, 2023, 11(4): 6494−6507, articleTitle=null, refAbstract=null), Reference(id=1327012590930211064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Jia Naizheng, Cui Weimeng, Wang Yuwei, et al. Robust acoustic TOA estimation based on multipath extraction in frequency domain[C/OL]//Proc of the 13th Int Conf on Indoor Positioning and Indoor Navigation (IPIN). Piscataway, NJ: IEEE, 2023 [2024-04-22]. https://ieeexplore.ieee.org/document/10332467/, articleTitle=null, refAbstract=null), Reference(id=1327012591005708537, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Chan Y, Ho K. A simple and efficient estimator for hyperbolic location[J]. IEEE Transactions on Signal Processing, 1994, 42(8): 1905−1915, articleTitle=null, refAbstract=null), Reference(id=1327012591064428794, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiong Jinyu, Wang Wei, Zhu Zhongliang. A new TDOA algorithm based on Taylor series expansion in cellular networks[J]. Journal of China Institute of Communications, 2004, 25(4): 144−150, articleTitle=null, refAbstract=null), Reference(id=1327012591144120571, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Hua Cheng, Zhao Kun, Dong Danan, et al. Multipath map method for tdoa based indoor reverse positioning system with improved Chan-Taylor algorithm[J]. Sensors, 2020, 20(11): 3223−3238, articleTitle=null, refAbstract=null), Reference(id=1327012591198646524, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Zang Lan, Shen Chong, Zhang Kun, et al. Research on hybrid algorithm based on TDOA[C]//Proc of the 20th IEEE Int Conf on Communication Technology (ICCT). Piscataway, NJ: IEEE, 2020: 539−542, articleTitle=null, refAbstract=null), Reference(id=1327012591265755389, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=黄冬梅,张宁宁,胡安铎,等. 基于双层Xgboost和数据增强的空间负荷预测方法[J]. 电力工程技术,2023,42(1):201−208, articleTitle=null, refAbstract=null), Reference(id=1327012591358030078, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Dongmei, Zhang Ningning, Hu Anduo. Spatial load forecasting method based on double-layer Xgboost and data enhancement[J]. Electric Power Engineering Technology, 2023, 42(1): 201−208 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012591433527551, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Tianqi, Guestrin C. Xgboost: A scalable tree boosting system[C]//Proc of the 22nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2016: 785–794, articleTitle=null, refAbstract=null), Reference(id=1327012591504830720, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Jinshan, Zhao Chenyue, Yu Haotong, et al. Use GBDT to predict the stock market[J]. Procedia Computer Science, 2020, 174: 161−171, articleTitle=null, refAbstract=null), Reference(id=1327012591592911106, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Ke Guolin, Meng Qi, Finley T, et al. LightGBM: A highly efficient gradient boosting decision tree[C]//Proc of the 31st Int Conf on Neural Information Processing Systems. New York: ACM, 2017: 3149−3157, articleTitle=null, refAbstract=null), Reference(id=1327012591664214275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=李丽颖,张润泽,魏同权. 面向边缘计算的服务解耦与部署策略[J]. 计算机研究与发展,2023,60(5):1073−1085, articleTitle=null, refAbstract=null), Reference(id=1327012591752294660, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Liying, Zhang Runze, Wei Tongquan. Service decoupling and deployment strategies for edge computing[J]. Journal of Computer Research and Development, 2023, 60(5): 1073−1085 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012591819403525, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Qu Yi, Lin Zhengkui, Li Honglei, et al. Feature recognition of urban road traffic accidents based on GA-Xgboost in the context of big data[J]. IEEE Access, 2019, 7: 170106−170115, articleTitle=null, refAbstract=null), Reference(id=1327012591882318086, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=严忻恺,霍宇驰,鲍虎军. 神经渲染及其硬件加速综述[J]. 计算机研究与发展,2024,61(11):2846−2869, articleTitle=null, refAbstract=null), Reference(id=1327012591945232647, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Xinkai, Huo Yuchi, Bao Hujun. Survey on neural rendering and its hardware acceleration[J]. Journal of Computer Research and Development, 2024,61(11):2846−2869 (in Chinese), articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327012574169772155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, xref=null, ext=[AuthorCompanyExt(id=1327012574178160764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1327012574186549373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学控制科学与工程学院 杭州 310013)])], figs=[ArticleFig(id=1327012577860759710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 1, caption=Structure diagram of a near-ultrasonic indoor localization system, figureFileSmall=Q9RmHPNNJeyJ/xRTtsWGFw==, figureFileBig=ecpVQ02OSSACQIdVKhPDPA==, tableContent=null), ArticleFig(id=1327012577944645791, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图1, caption=近超声室内定位系统结构图, figureFileSmall=Q9RmHPNNJeyJ/xRTtsWGFw==, figureFileBig=ecpVQ02OSSACQIdVKhPDPA==, tableContent=null), ArticleFig(id=1327012578129195168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 2, caption=Illustration of Chirp signal, figureFileSmall=splyyk1N4stQtl449ejSLw==, figureFileBig=hvIFbAuOsbqy9QpHImrnSw==, tableContent=null), ArticleFig(id=1327012578213081249, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图2, caption=Chirp信号示意图, figureFileSmall=splyyk1N4stQtl449ejSLw==, figureFileBig=hvIFbAuOsbqy9QpHImrnSw==, tableContent=null), ArticleFig(id=1327012578288578722, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 3, caption=Illustration of the received signal with reverberation, figureFileSmall=gJN4ISbXUgJjH6pi2HOxCg==, figureFileBig=vAE4X1R14y+R1YJkr/z7yw==, tableContent=null), ArticleFig(id=1327012578355687587, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图3, caption=带有混响的接收信号示意图, figureFileSmall=gJN4ISbXUgJjH6pi2HOxCg==, figureFileBig=vAE4X1R14y+R1YJkr/z7yw==, tableContent=null), ArticleFig(id=1327012578557014180, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 4, caption=Frequency-domain range profile obtained using FMCW method, figureFileSmall=s8cugVfr3yG4r960nIPUZA==, figureFileBig=0m+eOmg35sWMXT9v6NJCOQ==, tableContent=null), ArticleFig(id=1327012578628317349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图4, caption=FMCW方法求解所得的到达径频率图, figureFileSmall=s8cugVfr3yG4r960nIPUZA==, figureFileBig=0m+eOmg35sWMXT9v6NJCOQ==, tableContent=null), ArticleFig(id=1327012578712203430, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 5, caption=The plot for enhanced cross-correlation compared with the original cross-correlation, figureFileSmall=SMZM6cKi6jm7eMbvPHqRNg==, figureFileBig=ywfZjkYkLEcVufTe7ThLEQ==, tableContent=null), ArticleFig(id=1327012578800283815, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图5, caption=增强互相关与原始互相关对比图, figureFileSmall=SMZM6cKi6jm7eMbvPHqRNg==, figureFileBig=ywfZjkYkLEcVufTe7ThLEQ==, tableContent=null), ArticleFig(id=1327012578867392680, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 6, caption=Illustration of TDOA solution, figureFileSmall=mo+WtMGSrVb2JeHXcVD6bg==, figureFileBig=wlHFT8E3SiJY4TLsAxpQEw==, tableContent=null), ArticleFig(id=1327012578942890153, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图6, caption=TDOA求解示意图, figureFileSmall=mo+WtMGSrVb2JeHXcVD6bg==, figureFileBig=wlHFT8E3SiJY4TLsAxpQEw==, tableContent=null), ArticleFig(id=1327012579018387626, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 7, caption=Method of near-ultrasonic localization based on stacking ensemble learning, figureFileSmall=XPrmzPfBLPPbFkQehfsnyA==, figureFileBig=qBKJEhsTBmz9KgcaEo3N3w==, tableContent=null), ArticleFig(id=1327012579089690795, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图7, caption=基于融合集成学习的近超声定位方法, figureFileSmall=XPrmzPfBLPPbFkQehfsnyA==, figureFileBig=qBKJEhsTBmz9KgcaEo3N3w==, tableContent=null), ArticleFig(id=1327012579160993964, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 8, caption=Structure diagram of stacking ensemble model, figureFileSmall=ISYwEAw5DM53ehFdAJTJNQ==, figureFileBig=IfX4gzRA7F9T8a4wBwZPIQ==, tableContent=null), ArticleFig(id=1327012579257462957, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图8, caption=融合集成模型结构图, figureFileSmall=ISYwEAw5DM53ehFdAJTJNQ==, figureFileBig=IfX4gzRA7F9T8a4wBwZPIQ==, tableContent=null), ArticleFig(id=1327012579337154734, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 9, caption=Simulation analysis of ranging algorithm, figureFileSmall=SfBGlmpfqdMIRK4fZjDixA==, figureFileBig=N9QPo8udn+U/TxFRWTUSTw==, tableContent=null), ArticleFig(id=1327012579525898415, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图9, caption=测距算法仿真分析, figureFileSmall=SfBGlmpfqdMIRK4fZjDixA==, figureFileBig=N9QPo8udn+U/TxFRWTUSTw==, tableContent=null), ArticleFig(id=1327012581241368753, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 10, caption=Histogram of residual distribution for coordinate value fitting using stacking ensemble model, figureFileSmall=YsuR4gpOQ/w8YuI4QM0vGw==, figureFileBig=lI2Pz1taZEC42hFCV4PxRg==, tableContent=null), ArticleFig(id=1327012581312671922, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图10, caption=融合集成模型坐标值拟合残差分布直方图, figureFileSmall=YsuR4gpOQ/w8YuI4QM0vGw==, figureFileBig=lI2Pz1taZEC42hFCV4PxRg==, tableContent=null), ArticleFig(id=1327012581392363699, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 11, caption=Range RMSE errors of different TDOA solving methods under measurement noise errors, figureFileSmall=+ZWTaIVLQ+0b9VV44r5BvA==, figureFileBig=+b/0l/L97xrolGWCzBlm7Q==, tableContent=null), ArticleFig(id=1327012581476249780, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图11, caption=不同TDOA求解方法在测量噪声误差下的测距RMSE误差, figureFileSmall=+ZWTaIVLQ+0b9VV44r5BvA==, figureFileBig=+b/0l/L97xrolGWCzBlm7Q==, tableContent=null), ArticleFig(id=1327012581564330165, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 12, caption=Indoor positioning simulation model diagram, figureFileSmall=pPiwWBLZd2sd7nViHDgLfA==, figureFileBig=B1U0W/NVKUQSXRZLtNK9BA==, tableContent=null), ArticleFig(id=1327012581656604854, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图12, caption=室内定位仿真模型图, figureFileSmall=pPiwWBLZd2sd7nViHDgLfA==, figureFileBig=B1U0W/NVKUQSXRZLtNK9BA==, tableContent=null), ArticleFig(id=1327012581736296631, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 13, caption=Experimental equipment, figureFileSmall=aeCKZdhId5xYTfSnaG15sA==, figureFileBig=V6GDmNNPtxSevpiHGLU+1Q==, tableContent=null), ArticleFig(id=1327012581866320056, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图13, caption=实验设备, figureFileSmall=aeCKZdhId5xYTfSnaG15sA==, figureFileBig=V6GDmNNPtxSevpiHGLU+1Q==, tableContent=null), ArticleFig(id=1327012582008926393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 14, caption=Localization errors of three comparative methods in scenario 1, 2, figureFileSmall=2JOEgLg/RMMyzqMplVtXUA==, figureFileBig=lr8qshGLQAcIRgHDbVaWWQ==, tableContent=null), ArticleFig(id=1327012582122172602, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图14, caption=在场景1,2中3种对比方法的定位误差, figureFileSmall=2JOEgLg/RMMyzqMplVtXUA==, figureFileBig=lr8qshGLQAcIRgHDbVaWWQ==, tableContent=null), ArticleFig(id=1327012582256390331, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 15, caption=Cumulative error distribution for three comparative methods in scenario 1, 2, figureFileSmall=Ku1EQKVGHR1O55Jhj3GgFA==, figureFileBig=5xBWtnDIsp5Vf+WNFkRrgQ==, tableContent=null), ArticleFig(id=1327012582348665020, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图15, caption=在场景1,2中3种对比方法的累积误差分布, figureFileSmall=Ku1EQKVGHR1O55Jhj3GgFA==, figureFileBig=5xBWtnDIsp5Vf+WNFkRrgQ==, tableContent=null), ArticleFig(id=1327012582428356797, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 16, caption=Localization errors of three comparative methods in scenario 3, figureFileSmall=G3wQWkSRuOecDY7Iu7jYBw==, figureFileBig=WxRyOKs1ucvoRc7DPpBYkg==, tableContent=null), ArticleFig(id=1327012582491271358, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图16, caption=场景3中的3种对比方法定位误差, figureFileSmall=G3wQWkSRuOecDY7Iu7jYBw==, figureFileBig=WxRyOKs1ucvoRc7DPpBYkg==, tableContent=null), ArticleFig(id=1327012582562574527, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 17, caption=Cumulative error distribution of three comparative methods in scenario 3, figureFileSmall=Q/lKHE9T51dMi8z92b0yYw==, figureFileBig=abP8clz2kHDjqdCKUbayiQ==, tableContent=null), ArticleFig(id=1327012582675820736, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图17, caption=场景3中的3种对比方法的累积误差分布, figureFileSmall=Q/lKHE9T51dMi8z92b0yYw==, figureFileBig=abP8clz2kHDjqdCKUbayiQ==, tableContent=null), ArticleFig(id=1327012582768095425, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Figure 18, caption=Computation time of positioning methods in three scenarios, figureFileSmall=RNnRVEAXPNp8xIze0yftQg==, figureFileBig=MJiR7O3gWNdm483F/oXLLw==, tableContent=null), ArticleFig(id=1327012582847787202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=图18, caption=3种场景中的定位方法运算时间, figureFileSmall=RNnRVEAXPNp8xIze0yftQg==, figureFileBig=MJiR7O3gWNdm483F/oXLLw==, tableContent=null), ArticleFig(id=1327012582948450500, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Table 1, caption=Error Statistics of Ranging Algorithms Under Different SNR Ratios m, figureFileSmall=null, figureFileBig=null, tableContent=
SNR/dB方法最大值最小值均值标准差0.95 cdf0.50 cdf
注:cdf表示误差累积分布.
10本文方法0.2900.0030.0540.0580.1760.033
90.2110.0030.0500.0490.1540.033
80.2690.0030.0610.0570.1790.047
70.2190.0030.0580.0550.1940.046
60.2400.0030.0590.0510.1610.042
50.2830.0030.0520.0520.1540.033
40.3330.0030.0600.0620.1790.040
30.2470.0030.0610.0540.1830.047
20.2610.0030.0670.0590.1940.047
10.2760.0030.0580.0630.2010.033
00.3110.0030.0600.0660.2010.033
10GCC[24-27]3.6630.0401.0330.8432.7950.769
94.8200.0181.0960.9153.0020.912
83.6840.0331.0370.8252.6520.769
73.6130.0031.0070.8832.9200.765
65.8490.0181.1150.9813.0950.926
55.8070.0181.1511.1653.9700.719
43.7630.0031.1490.9292.9050.901
34.0840.0181.0800.9593.2410.805
23.7910.0330.9880.7922.2940.790
12.7340.0030.9430.7452.5160.726
03.4980.0470.9410.7642.9800.772
), ArticleFig(id=1327012583091056837, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=表1, caption=

不同信噪比下的测距算法误差统计

, figureFileSmall=null, figureFileBig=null, tableContent=
SNR/dB方法最大值最小值均值标准差0.95 cdf0.50 cdf
注:cdf表示误差累积分布.
10本文方法0.2900.0030.0540.0580.1760.033
90.2110.0030.0500.0490.1540.033
80.2690.0030.0610.0570.1790.047
70.2190.0030.0580.0550.1940.046
60.2400.0030.0590.0510.1610.042
50.2830.0030.0520.0520.1540.033
40.3330.0030.0600.0620.1790.040
30.2470.0030.0610.0540.1830.047
20.2610.0030.0670.0590.1940.047
10.2760.0030.0580.0630.2010.033
00.3110.0030.0600.0660.2010.033
10GCC[24-27]3.6630.0401.0330.8432.7950.769
94.8200.0181.0960.9153.0020.912
83.6840.0331.0370.8252.6520.769
73.6130.0031.0070.8832.9200.765
65.8490.0181.1150.9813.0950.926
55.8070.0181.1511.1653.9700.719
43.7630.0031.1490.9292.9050.901
34.0840.0181.0800.9593.2410.805
23.7910.0330.9880.7922.2940.790
12.7340.0030.9430.7452.5160.726
03.4980.0470.9410.7642.9800.772
), ArticleFig(id=1327012583267217607, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Table 2, caption=Localization Results of Coordinate Value Fitting and Correction Using Machine Learning Models, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称RMSE/mMAE/m$ R^2 $
注:黑体数值表示最优值.
GBDT0.0340.017 40.999 98
SVR0.1240.109 40.999 79
MLP0.0280.022 20.999 98
LASSO0.2590.208 30.999 10
Adaboost1.0020.824 80.986 69
RF0.0130.007 90.999 99
Xgboost0.0330.020 20.999 98
LightGBM0.0510.035 40.999 96
GA-Xgboost0.0190.013 20.999 99
GA-LightGBM0.0470.030 80.999 96
融合集成学习模型0.0060.000 80.999 99
), ArticleFig(id=1327012583355297992, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=表2, caption=

使用机器学习模型对坐标值拟合修正的定位结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称RMSE/mMAE/m$ R^2 $
注:黑体数值表示最优值.
GBDT0.0340.017 40.999 98
SVR0.1240.109 40.999 79
MLP0.0280.022 20.999 98
LASSO0.2590.208 30.999 10
Adaboost1.0020.824 80.986 69
RF0.0130.007 90.999 99
Xgboost0.0330.020 20.999 98
LightGBM0.0510.035 40.999 96
GA-Xgboost0.0190.013 20.999 99
GA-LightGBM0.0470.030 80.999 96
融合集成学习模型0.0060.000 80.999 99
), ArticleFig(id=1327012583460155593, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Table 3, caption=Comparison of Localization RMSE Errors for Different Methods Under Multipath and NLOS Conditions m, figureFileSmall=null, figureFileBig=null, tableContent=
测试点位位置误差数据Chan方法Taylor方法本文方法
注:黑体数值表示最优值.
T1x坐标51.30不收敛21
y坐标49.80不收敛20.7
$ {{{{RMS E}}}} $43.22不收敛1.22
T2x坐标26.3218.6418.92
y坐标27.2519.0319.3
$ {{{{RMS E}}}} $11.030.350.31
T3x坐标11.6718.1718.67
y坐标11.8817.9818.54
$ {{{{RMS E}}}} $8.810.170.86
T4x坐标0.000.0017.3
y坐标0.000.0016.9
$ {{{{RMS E}}}} $24.0424.040.31
T5x坐标0.000.0016.4
y坐标0.000.0016.4
$ {{{{RMS E}}}} $22.6322.620.56
T6x坐标0.0014.7315.2
y坐标1.9815.2215.7
$ {{{{RMS E}}}} $19.860.340.72
), ArticleFig(id=1327012583539847370, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=表3, caption=

不同方法在多径和NLOS情况下的定位RMSE误差对比

, figureFileSmall=null, figureFileBig=null, tableContent=
测试点位位置误差数据Chan方法Taylor方法本文方法
注:黑体数值表示最优值.
T1x坐标51.30不收敛21
y坐标49.80不收敛20.7
$ {{{{RMS E}}}} $43.22不收敛1.22
T2x坐标26.3218.6418.92
y坐标27.2519.0319.3
$ {{{{RMS E}}}} $11.030.350.31
T3x坐标11.6718.1718.67
y坐标11.8817.9818.54
$ {{{{RMS E}}}} $8.810.170.86
T4x坐标0.000.0017.3
y坐标0.000.0016.9
$ {{{{RMS E}}}} $24.0424.040.31
T5x坐标0.000.0016.4
y坐标0.000.0016.4
$ {{{{RMS E}}}} $22.6322.620.56
T6x坐标0.0014.7315.2
y坐标1.9815.2215.7
$ {{{{RMS E}}}} $19.860.340.72
), ArticleFig(id=1327012583615344843, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=EN, label=Table 4, caption=Location Error Statistics of Comparative Methods in Multiple Scenarios m, figureFileSmall=null, figureFileBig=null, tableContent=
场景方法平均值标准差最大值最小值95%分
位数
50%分
位数
注:NA表示矩阵不收敛无法求解,黑体数值表示最优值.
1Chan方法3.025.4416.870.1214.120.26
Taylor 方法0.450.531.860.061.640.24
本文方法0.200.110.500.100.450.16
2Chan方法9.848.1217.540.1017.1115.82
Taylor方法1.581.182.560.072.562.49
本文方法0.690.451.130.101.131.00
3Chan方法1.58NA1.581.581.581.58
Taylor方法1.58NA1.581.581.581.58
本文方法0.050.050.180.010.180.04
), ArticleFig(id=1327012583695036620, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, language=CN, label=表4, caption=

多场景对比方法定位误差统计

, figureFileSmall=null, figureFileBig=null, tableContent=
场景方法平均值标准差最大值最小值95%分
位数
50%分
位数
注:NA表示矩阵不收敛无法求解,黑体数值表示最优值.
1Chan方法3.025.4416.870.1214.120.26
Taylor 方法0.450.531.860.061.640.24
本文方法0.200.110.500.100.450.16
2Chan方法9.848.1217.540.1017.1115.82
Taylor方法1.581.182.560.072.562.49
本文方法0.690.451.130.101.131.00
3Chan方法1.58NA1.581.581.581.58
Taylor方法1.58NA1.581.581.581.58
本文方法0.050.050.180.010.180.04
)], 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/issn1000-1239.202330882, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330882, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202330882, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202330882, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1738339200000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于融合集成学习的鲁棒近超声室内定位方法
贾乃征 , 薛灿 , 杨骝 , 王智 *
计算机研究与发展 | 网络与信息安全 2025,62(2): 488-502
收起
收藏切换
计算机研究与发展 |网络与信息安全 2025 , 62 (2) : 488 -502
基于融合集成学习的鲁棒近超声室内定位方法
全屏
[Author(id=1327012574266241151, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=naizheng.jia@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327012574350127233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574266241151, language=EN, stringName=Naizheng Jia, firstName=Naizheng, middleName=null, lastName=Jia, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 1998. PhD candidate. His main research interests include signal processing and acoustic signal localization

"}, bioImg=null, bioContent=

born in 1998. PhD candidate. His main research interests include signal processing and acoustic signal localization

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012574425624707, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574266241151, language=CN, stringName=贾乃征, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学控制科学与工程学院 杭州 310013, bio={"img":"4HvXn0p0W60BjfkoKJo1Qg==","content":"

1998年生. 博士研究生. 主要研究方向为信号处理、声信号定位

"}, bioImg=4HvXn0p0W60BjfkoKJo1Qg==, bioContent=

1998年生. 博士研究生. 主要研究方向为信号处理、声信号定位

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012574169772155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, xref=null, ext=[AuthorCompanyExt(id=1327012574178160764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1327012574186549373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学控制科学与工程学院 杭州 310013)])]), Author(id=1327012574496927877, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, 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=1327012574656311431, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574496927877, language=EN, stringName=Can Xue, firstName=Can, middleName=null, lastName=Xue, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 1997. PhD candidate. His main research interests include embedded system and acoustic signal localization

"}, bioImg=null, bioContent=

born in 1997. PhD candidate. His main research interests include embedded system and acoustic signal localization

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012574719225992, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574496927877, language=CN, stringName=薛灿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学控制科学与工程学院 杭州 310013, bio={"img":"KKwwNArx8EPg9LGzeVxl5A==","content":"

1997年生. 博士研究生. 主要研究方向为嵌入式系统开发、声信号定位

"}, bioImg=KKwwNArx8EPg9LGzeVxl5A==, bioContent=

1997年生. 博士研究生. 主要研究方向为嵌入式系统开发、声信号定位

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012574169772155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, xref=null, ext=[AuthorCompanyExt(id=1327012574178160764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1327012574186549373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学控制科学与工程学院 杭州 310013)])]), Author(id=1327012574819889290, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, 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=1327012574945718412, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574819889290, language=EN, stringName=Liu Yang, firstName=Liu, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 2000. PhD candidate. His main research interests include acoustic signal processing and robot localization

"}, bioImg=null, bioContent=

born in 2000. PhD candidate. His main research interests include acoustic signal processing and robot localization

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012575029604493, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012574819889290, language=CN, stringName=杨骝, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学控制科学与工程学院 杭州 310013, bio={"img":"q5RNDj/GvJUK4Q5LfDYxGA==","content":"

2000年生. 博士研究生. 主要研究方向为声信号处理、机器人定位

"}, bioImg=q5RNDj/GvJUK4Q5LfDYxGA==, bioContent=

2000年生. 博士研究生. 主要研究方向为声信号处理、机器人定位

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012574169772155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, xref=null, ext=[AuthorCompanyExt(id=1327012574178160764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1327012574186549373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学控制科学与工程学院 杭州 310013)])]), Author(id=1327012576703131791, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zjuwangzhi@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327012576791212178, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012576703131791, language=EN, stringName=Zhi Wang, firstName=Zhi, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 1967. PhD, associate professor. Member of CCF. His main research interests include signal processing and acoustic signal sensing, and robot navigation

"}, bioImg=null, bioContent=

born in 1967. PhD, associate professor. Member of CCF. His main research interests include signal processing and acoustic signal sensing, and robot navigation

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012576858321043, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, authorId=1327012576703131791, language=CN, stringName=王智, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=浙江大学控制科学与工程学院 杭州 310013, bio={"img":"+jn5V0dEhW0qnO8862+Ryw==","content":"

1967年生. 博士,副教授. CCF会员. 主要研究方向为信号处理、声波感知、机器人导航

"}, bioImg=+jn5V0dEhW0qnO8862+Ryw==, bioContent=

1967年生. 博士,副教授. CCF会员. 主要研究方向为信号处理、声波感知、机器人导航

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012574169772155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, xref=null, ext=[AuthorCompanyExt(id=1327012574178160764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Control Science and Engineering, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1327012574186549373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327012568088031305, companyId=1327012574169772155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学控制科学与工程学院 杭州 310013)])])]
贾乃征 , 薛灿, 杨骝, 王智*
作者信息
  • 浙江大学控制科学与工程学院 杭州 310013
通讯作者:
作者简介:

1998年生. 博士研究生. 主要研究方向为信号处理、声信号定位

1997年生. 博士研究生. 主要研究方向为嵌入式系统开发、声信号定位

2000年生. 博士研究生. 主要研究方向为声信号处理、机器人定位

1967年生. 博士,副教授. CCF会员. 主要研究方向为信号处理、声波感知、机器人导航

A Near-Ultrasonic Robust Indoor Localization Method Based on Stacking Ensemble Learning
Naizheng Jia , Can Xue, Liu Yang, Zhi Wang*
Affiliations
  • College of Control Science and Engineering, Zhejiang University, Hangzhou 310013
  • born in 1998. PhD candidate. His main research interests include signal processing and acoustic signal localization

    born in 1997. PhD candidate. His main research interests include embedded system and acoustic signal localization

    born in 2000. PhD candidate. His main research interests include acoustic signal processing and robot localization

    born in 1967. PhD, associate professor. Member of CCF. His main research interests include signal processing and acoustic signal sensing, and robot navigation

出版时间: 2025-02-01 doi: 10.7544/issn1000-1239.202330882
文章导航
收藏切换

近年来随着经济的发展,室内定位系统的需求越来越迫切. 传统的室内定位系统如WIFI定位和蓝牙定位面临着定位精度低、易受非视距(non-line-of-sight,NLOS)和噪声干扰等挑战. 针对这些问题,提出了一种基于融合集成学习的近超声室内定位方法. 首先,使用优化的增强互相关方法有效地抵消多径干扰. 与传统基于峰值提取或固定阈值的方法相比,此法在混响环境中明显提升了测距的精度. 然后,利用到达时间差(time difference of arrival,TDOA)作为特征进行提取. 最终,采用了融合集成学习模型,对设定好的训练集进行交叉融合训练,并输入特征,从而得到修正的定位结果. 仿真和实验测试结果表明,所提出的方法可以在室内NLOS和噪声干扰的情况下克服较大误差实现精确定位,并且精度优于对比方法50%~90%. 本文核心数据公布在https://github.com/ChirsJia/JSJYF上.

室内定位  /  近超声定位  /  信号处理  /  机器学习  /  到达时间差

Recent economic advancements have significantly supported the popularity of indoor positioning systems (IPS) and indoor localization-based services (ILBS). This trend is particularly obvious as global navigation satellite systems (GNSS) are ineffective in indoor environments. Traditional IPS, such as WIFI and Bluetooth positioning, face challenges like low accuracy and are prone to non-line-of-sight (NLOS) and noise interference. In response to this issue, we propose a novel near-ultrasonic robust indoor localization method based on the stacking ensemble model. Initially, the method employs an optimized enhanced cross-correlation technique to effectively mitigate multipath interference in acoustic ranging. Compared with the conventional methods based on peak extraction or fixed thresholding, this approach significantly improves ranging accuracy in reverberant environments. Subsequently, time difference of arrival (TDOA) is extracted as a feature. Finally, we utilize a stacking ensemble learning model, incorporating optimized machine learning models, to train a pre-set dataset. This method, integrating the extracted feature, enables to achieve correct localization results in NLOS and large ranging error. Numerical simulations, ray-tracing acoustic analyses, and empirical validations suggest that our approach notably mitigates errors prevalent in NLOS and acoustically noisy indoor environments and yielding localization accuracy significantly exceeds current methods by 50%−90%. The core dataset available at https://github.com/ChirsJia/JSJYF.

indoor positioning  /  near-ultrasonic localization  /  signal processing  /  machine learning  /  TDOA
贾乃征, 薛灿, 杨骝, 王智. 基于融合集成学习的鲁棒近超声室内定位方法. 计算机研究与发展, 2025 , 62 (2) : 488 -502 . DOI: 10.7544/issn1000-1239.202330882
Naizheng Jia, Can Xue, Liu Yang, Zhi Wang. A Near-Ultrasonic Robust Indoor Localization Method Based on Stacking Ensemble Learning[J]. Journal of Computer Research and Development, 2025 , 62 (2) : 488 -502 . DOI: 10.7544/issn1000-1239.202330882
随着经济与科技的持续进步,以及城市化进程的不断加速,工业室内空间的总面积已经呈现显著增长趋势[1]. 此外,随着产业对室内位置信息需求的日益增强,精确的定位信息对于诸如电力系统、化学工厂等高风险领域显得尤为关键. 这不仅可以有效提升工业人员的安全性,还能优化工业系统的运行效率. 因此,如何准确地获取这一位置信息已成为当前工业领域亟待研究和解决的核心问题. 近些年来,随着智能手机的普及,位置信息的获取已经越来越方便. 当今最流行的定位系统当属全球卫星导航系统(global navigation satellite system,GNSS)[2]. GNSS采用卫星获得相对距离信息最终求解位置. 然而在室内环境,卫星的电磁信号会极大衰减从而导致GNSS无法实现定位[3]. 为了解决这一问题,GNSS实时运动测量(real-time kinematic,RTK)和GNSS 精确点定位(precise point positioning,PPP)可以实现高精度的GNSS定位[4]. 然而RTK和PPP需要特制的手持机,这使得它们在工业界的广泛应用面临挑战[5]. 为了克服这些挑战,许多射频(radio frequency,RF)技术已经应用到了室内定位领域,例如无线保真(wireless fidelity,WIFI)定位[6]、蜂窝移动定位[7-9]、低功耗蓝牙(bluetooth low energy,BLE)定位[10-11]、超宽带(ultra-wide band,UWB)定位[12-14]和声学定位[15-17]等室内定位技术. 但是许多室内空间是密闭空间,且多遮蔽和电磁、噪声干扰,导致许多定位手段在室内空间内部无法正常应用. WIFI不需要增加额外的基站和设备,是十分节约成本的定位方式,常用的WIFI定位方法有WIFI接收信号强度指示器(received signal strength indicator,RSSI)、WIFI 往返时间(round trip time,RTT)和WIFI指纹法定位[18]. 然而WIFI RSSI由于衰减系数的不确定,对环境有很强的依赖性. WIFI RTT需要特殊的节点(access point,AP)来进行辅助定位. WIFI指纹法需要利用机器学习来拟合指纹模型,采样较为困难. 而蜂窝移动和BLE系统利用的电磁频谱可为用户提供高精度定位和多样的交互式定位服务. 但是蜂窝移动技术对使用终端有一定要求,造价昂贵. BLE RSSI也可以利用信号的强度信息进行定位,但是RSSI无法实现远距离非视距(non-light of sight,NLOS)定位. BLE 到达角(angle of arrival,AOA)可以实现高精度的厘米级室内定位,然而BLE AOA所需要的基站极其昂贵,由于BLE的传输距离较近,因此布置基站的成本极高,从而不适合在室内空间应用[19]. 相比之下,UWB是当前工业系统较为流行的室内定位技术,利用其500 MHz带宽的脉冲信号可以实现室内厘米级定位. 然而UWB基站的成本过于昂贵,信号穿透力弱,且在金属遮蔽干扰的情况下,很难准确识别到接收信号. 随着无人设备的普及,激光雷达[20] 主要通过发射激光束来测量距离并生成点云数据. 通过利用激光点云结合同时定位与地图(simultaneous localization and mapping,SLAM)构建算法,可以实现极高的定位精度. 然而激光雷达的成本过高,且在遮挡环境下完全无法使用,因此很难在工业领域实现广泛的应用.
针对以上问题,声学室内定位提供了一种完全不同的思路. 声学方法通常利用分布式声学基站来发送调制信号,定位系统利用声波传输到麦克风的到达时间测距,并进一步利用到达时间(time of arrival,TOA)或者到达时间差(time difference of arrival,TDOA)方法解算出距离[21]. 同时,由于声学的多普勒效应,也可以求解出被定位目标的速度[22]. 声学定位系统仅需简易的扬声器和麦克风配置,便可实现定位目的,因而具有显著的成本优势. 值得一提的是,现代智能手机能够捕获低于22 kHz的声波信号. 这一特点使声学定位系统在兼容性方面具有优势,适合广泛应用于民用和工业领域的定位需求. 但是,在遭受强烈多径干扰的环境下,声学信号的到达时间估计面临诸多困难. 尤其是在噪声强烈和非视距干扰频繁的场景中,得到的测距值可能呈现出非高斯分布的显著误差. 在这样的环境条件下,依赖传统的测距和定位技术来达到高精度位置估计变得尤为困难.
近超声室内定位系统如图1所示,由定位基站、同步主站、定位标签和云计算平台组成. 具体组成为:
1)定位基站. 定位基站是一种采用时分轮询方式的时序信号发生器. 每个基站间隔0.15 s发出指定声信号.
2)同步主站. 通过Lora系统实现定位基站时序同步.
3)定位标签. 定位标签是一种便携设备,可以接收声信号并将声信号录制结果上传到云计算平台. 录音采样频率设定为48 kHz.
4)云计算平台. 云计算平台计算标签信号的到达时间,通过基站坐标自适应训练改进的TDOA模型,并根据定位标签接收到的到达时间值计算出准确的坐标值.
本文的主要技术贡献是提出了一种新的基于集成融合学习的近超声室内空间定位方法. 以17~21 kHz的扫频余弦信号(Chirp)作为定位信号;以基于增强互相关技术作为检测信号到达时间的方法;以基于融合集成学习改进的TDOA方法对定位点具体坐标进行修正. 仿真和实验结果表明该方法可以在室内空间中实现稳定且高精度的定位.
近超声室内定位是指利用频率17~22 kHz的近超声波进行信息传递和室内定位. 近超声室内定位的载体多为智能手机. 它不受电磁波的干扰,利用滤波和互相关等技术可以实现噪声环境下高精度定位[23].
近超声声学测距主要以手机发出频率范围在17 kHz以上的Chirp信号,并在接收端利用匹配滤波器(match filter,MF)或广义互相关(general cross correlation,GCC)的方法实现到达时间估计,并进一步转换成测距值. 目前,较多的方法依然采用GCC的最大峰值位置来确定到达时间[24-27],该方法抗噪声能力强,检测较为简便. 然而在室内混响较为严重的环境下,无法实现高精度测距. 文献[28]利用编码的声信号进行室内测距,能够将误差控制在20 cm以内. 文献[29]通过对声信号功率谱分析从而抑制环境混响的方法实现了在低信噪比下20 cm误差的声波测距. 文献[30]利用2阶段法和阈值检测融合的方法实现在多径环境下的近超声测距. 文献[31]使用双向传感进行纯软件方案的室内传感和定位,达到了0.1 m的测距精度. 然而,以上方法多基于匹配滤波结果进行计算,在多径和非视距干扰的环境下寻峰难度大,难以准确地分辨到达径.文献[32]利用迭代的方法反复重建信号,滤除环境多径对近超声测距所带来的干扰. 然而该方法利用迭代分数傅里叶运算,计算求解复杂度过高,实用性较差. 近些年来,随着虚拟现实(virtual reality,VR)的兴起,利用声波追踪来定位麦克风位置的应用也越来越受到关注. 文献[33]引入调频连续波(frequency modulated continuous wave,FMCW)技术可以在5 m距离以内实现毫米级测距追踪. 然而,利用FMCW实现声波测距方法的测距量程有限,无法实现远距离测距. 文献[34-35]利用声波单频信号的相位来计算麦克风接收设备的相对位移,并进一步求解设备运动轨迹. 然而这些方法仅能对动态目标实现追踪,无法对静态、快速移动目标实现高精度测距.
文献[21]利用异步声学的参与式定位系统实现了0.98 m的定位精度. 文献[30]在室内实现了0.50 m的定位精度. 然而,上述定位系统并未考虑在NLOS环境下的定位模式. 文献[17]使用正交编码的声波信号,利用卡尔曼滤波器融合惯性定位导航(inertial measurement unit,IMU)和地图信息,实现室内声信号高精度定位. 文献[36-38]利用步行者航位推算(pedestrian dead reckoning,PDR)融合定位结果来矫正声波定位带来的非视距误差,然而PDR难以估计步长,应用范围有限且需要增加额外设备. 文献[39]使用高精度的编码操作实现声信号的捕捉和定位. 然而上述方案的基站设备布局和对声学信号的处理过程过于复杂,对环境噪声以及NLOS影响干扰的容忍度低,难以在室内空间的场景中达到一个稳定的人员定位精度.
在室内近超声定位信号选择方面,声信号通常选择相关性好、易区分的不可听声. Chirp信号符合这一特征. Chirp信号是声音频率随时间线性变化的信号,该信号具有很强的自相关特性且不易受多径影响[40]. 本文选取信号频率为17~21 kHz、采样率为48 kHz、持续时间为40 ms、信号刷新率为1 Hz的Chirp信号作为定位信号.
Chirp信号$x(t)$表达定义为
$ x(t)=\cos\left(2\text{π}\left(f_0t+\dfrac{1}{2}u_0t^2\right)\right), $
其中${f_0}$ 为基础频率;${u_0}$为调频率,目的是控制信号频率随时间的变化率;T为信号持续时间,$t \in [0,T]$.
然而该信号会因低频泄露导致人耳不适,为解决这一问题需要对信号进行加汉明窗控制其低频信号泄露,从而减少对人的干扰. 汉明窗表达式为
$ w\left( t \right) = \;\dfrac{1}{2}\left( {1 - \cos \dfrac{{2{\text{π}}t}}{T}} \right) . $
式(2)所生成的Chirp信号波形图和频谱图如图2所示.
基于Chirp信号相关性能好的特点,通常情况下使用广义互相关求解信号的到达时间. 对于原始信号$x(t)$和接收信号$y(t)$,接收信号可以写为
$ y(t)=\displaystyle\sum\limits_{i=1}^L\alpha_ix(t-\tau_i), $
其中L为到达信号的总路径数,${\tau _i}$为每个路径信号的到达时间,$ {\alpha _i} $为每个路径的衰减系数. 通常情况下,$y(t)$也可以写为
$ y(t)=h(t)\otimes x(t), $
其中$h(t)$可以表示为[29]
$ h(t)=g(t)\text{e}^{-\eta t}, $
其中$ g(t) $为随机高斯白噪声,$ \eta $是被定义为一种与室内混响参数相关的系数,在本文中,$ \eta = \dfrac{{3\ln 10}}{{{T_{\text{r}}}}} $,$ {T_{\text{r}}} $通常取160 ms[29,41].
对该信号求互相关值可以得到
$ {R_{xy}}(t) = \int_{ - \infty }^{ + \infty } {x(t)y(t - p){\text{d}}p} . $
到达时间值可以通过传统的求广义互相关结果的最大阈值获得. 然而在实际测量中,由于多径带来的干扰,较难从互相关结果图中提取第1径. 图3展示了通过式(5)(6)仿真得到的带有混响的接收信号和互相关值. 可以发现此时的信号混响较为严重,难以辨别准确的信号到达时间.
为解决这一问题,本文提出了第1径增强算法求解到达时间值. 首先,求解到达时间的粗估计值
$ {t_{{\text{coarse}}}} = \arg \max [{\hat R_{xy}}\left( n \right)] . $
通常情况下,由于多径干扰的存在,$ {t_{{\text{coarse}}}} $会落后于实际的到达时间. 在这里,可以利用FMCW方法的中频信号提取信号的多径信息. 首先设置$ {t_{{\text{ahead}}}} $为提前信号检测时间,在这里设置${t_{{\text{ahead}}}}= $0.01 s,这一步目的是提取完整的多径信号. 含有多径信息的中频信号$ {x_{{\text{IF}}}} $可以表示为
$ \begin{split}x_{\text{IF}}= & x(t)y(t)=x(t)\displaystyle\sum\limits_{i=1}^L\alpha_ix(t-\tau_i)= \\ & \dfrac{1}{2}\displaystyle\sum\limits_{i=1}^L\alpha_i\cos\left(2\text{π}\left(u_0\tau_it+f_0\tau_i\right)\right),\end{split} $
其中对信号$ {x_{{\text{IF}}}} $进行傅里叶变换得到$ {X_{{\text{IF}}}} $,即可得到将多径信号显示在不同频率对应的峰值中的每一个到达径,如图4所示,相比于互相关值图3(b),可以观察到在频谱图上直观地呈现出信号的到达径.
然而,FMCW的分辨率有限,在声学中,FMCW的距离分辨率为$ \dfrac{c}{{2{u_0}T}} = 0.042\;9\;{\text{m}} $,无法满足信号多径分辨率的提取需求. 因此需要继续结合互相关谱来对第1径进行增强. 对信号频谱求极值得到的频谱极值集合为
$ F = \mathop {extremum}\limits_f (peak({X_{{\text{IF}}}}(f))) , $
其中$ \mathop {extremum}\limits_f ( \cdot ) $为极值算子,$peaks( \cdot )$为寻峰算子,最终选择出第1径代表的频率峰值为
$ {f_\eta } = \mathop {\min }\limits_f \left( {{X_{{\text{IF}}}}\left( F \right) \geqslant 0.2\max \left( {{X_{{\text{IF}}}}} \right)} \right) . $
本文选择0.2作为频率${f_\eta } $阈值,旨在有效消除中频信号旁瓣的干扰. 基于先前的研究成果,设定频率${f_\eta } $阈值为0.2能在最大程度上减少快速傅里叶变换(fast Fourier transform,FFT)以及环境背景噪声中旁瓣的干扰效应[42].
此时$ {f_\eta } $对应的到达时间为
$ {t_0} = {t_{{\text{coarse}}}} - {t_{{\text{ahead}}}} - \dfrac{{{f_\eta }}}{{{u_0}}} . $
对信号广义互相关的结果增强可以求得
$ \begin{split} &{\hat R_{xy}}\left( {{t_0} - \dfrac{c}{{4{u_0}T}},{t_0} + \dfrac{c}{{4{u_0}T}}} \right) = spline \Bigg( \dfrac{{\max \left( {{X_{{\text{IF}}}}} \right)}}{{{X_{{\text{IF}}}}({f_\eta })}}{{\hat R}_{xy}}\Bigg( {t_0} -\\&\quad \dfrac{c}{{4{u_0}T}},{t_0} + \dfrac{c}{{4{u_0}T}} \Bigg) \Bigg),\\[-1pt]\end{split} $
其中$ spline{\text{(}} \cdot {\text{)}} $代表的是基本3次样条差值法算子. 其目的是避免采样率间隔带来测距误差. 此时互相关结果$ {\hat R_{xy}} $的第1径已经被增强. 图5展示了这一过程,可以清晰地观察到第1径已经得到显著增强,呈现出明显的特征. 因此可以直接计算该到达时间值.
TDOA方法是通过获得各参考基站与待定位目标之间的距离之差,进而求解非线性双曲方程组来推断待定位对象相对于各参考基站的相对位置的定位方法. 欲要求解目标坐标,就需要求解多个基站相关的非线性方程组. 非线性方程组为
$ \begin{split} & \sqrt {{{\left( {{X_i} - x} \right)}^2} + {{\left( {{Y_i} - y} \right)}^2}} - \sqrt {{{\left( {{X_1} - x} \right)}^2} + {{\left( {{Y_1} - y} \right)}^2}} = {R_{i,1}},\\&\quad i = 1,2,…,n,\\[-1pt] \end{split}$
其中$ ({X_i},{Y_i}) $为第i个基站坐标,$ ({X_1},{Y_1}) $为基准基站坐标,$ (x,y) $为目标所在坐标,n为基站总数量,$ {R_{i,1}} $为基站 i到达目标与基准基站到达目标的距离差,记为$ {R_{i,1}} = {t_{i,1}}c $,$ c $为声速,$ {t_{i,1}} $为第i个基站到达目标的时间与基准基站到达目标的时间之差,也记作TDOA值. 该方法示意图如图6所示.
在通常情况下传统 TDOA方程组在有误差的情况下求解极其困难. 为解决这一问题,在实际应用有误差干扰的影响下会需要用近似优化的TDOA方法,如Chan方法[43]、Taylor方法[44-46]在低误差情况下可以逼近克拉美罗下界(Cramer-rao lower bound,CRLB). 然而Chan方法[43]没有考虑到NLOS误差,且在基站数目较小的情况下该方法无法收敛. Taylor方法[44-46]对初值选取有一定要求,在初值误差较大的情况下很难收敛. 因此以上2种方法不适宜用于室内定位. 针对以上2种情况,本文提出了一种如图7所示的基于融合集成学习模型改进的TDOA方法. 该方法通过基站的TDOA值作为特征,融合集成学习模型直接拟合出实际的坐标值,可以很好地克服大尺度误差对定位点的影响.
图7所示步骤可解释如下:
1)时间戳获取. 由于在实际过程中获得各个基站时间戳的准确数据比较困难,且混杂误差,不易操作和计算. 为了克服上述困难,可以将实验所需地形、基站坐标进行准确测量,待测量结束后,以0.1 m为网格最小单位,利用网格法获得每一个小区域到达各个基站的时间戳值,并转化为TDOA值. 以4∶1的比例划分训练集与测试集.
2)数据增强. 为了防止图7模型过拟合或者不能应对实际声学环境的噪声干扰,在原有的数据集基础上加入均值为0、标准差为0.1 m的符合高斯分布的误差值. 将该数据与原有数据混合并随机打乱.
3)多输出. 以数据增强所得的TDOA值为特征(4个基站就有3个TDOA特征). 由于机器学习模型并没有双输出结构,因此要对实际x轴坐标、y轴坐标均进行预测,最后依次输出结果.
4)TDOA值修正. 将拟合出的新坐标作为最终坐标.
融合集成模型是一种分级的回归模型. 它利用原有1级回归器(基模型)对训练集通过交叉验证分层来预测结果形成新的特征,并利用2级预测器(最终模型)对混合特征进行预测. 该模型在数据量较大、特征数量较小、单模型性能不足时,可以有效地混合各个模型的优点,对原有误差进行修正,加入基模型的预测结果作为特征,并提高原有基模型的预测精度. 该模型已经被广泛应用在卡古(Kaggle)等数据比赛当中. 在本文中融合集成模型将支持向量回归(support vector regression,SVR)、梯度提升回归树(gradient boosting decision tree,GBDT)、遗传算法(genetic algorithm,GA)优化的极端提升树GA-Xgboost和遗传算法优化的轻量级梯度提升树GA-LightGBM模型作为基模型,随机森林(random forest,RF)作为最终预测器,采用5折交叉验证来构成新的特征. 融合集成结构和具体训练步骤如图8所示.
融合集成学习模型的具体步骤如下:
1)将原有数据集随机打乱,按照20%比例分为训练集$ {{{P}}_{{\text{train}}}} $和测试集$ {{{P}}_{{\text{test}}}} $.
2)将训练集$ {{{P}}_{{\text{train}}}} $按照5折交叉验证方法平均划分成5个子集,如图8(b)所示. 将每个子集依次做一次验证集,其余4个子集充作基模型的训练集. 可以得到第n个基模型的预测结果集合为$ {{{L}}_n} = \{ {{{S}}_1},{{{S}}_2}, … , {{{S}}_5} \} $,$ {{{S}}_k} $代表第k个训练集的子集在其余4个子集充作基模型的训练集情况下对该子集的预测结果. 同时也用该模型对测试集$ {{{P}}_{{\text{test}}}} $进行预测,每次预测结果为$ {R_i},i = 1,2,…,5 $. 第n个基模型在5次训练之后可以得到新的测试集平均值为$ {{{K}}_n} = \dfrac{1}{5}( { {{{{{R}}_1} + {{{R}}_2} + {{{R}}_3} + {{{R}}_4} + {{{R}}_5}}}} ) $. 注意,训练过程只能在训练集上进行,以防止数据泄露.
3)将训练集$ {{{P}}_{{\text{train}}}} $与$ {{{L}}_n} $合并,测试集$ {{{P}}_{{\text{test}}}} $与$ {{{K}}_n} $合并,得到新的训练集$ {{P}}^*_{{\text{train}}} = \{{{{P}}_{{\text{train}}}},{{{L}}_1},{{{L}}_2},{{{L}}_3},{{{L}}_4}\} $和新的测试集$ {{P}}^*_{\text{test}} = \{{{{P}}_{{\text{test}}}},{{{K}}_1},{{{K}}_2},{{{K}}_3},{{{K}}_4}\} $. 此时模型的特征数增加4个由基模型在训练集上构成的新特征.
4)用最终预测器训练$ \boldsymbol{\mathit{P}}_{\text{train}}^* $,并在$ \boldsymbol{\mathit{P}}_{\text{test}}^* $上进行验证.
在本文中,采用了一种仅在训练集上训练数据的方法,有效避免了数据泄露现象,同时充分吸收了各个模型的优势. 特别在NLOS条件下,该方法对于可能出现的1~2个基站的TDOA偏差表现出显著的纠正能力. 值得注意的是,尽管集成学习模型在Kaggle等数据分析竞赛中已被广泛应用,我们却发现该模型容易引起显著的过拟合效应,从而影响数据的拟合和分类性能. 然而,这种过拟合特性在非视距定位领域中反而可以被有效利用. 通过本文开发的方法,我们能够准确修正TDOA值的变化,并利用过拟合效应实现高精度的误差矫正. 此外,使用NLOS条件下的数据进行训练可能会由于过拟合效应而导致定位误差. 因此,在训练数据集中,我们主要采用了理想的TDOA定位值.
在回归模型中,目标函数是最小化错误率和误差. 而极端梯度提升树Xgboost模型通过泰勒展开和松弛等方法优化目标函数[47]. 在Xgboost模型中,定义误差函数为
$ O_{\text{obj}}(\theta)=L(\theta)+W(\theta), $
其中$L(\theta )$是系统的损失函数,通常定义为均方根误差(mean square error,MSE),$W(\theta )$为正则化项,$\theta $为误差参量,通常为预测值和真值的差值.
式(14)的运算可以避免训练过程中产生过拟合[48]. 然而传统MSE损失函数对异常值容忍度较小,因此本文在这里采用胡伯损失(Huber-Loss)函数. Huber-Loss的损失函数定义为
$ \hat{O}_{\text{obj}}(y,f(x))=\left\{\begin{aligned} & \dfrac{1}{2}(y-f(x))^2,\; \; |y-f(x)|\leqslant\delta, \\ & \delta|y-f(x)|-\dfrac{1}{2}\delta^2,\; \; |y-f(x)| > \delta\text{, }\end{aligned}\right. $
其中y为真值,f (x)为预测值,$ \delta $为常数参量,且$\delta=1.5 $.
Huber-Loss在零点不可导,不满足Xgboost的损失函数形式,可以用近似胡伯损失(Psudo-Huber)函数表示Psudo-Huber为
$ {\hat O_{{\text{psudo}}}}(y,f(x)) = {\delta ^2}\left( {\sqrt {1 + {{\left( {\dfrac{{f(x) - y}}{\delta }} \right)}^2}} - 1} \right). $
通过式(18)将MSE损失函数转换为Huber-Loss,进一步提高对模型异常值的容忍度.
GBDT模型是机器学习中一个重要的模型,该模型通过产生弱分类器,以及通过对弱分类器的迭代训练从而得到最佳模型[49]. 然而当其遇到大规模数据时,其梯度下降算法会导致算法的运算复杂度较高,实际生产生活当中无法实用化. 为了解决这个问题,微软研究院提出了轻量级梯度提升树模型LightGBM[50],该模型在数据与处理方面采用基于直方图的决策和单边梯度采样等算法,在特征分析方面采用互斥特征捆绑算法,可以使原有模型具有更快的训练速度、更低的内存消耗、更好的准确率,支持分布式可以快速处理大规模数据.
遗传算法是一种全局优化算法[51]. 由于集成学习的模型超参数并没有线性对应关系,而常用算法如贝叶斯参数法、网格搜索法多为全局遍历搜索,精度极低且计算复杂度较高,在大规模数据模型上难以应用. 本文采用GA优化算法调整Xgboost和LightGBM的超参数[52],改进的新模型成为GA-Xgboost模型和GA-LightGBM模型. GA算法步骤为:
1)种群和染色体编码
由于GA算法用来优化集成学习模型参数,因此GA算法的染色体数目为集成学习模型中需要调参的个数. 编码方式采用实数编码,避免二进制编码带来精度上的误差.
2)适应度函数和策略
适应度函数为定位点的均方根误差. 交叉采用二项分布交叉,在选择过程中采用种马策略和一对一选择策略. 在本文中,GA模型的相关参数如下:种群规模为50、迭代次数为50次、变异率为0.8、交叉率为0.2.
本节将通过仿真验证完整算法. 仿真使用软件为MATLAB 2021a和Python 3.8. 硬件处理器为Intel® CoreTM i5-7500 CPU,内存16 GB. 基站A坐标为(0, 30 m),基站B坐标为 (30 m, 30 m),基站C坐标为(0, 0),基站D坐标为(30 m, 30 m). 测试定位标签${T_{{\text{tag}}}}$的坐标为(11.6 m, 7.5 m).
首先本文对近超声测距算法设计了仿真验证. 图9展示了本文所述定位方法的数值仿真分析. 信道模型为$ g(t){{\text{e}}^{\eta t}} $. 通过结果可以得出本文所提出的测距算法精度要极大优于传统的GCC方法[24-27].
为了验证本文算法在噪声环境下的表现,表1统计了在不同信噪比(signal-to-noise ratio,SNR)下本文所提测距算法和传统GCC方法[24-27]测距算法的误差值的各项属性. 从表1可以得知,本文方法在噪声的环境下表现更优. 同时,噪声并没有对测距算法的精度产生显著影响.
表2比较了不同机器学习(machine learning,ML)模型在测试集上的坐标值拟合能力. 这一性能决定了该方法最终的定位性能. 共比较了GBDT、SVR、多层感知器(multiple layer perceptor,MLP[53]、拉索(LASSO)回归、自适应提升算法(Adaboost)回归器、随机森林(RF)、Xgboost、LightGBM、GA-Xgboost、GA-LightGBM和融合集成学习模型共11种模型. 验证函数为均方根误差(root mean square error,RMSE)、绝对平均误差(mean absolute error,MAE)和决定系数R2. 其定义式分别为
$ {{{{RMS E}}}} = \displaystyle\sum\limits_{i = 1}^N {\sqrt {\dfrac{{{{({x_i} - x)}^2} + {{({y_i} - y)}^2}}}{{2N}}} } \text{,} $
$ {{{{MAE}}}} = \displaystyle\sum\limits_{i = 1}^N {\dfrac{{\left| {{x_i} - x} \right| + \left| {{y_i} - y} \right|}}{{2N}}} \text{,} $
$ {{{{{R}}^{\text{2}}}}} = 1 - \dfrac{{\displaystyle\sum\limits_{i = 1}^N {[{{({y_i} - y)}^2} + {{({x_i} - x)}^2}]} }}{{\displaystyle\sum\limits_{i = 1}^N {[{{({y_i} - \bar y)}^2} + {{({x_i} - \bar x)}^2}]} }} \text{,} $
其中$ {x_i} $,$ {y_i} $分别为预测点i的x轴坐标和y轴坐标,x,y分别目标所在点的x轴坐标和y轴坐标,$ \bar x $与$ \bar y $为预测的x轴坐标和y轴坐标的均值. N为样本总数.
根据表现较为出色的RF模型、GBDT模型、GA-Xgboost模型和GA-LightGBM模型,将它们组成融合集成学习模型. 经过表2对比证明融合集成学习模型在测试集上有最低的RMSE、最低的MAE和最高的R2. 接下来,将上述模型组合转换为TDOA定位方法,并进行性能评估.
为进一步验证该坐标修正模型的解释可行性,本文对融合集成学习模型在测试集上的相对误差进行了验证. 定义模型的位置误差为
$ {\delta _{{\text{error}}}} = {x_i} - x + {y_i} - y . $
如果$ {\delta _{{\text{error}}}} $残差分布符合正态分布,则说明融合集成学习模型能够完好地修正坐标值. 图10说明了融合集成学习模型在测试集上的残差分布符合正态分布,因此该模型有良好的解释性.
为确定融合集成学习的TDOA在定位上的泛化能力,并与传统模型对比其优越性. 使用500次蒙特卡洛仿真,对每一组得到的TDOA加入不同尺度的测量误差. 误差尺度定义为符合正态分布的$N(0,\sigma )$,$\sigma $为误差尺度的标准差. 定位结果的RMSE与Chan方法[43]、 Taylor方法[44-46]和理论误差的最低值CRLB做对比,最终结果如图11所示. 测距误差p所对应的当前仿真环境的$ {{{\rm CRLB} (p)}} $可以计算为
$ \rm{C}RLB(p)=\sqrt{\rm{t}r\left(\left(\boldsymbol{G}^{\text{T}}\boldsymbol{C(}p\boldsymbol{)}^{-1}\boldsymbol{G}\right)^{-1}\right)}, $
其中$ {\boldsymbol{C}}(p) $为当前测距误差p所对应的协方差矩阵,$ {\boldsymbol{G}} $为待定位点与基站坐标的TDOA值矩阵.
从图11可以看出,在加入不同尺度的高斯噪声误差下,Chan方法[43]、Taylor方法[44-46]在误差较大的情况下无法精确定位. 而本文基于融合集成学习改进的TDOA有最稳定的定位效果,在误差较大的情况下依然接近CRLB.
本文采用MATLAB 2022a软件和射线仿真法[16],用于分析信号在室内传播中的多普勒效应和多径效应, 在声学室内仿真中具有重要作用. 该平台可以搭建复杂的室内环境,可以设置遮挡、反射系数、反射次数,其声信号传播衰减系数是根据实际温度、湿度、压强来修正;该平台的信号传播是以仿真所得脉冲响应函数和原始信号卷积模拟.
仿真环境为密闭室内空间,预先设置房间温度为25 ℃,相对湿度为30%,大气压为101 kPa,声速为346 m/s,墙壁反射率为0.6.为考虑真实环境,该模型采用3维坐标定位. 基站3维坐标分别为基站A3(0, 30, 3),基站B3(30, 30, 3),基站C3(30, 0, 3),基站D3(0, 0, 3),测试目标点位分别为T1(20,20,3),T2(19, 19, 3),T3(18,18,3),T4(17,17,3),T5(16,16,3),T6(15,15,3). 此时到达时间和TDOA值误差较大,适合比较模型在实际场景中的定位能力.
仿真在NLOS情况下进行,对应的房间平面图、立体图和不同基站产生的RIR(room impulse response) 如图12所示. NLOS通过图12 (a)(b)在基站 B3前添设遮挡和障碍物来模拟. 从这2种情况的RIR响应可以看出,在该密闭空间的环境下,声信号传播的混响效应严重. 在NLOS情况下,声信号时延较为严重,难以分辨直接到达的信号.
选取本文基于融合集成学习的TDOA模型和上文分析中表现效果较稳定的Chan方法[43]、Taylor方法[44-46]. 不同方法在NLOS环境下的误差如表3所示. 定义定位点的RMSE误差为
$ RMS E=\sqrt{(\hat{x}_i-x)^2+(\hat{y}_i-y)^2}, $
其中$ {\hat x_i} $,$ {\hat y_i} $分别是通过不同方法解算出的x轴坐标、y轴坐标. x,y分别是目标所在点的x轴坐标、y轴坐标.
可以发现此时由于环境非视距较为严重的原因,Chan 方法[43]无法得出准确值,Taylor方法[44-46]基于Chan方法[43]进行迭代,在某些时刻可以得到较为精准的定位值,但是定位的波动性极大,且不易收敛. 而本文提出的融合集成学习的TDOA定位方法可以将误差过大的TDOA值修正,克服了对比方法在NLOS下定位失准的缺点,在非视距情况下可以得到鲁棒性较高的定位结果.
为了验证文中提到的方法在不同环境下的鲁棒性和实际效果,我们在3个不同尺寸的场景中进行了实验. 具体场景尺寸如下:30m×30m(场景1)、20 m×20 m(场景2)以及6.5 m×7.2 m(场景3). 这3个场景在尺寸、构成材料、非视距遮挡物及其声学特性方面存在显著差异. 场景1(某电子研究所试验场)具有较大空间、高电子干扰和金属反射,以及金属板遮挡物,导致强烈的声波反射和混响. 场景2(某无人机试验场)较小,主要由海绵和纸壳组成,吸音性能较好,以人体为主要遮挡物,影响声波散射和吸收. 场景3(某研究院办公室)是一个更小的室内空间,以具有多样化的物体和材料,以及安全帽作为遮挡物,可能导致不规则反射和较大混响. 这些差异对超声波定位系统的性能产生直接影响,尤其是在定位精度和效率方面. 在这些实验中,采用了自主研发的近超声定位基站. 该基站使用Chirp信号进行通信,其时序时间为40 ms,频率带宽范围为19~21 kHz. 在接收端,我们采用了自研的近超声波定位标签,其主控制器为STM32F103,这使得它能够实时进行信号处理和计算. 本文中使用了LLCC68芯片的LoRa模组,并结合了我们自主研发的同步算法,以实现基站之间以及基站与定位标签之间的近超声波信号同步. 这种同步确保了在采用时间到达算法进行距离估计时标准时间的准确性. 值得一提的是,基站之间以及基站与定位标签之间的同步误差控制在了8.5 μm以内. 的在定位过程中,到达时间的真值是通过激光测距仪标定得到的. 在每一个场景中,基站被放置于场景的4个固定点. 为了模拟非视距条件,每次实验都会将其中1个基站设置为非视距状态,并通过障碍物来实现非视距测距. 标签的坐标分别设置为(20, 20),(15, 15),(1.4, 0.5),并在对应的定位点上采集数据点. 实验设备如图13所示. 通过在这个实验环境中进行验证,可以对所提出的方法进行有效性和准确性的评估.
在获得TOA值后,将这些实验数据输入已经预训练好的集成模型中,以估算目标位置. 为了更直观地体现本文方法的优势,在定位实验中将其与Chan方法[43]、Taylor方法[44-46]进行了对照比较. 对于求解出包含复数解的Chan方法和Taylor方法,仅取求解结果的实数部分. 场景1和场景2的定位效果如图14和图15所示. 经过结果比对,相对于传统的定位策略,本文方法在定位精度上显现出了明显的优势.
场景3的定位效果如图16和图17所示. 此时由于空间较小且定位点位过于接近主基站,Chan [43]方法、Taylor[44-46]方法均无法实时定位出点数. 而本文所提方法依然可以实现高精度的室内定位. 表4详细列出了在3种不同场景下的误差统计数据,涵盖了各种定位方法的平均误差、标准差、最大误差、最小误差以及误差的95%和50%分位数. 通过这些数据,可以清楚地观察到本文方法在各项统计指标上均优于参考的对比方法. 具体来说,与Chan方法[43]、Taylor方法[44-46]相比,在场景1,本文方法的性能提高了93%和55%. 在场景2,本文方法性能提升分别为93%和55%. 而在场景3,本文方法相对于上述2种方法,性能均得到了96.5%的显著提升.
图18 呈现了3种不同场景下定位方法的计算时间箱型图. 可发现,该方法的计算时间中位数约为26.5 ms. 尽管本文方法的结构和超参数优化相对复杂,但其计算效率仍然显著.
本文提出了一种基于融合集成学习的近超声室内定位方法. 该方法采用改进的TOA检测方法和改进的TDOA方法,同时结合室内空间的实际场景,解决了传统定位手段和定位方法在多径和NLOS情况下不适用的问题,适用于室内的人员和设备定位.
然而,该方法的训练时间和超参数优化所需时间较长,仿真和实验场景过于单一不够多样. 硬件平台还未能完全应用增强测距方法. 该方法可以进一步优化,以弥补技术上的不足.
作者贡献声明:贾乃征提出了方法思路和仿真方案,并撰写了论文;薛灿提供实验器材并负责修改论文;杨骝和王智提出指导意见并修改论文.

参考文献 引证文献
排序方式:
1
Obeidat H, Shuaieb W, Obeidat O, et al. A review of indoor localization techniques and wireless technologies[J]. Wireless Personal Communications, 2021, 119: 289−327
2
Zhang Lan, Liu Kebin, Jiang Yonghang, et al. Montage: Combine frames with movement continuity for realtime multi-user tracking[J]. IEEE Transactions on Mobile Computing, 2017, 16(4): 1019−1031
3
薛灿,韩强,王智. 基于信号统计模型的变电站半遮挡融合定位方法[J]. 电力工程技术,2023,42(1):185−192
Xue Can, Han Qiang, Wang Zhi. Semi-occlusion substation fusion positioning method based on multi-sensor signal statistical model[J]. Electric Power Engineering Technology, 2023, 42(1): 185−192 (in Chinese)
4
Cheng Sisi, Wang Feng, Li Guangcai, et al. Single-frequency multi-GNSS PPP-RTK for smartphone rapid centimeter-level positioning[J]. IEEE Sensors Journal, 2023, 23(18): 21553−21561
5
Jia Naizheng, Shu Haoran, Wang Xinheng, et al. Smartphone-based social distance detection technology with near-ultrasonic signal[J]. Sensors, 2022, 22(19): 7345−7375
6
Zou Han, Zhou Yuxun, Yang Jianfei, et al. Unsupervised WIFI-enabled IOT device-user association for personalized location-based service[J]. IEEE Internet of Things Journal, 2019, 6(1): 1238−1245
7
Shi Lina, Shi Dayu, Zhang Xun, et al. 5G Internet of radio light positioning system for indoor broadcasting service[J]. IEEE Transactions on Broadcasting, 2020, 66(2): 534−544
8
AlHory O, Shoushara O, Al Suri H, et al. 5G mmwave indoor location identification using beamforming and RSSI[C]//Proc of the 11th Int Conf on Information and Communication Systems (ICICS). Piscataway, NJ: IEEE, 2020: 91−95
9
Deng Zhongliang, Zheng Xinyu, Zhang Chongyu, et al. A TDOA and PDR fusion method for 5G indoor localization based on virtual base stations in unknown areas[J]. IEEE Access, 2020, 8: 225123−225133
10
Yu Yue, Chen Ruizhi, Chen Liang, et al. A novel 3-D indoor localization algorithm based on BLE and multiple sensors[J]. IEEE Internet of Things Journal, 2021, 8(11): 9359−9372
11
You Yuan, Wu Chang. Hybrid indoor positioning system for pedestrians with swinging arms based on smartphone IMU and RSSI of BLE[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1−15
12
Rahman M, Haider A, Naghshvarianjahromi M. A systematic methodology for the time-domain ringing reduction in UWB band-notched antennas[J]. IEEE Antennas and Wireless Propagation Letters, 2020, 19(3): 482−486
13
Bao Dongxuan, Zou Zhuo, Nejad M, et al. A wirelessly powered UWB RFID sensor tag with time-domain analog-to-information interface[J]. IEEE Journal of Solid-State Circuits, 2018, 53(8): 2227−2239
14
Sharma S, Deka K, Mandloi M. Deep learning noncoherent UWB receiver design[J]. IEEE Sensors Letters, 2021, 5(6): 1−4
15
Liu Manni, Cheng Linsong, Qian Kun, et al. Indoor acoustic localization: A survey[J]. Human-centric Computing and Information Sciences, 2020, 10(1): 1−24
16
Albuquerque D, Vieira J, Lopes S, et al. Indoor acoustic simulator for ultrasonic broadband signals with doppler effect[J]. Applied Acoustics, 2015, 97: 140−151
17
Gualda D, Perez-Rubio M, Urena J, et al. Locate-us: Indoor positioning for mobile devices using encoded ultrasonic signals, inertial sensors and graph-matching[J]. Sensors, 2021, 21(6): 1950−1973
18
Dubey A, Sood P, Santos J, et al. An enhanced approach to imaging the indoor environment using WIFI RSSI measurements[J]. IEEE Transactions on Vehicular Technology, 2021, 70(9): 8415−8430
19
Zafari F, Gkelias A, Leung K. A survey of indoor localization systems and technologies[J]. IEEE Communications Surveys & Tutorials, 2019, 21(3): 2568−2599
20
Zhang Ji, Singh S. Loam: Lidar odometry and mapping in real-time[J]. Robotics: Science and Systems, 2014, 2(9): 1−9
21
Cai Chao, Hu Menglan, Cao Doudou, et al. Self-deployable indoor localization with acoustic-enabled IoT devices exploiting participatory sensing[J]. IEEE Internet of Things Journal, 2019, 6(3): 5297−5311
22
Huang Wenchao, Xiong Yan, Li Xiangyang, et al. Swadloon: Direction finding and indoor localization using acoustic signal by shaking smartphones[J]. IEEE Transactions on Mobile Computing, 2014, 14(10): 2145−2157
23
Yang Lingyu, Feng Xiaoke, Zhang Jing, et al. Multi-ray modeling of ultrasonic sensors and application for micro-UAV localization in indoor environments[J]. Sensors, 2019, 19(8): 1770−1787
24
Höflinger F, Zhang Rui, Hoppe J, et al. Acoustic self-calibrating system for indoor smartphone tracking (ASSIST)[C/OL]//Proc of the 1st Int Conf on Indoor Positioning and Indoor Navigation (IPIN). Piscataway, NJ: IEEE, 2012 [2024-04-22]. https://ieeexplore.ieee.org/document/6418877
25
Höflinger F, Bordoy J, Simon N, et al. Indoor-localization system for smart phones[C/OL]//Proc of the 3rd IEEE Int Workshop on Measurements & Networking (M&N). Piscataway, NJ: IEEE, 2015 [2024-04-22]. https://ieeexplore.ieee.org/document/7322974/
26
Prieto J, Jiménez A, Guevara J, et al. Performance evaluation of 3D-locus advanced acoustic LPS[J]. IEEE Transactions on Instrumentation and Measurement, 2009, 58(8): 2385−2395
27
Sertatıl C, Altınkaya M, Raoof K. A novel acoustic indoor localization system employing CDMA[J]. Digital Signal Processing, 2012, 22(3): 506−517
28
Liu Kaikai, Liu Xinxin, Li Xiaolin. Guoguo: Enabling fine-grained smartphone localization via acoustic anchors[J]. IEEE Transactions on Mobile Computing, 2016, 15(5): 1144−1156
29
Liu Zuoya, Chen Ruizhi, Ye Feng, et al. Improved TOA estimation method for acoustic ranging in a reverberant environment[J]. IEEE Sensors Journal, 2020, 22(6): 4844−4852
30
Cao Shuai, Chen Xiang, Zhang Xu, et al. Effective audio signal arrival time detection algorithm for realization of robust acoustic indoor positioning[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(10): 7341−7352
31
Peng Chunyi, Shen Guobin, Zhang Yongguang. Beepbeep: A high-accuracy acoustic-based system for ranging and localization using cots devices[J]. ACM Transactions on Embedded Computing Systems, 2012, 11(1): 1−29
32
Zhang Lei, Chen Minlin, Wang Xinheng, et al. TOA estimation of chirp signal in dense multipath environment for low-cost acoustic ranging[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 68(2): 355−367
33
Mao Wenguang, He Jian, Qiu Lili. Cat: High-precision acoustic motion tracking[C]//Proc of the 22nd Annual Int Conf on Mobile Computing and Networking. New York: ACM, 2016: 69−81
34
Liu Yunhao, Wang Jiliang, Zhang Yunting, et al. Vernier: Accurate and fast acoustic motion tracking using mobile devices[J]. IEEE Transactions on Mobile Computing, 2019, 20(2): 754−764
35
Wang Wei, Liu A, Sun Ke. Device-free gesture tracking using acoustic signals[C]//Proc of the 22nd Annual Int Conf on Mobile Computing and Networking. New York: ACM, 2016: 82−94
36
Lin Xinchuang, Chen Ruizhi, Huang Lixiong, et al. Chirptracker: A precise-location-aware system for acoustic tag using single smartphone[J]. IEEE Internet of Things Journal, 2023, 11(1): 848−862
37
Wang Hucheng, Xue Can, Wang Zhi, et al. Smartphone-based pedestrian NLOS positioning based on acoustics and IMU parameter estimation[J]. IEEE Sensors Journal, 2022, 22(23): 23095−23108
38
Wang Hucheng, Wang Zhi, Zhang Lei, et al. A highly stable fusion positioning system of smartphone under NLOS acoustic indoor environment[J]. ACM Transactions on Internet Technology, 2023, 23(2): 1−19
39
Cai Chao, Zheng Rong, Li Jun, et al. Asynchronous acoustic localization and tracking for mobile targets[J]. IEEE Internet of Things Journal, 2020, 7(2): 830−845
40
Ji Cheng, Chen Minlin, Sun Peng, et al. An encoding and decoding scheme for long-distance ultrasonic localization[C]//Proc of the 39th Chinese Control Conf (CCC). Piscataway, NJ: IEEE, 2020: 5247−5252
41
Li Zheng, Chen Ruizhi, Guo Guangyi, et al. Dual-step acoustic chirp signals detection using pervasive smartphones in multipath and NLOS indoor environments[J]. IEEE Internet of Things Journal, 2023, 11(4): 6494−6507
42
Jia Naizheng, Cui Weimeng, Wang Yuwei, et al. Robust acoustic TOA estimation based on multipath extraction in frequency domain[C/OL]//Proc of the 13th Int Conf on Indoor Positioning and Indoor Navigation (IPIN). Piscataway, NJ: IEEE, 2023 [2024-04-22]. https://ieeexplore.ieee.org/document/10332467/
43
Chan Y, Ho K. A simple and efficient estimator for hyperbolic location[J]. IEEE Transactions on Signal Processing, 1994, 42(8): 1905−1915
44
Xiong Jinyu, Wang Wei, Zhu Zhongliang. A new TDOA algorithm based on Taylor series expansion in cellular networks[J]. Journal of China Institute of Communications, 2004, 25(4): 144−150
45
Hua Cheng, Zhao Kun, Dong Danan, et al. Multipath map method for tdoa based indoor reverse positioning system with improved Chan-Taylor algorithm[J]. Sensors, 2020, 20(11): 3223−3238
46
Zang Lan, Shen Chong, Zhang Kun, et al. Research on hybrid algorithm based on TDOA[C]//Proc of the 20th IEEE Int Conf on Communication Technology (ICCT). Piscataway, NJ: IEEE, 2020: 539−542
47
黄冬梅,张宁宁,胡安铎,等. 基于双层Xgboost和数据增强的空间负荷预测方法[J]. 电力工程技术,2023,42(1):201−208
Huang Dongmei, Zhang Ningning, Hu Anduo. Spatial load forecasting method based on double-layer Xgboost and data enhancement[J]. Electric Power Engineering Technology, 2023, 42(1): 201−208 (in Chinese)
48
Chen Tianqi, Guestrin C. Xgboost: A scalable tree boosting system[C]//Proc of the 22nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2016: 785–794
49
Yang Jinshan, Zhao Chenyue, Yu Haotong, et al. Use GBDT to predict the stock market[J]. Procedia Computer Science, 2020, 174: 161−171
50
Ke Guolin, Meng Qi, Finley T, et al. LightGBM: A highly efficient gradient boosting decision tree[C]//Proc of the 31st Int Conf on Neural Information Processing Systems. New York: ACM, 2017: 3149−3157
51
李丽颖,张润泽,魏同权. 面向边缘计算的服务解耦与部署策略[J]. 计算机研究与发展,2023,60(5):1073−1085
Li Liying, Zhang Runze, Wei Tongquan. Service decoupling and deployment strategies for edge computing[J]. Journal of Computer Research and Development, 2023, 60(5): 1073−1085 (in Chinese)
52
Qu Yi, Lin Zhengkui, Li Honglei, et al. Feature recognition of urban road traffic accidents based on GA-Xgboost in the context of big data[J]. IEEE Access, 2019, 7: 170106−170115
53
严忻恺,霍宇驰,鲍虎军. 神经渲染及其硬件加速综述[J]. 计算机研究与发展,2024,61(11):2846−2869
Yan Xinkai, Huo Yuchi, Bao Hujun. Survey on neural rendering and its hardware acceleration[J]. Journal of Computer Research and Development, 2024,61(11):2846−2869 (in Chinese)
2025年第62卷第2期
115
55
0
引用本文
BibTeX
文章信息
doi: 10.7544/issn1000-1239.202330882
  • 接收时间:2023-10-31
  • 首发时间:2026-11-10
  • 出版时间:2025-02-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-10-31
  • 修回日期:2024-04-26
  • 录用日期:2024-05-24
基金
作者信息
    浙江大学控制科学与工程学院 杭州 310013

通讯作者:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202330882
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