Article(id=1251458158766535421, tenantId=1146029695717560320, journalId=1251194880429441115, issueId=1251458153020342360, articleNumber=null, orderNo=null, doi=10.3979/j.issn.1673-825X.202501180025, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1737129600000, receivedDateStr=2025-01-18, revisedDate=1757433600000, revisedDateStr=2025-09-10, acceptedDate=null, acceptedDateStr=null, onlineDate=1776300476018, onlineDateStr=2026-04-16, pubDate=null, pubDateStr=null, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1776300476018, onlineIssueDateStr=2026-04-16, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1776300476018, creator=13041195026, updateTime=1776300476018, updator=13041195026, issue=Issue{id=1251458153020342360, tenantId=1146029695717560320, journalId=1251194880429441115, year='2025', volume='37', issue='5', pageStart='627', pageEnd='780', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1776300474648, creator=13041195026, updateTime=1776311939434, updator=13041195026, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1251506239914586238, tenantId=1146029695717560320, journalId=1251194880429441115, issueId=1251458153020342360, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1251506239914586239, tenantId=1146029695717560320, journalId=1251194880429441115, issueId=1251458153020342360, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=627, endPage=637, ext={EN=ArticleExt(id=1251458159131439883, articleId=1251458158766535421, tenantId=1146029695717560320, journalId=1251194880429441115, language=EN, title=Research on BLE and PDR fusion localization method based on ranging correction, columnId=1251458153846620250, journalTitle=Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), columnName=New-Generation Mobile Communication, runingTitle=null, highlight=null, articleAbstract=

To address the significant decline in positioning accuracy of traditional algorithms under indoor non line of sight(NLOS)conditions and low beacon deployment density, this paper proposes a fused positioning method based on ranging correction, combining bluetooth low energy(BLE)and pedestrian dead reckoning(PDR). Firstly, the received signal strength(RSS)of BLE is rapidly constructed using SketchUp indoor 3D modeling software integrated with a ray-tracing algorithm, eliminating the need for tedious manual RSS field collection. Subsequently, a variational autoencoder based on convolutional neural network(VAE-CNN)is designed to predict and correct BLE ranging errors, thereby improving BLE positioning accuracy. Finally, an extended Kalman filter(EKF)is employed to fuse the positioning results from BLE and PDR. Experimental results demonstrate that the proposed ranging-corrected BLE positioning and EKF-based fusion positioning achieve superior performance in environments with NLOS interference and low beacon deployment density.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Hui LIU, Hangchuan HE), CN=ArticleExt(id=1251458171995369683, articleId=1251458158766535421, tenantId=1146029695717560320, journalId=1251194880429441115, language=CN, title=基于测距修正的BLE和PDR融合定位方法研究, columnId=1251458154026975325, journalTitle=重庆邮电大学学报(自然科学版), columnName=新一代移动通信, runingTitle=null, highlight=null, articleAbstract=

为解决室内非视距(non line of sight,NLOS)环境以及低信标部署密度下传统定位算法精度急剧下降的问题,提出一种基于测距修正的低功耗蓝牙(bluetooth low energy,BLE)和行人航位推算(pedestrian dead reckoning,PDR)融合定位方法。通过SketchUp室内3D建模软件联合射线追踪算法实现BLE的接收信号强度(received signal strength,RSS)快速构建,避免人工繁琐的RSS实地采集。设计一种基于卷积神经网络的变分自编码器(variational autoencoder based on convolution neural network,VAE-CNN)模型对BLE测距误差进行预测和修正,提升BLE定位精度。采用扩展卡尔曼滤波(extended Kalman filter,EKF)融合BLE和PDR的定位结果。实验结果表明,采用测距修正后的BLE测距定位以及EKF融合定位在NLOS以及信标部署密度低的环境下具有较好的定位性能。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
何航川
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=m7xxkPnFcYUnB4ZaBd37PA==, magXml=SVC+mXCLJmCBKTXs9loI5A==, pdfUrl=null, pdf=heBe2tEj8nZCpINpCdOXZg==, pdfFileSize=12636842, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Ch//cFgk7cTMFIPY7A+xXw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=BpfsCjQ+VA/DbFc7xTZdUA==, mapNumber=null, authorCompany=null, fund=null, authors=

刘辉,正高级工程师,硕士,主要研究方向为目标检测、深度学习、室内定位。E-mail:

何航川,硕士研究生,主要研究方向为深度学习、室内定位。E-mail:

, authorsList=刘辉, 何航川)}, authors=[Author(id=1251458172330914023, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liuhui@cqcyit.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251458172427383019, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, authorId=1251458172330914023, language=EN, stringName=Hui LIU, firstName=Hui, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, P R China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251458172511269102, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, authorId=1251458172330914023, language=CN, stringName=刘辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=重庆邮电大学 通信与信息工程学院,重庆 400065, bio={"content":"

刘辉,正高级工程师,硕士,主要研究方向为目标检测、深度学习、室内定位。E-mail:

"}, bioImg=null, bioContent=

刘辉,正高级工程师,硕士,主要研究方向为目标检测、深度学习、室内定位。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251458172242833632, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, xref=null, ext=[AuthorCompanyExt(id=1251458172251222241, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, companyId=1251458172242833632, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, P R China), AuthorCompanyExt(id=1251458172255416546, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, companyId=1251458172242833632, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=重庆邮电大学 通信与信息工程学院,重庆 400065)])]), Author(id=1251458172599349491, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hangchuan_he@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251458174214156538, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, authorId=1251458172599349491, language=EN, stringName=Hangchuan HE, firstName=Hangchuan, middleName=null, lastName=HE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, P R China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251458174319014142, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, authorId=1251458172599349491, language=CN, stringName=何航川, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=重庆邮电大学 通信与信息工程学院,重庆 400065, bio={"content":"

何航川,硕士研究生,主要研究方向为深度学习、室内定位。E-mail:

"}, bioImg=null, bioContent=

何航川,硕士研究生,主要研究方向为深度学习、室内定位。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251458172242833632, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, xref=null, ext=[AuthorCompanyExt(id=1251458172251222241, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, companyId=1251458172242833632, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, P R China), AuthorCompanyExt(id=1251458172255416546, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, companyId=1251458172242833632, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=重庆邮电大学 通信与信息工程学院,重庆 400065)])])], keywords=[Keyword(id=1251458174432260355, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, orderNo=1, keyword=bluetooth low energy), Keyword(id=1251458174545506569, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, orderNo=2, keyword=pedestrian dead reckoning), Keyword(id=1251458174625198351, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, orderNo=3, keyword=ray tracing), Keyword(id=1251458174713278738, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, orderNo=4, keyword=variational autoencoder), Keyword(id=1251458174809747737, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, orderNo=5, keyword=extended Kalman filter), Keyword(id=1251458174889439514, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, orderNo=1, keyword=低功耗蓝牙), Keyword(id=1251458174969131295, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, orderNo=2, keyword=行人航位推算), Keyword(id=1251458175032045856, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, orderNo=3, keyword=射线追踪), Keyword(id=1251458175141097765, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, orderNo=4, keyword=变分自编码器), Keyword(id=1251458175212400936, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, orderNo=5, keyword=扩展卡尔曼滤波)], refs=[Reference(id=1251458180199428569, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=KOUASSI H K W, STIENNE G, REBOUL S, journalName=null, refType=null, unstructuredReference=KOUASSI H K W, STIENNE G, REBOUL S. GNSS phase positioning without ambiguity resolution[C]//2024 International Conference on Localization and GNSS (ICL-GNSS). Antwerp, Belgium: IEEE, 2024: 1-7., articleTitle=GNSS phase positioning without ambiguity resolution, refAbstract=null), Reference(id=1251458180283314656, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2023, volume=10, issue=17, pageStart=15632, pageEnd=15641, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=XU Y, SHMALIY Y S, BI S, journalName=IEEE Internet of Things Journal, refType=null, unstructuredReference=XU Y, SHMALIY Y S, BI S, et al. Extended Kalman/UFIR filters for UWB-based indoor robot localization under time-varying colored measurement noise[J]. IEEE Internet of Things Journal,2023,10(17):15632-15641., articleTitle=Extended Kalman/UFIR filters for UWB-based indoor robot localization under time-varying colored measurement noise, refAbstract=null), Reference(id=1251458180379783653, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1087, pageEnd=1092, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=QI H, SONG X, ZHANG Y, journalName=null, refType=null, unstructuredReference=QI H, SONG X, ZHANG Y, et al. Multi-scale sensing network for WiFi Indoor localization[C]//2023 IEEE 23rd International Conference on Communication Technology(ICCT).Wuxi,China:IEEE,2023:1087-1092., articleTitle=Multi-scale sensing network for WiFi Indoor localization, refAbstract=null), Reference(id=1251458180472058347, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=24, pageStart=30728, pageEnd=30738, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=GUO G, CHEN R, YAN K, journalName=IEEE Sensors Jour nal, refType=null, unstructuredReference=GUO G, CHEN R, YAN K, et al. Multi-channel and multi-RSS based BLE range estimation for indoor tracking of commercial smartphones[J]. IEEE Sensors Jour nal, 2023, 23(24): 30728-30738., articleTitle=Multi-channel and multi-RSS based BLE range estimation for indoor tracking of commercial smartphones, refAbstract=null), Reference(id=1251458180576915952, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=7, pageStart=7130, pageEnd=7141, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=SUN M, WANG Y, JOSEPH W, journalName=IEEE Sensors Journal, refType=null, unstructuredReference=SUN M, WANG Y, JOSEPH W, et al. Indoor localization using mind evolutionary algorithm-based geomagnetic positioning and smartphone IMU sensors[J]. IEEE Sensors Journal, 2022, 22(7): 7130-7141., articleTitle=Indoor localization using mind evolutionary algorithm-based geomagnetic positioning and smartphone IMU sensors, refAbstract=null), Reference(id=1251458180685967861, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2014, volume=15, issue=6, pageStart=2615, pageEnd=2629, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=ROSE C, BRITT J, ALLEN J, journalName=IEEE Transactions on Intelligent Transportation Systems, refType=null, unstructuredReference=ROSE C, BRITT J, ALLEN J, et al. An integrated vehicle navigation system utilizing lane-detection and lateral position estimation systems in difficult environments for GPS[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(6): 2615-2629., articleTitle=An integrated vehicle navigation system utilizing lane-detection and lateral position estimation systems in difficult environments for GPS, refAbstract=null), Reference(id=1251458180786631161, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2020, volume=69, issue=4, pageStart=4340, pageEnd=4352, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=WEN K, YU K, LI Y, journalName=IEEE Transactions on Vehicular Technology, refType=null, unstructuredReference=WEN K, YU K, LI Y, et al. A new quaternion Kalman filter based foot-mounted IMU and UWB tightly-coupled method for indoor pedestrian navigation[J]. IEEE Transactions on Vehicular Technology, 2020, 69(4): 4340-4352., articleTitle=A new quaternion Kalman filter based foot-mounted IMU and UWB tightly-coupled method for indoor pedestrian navigation, refAbstract=null), Reference(id=1251458180908265981, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=4, pageStart=3062, pageEnd=3073, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=TAO Y, ZHAO L, journalName=IEEE Internet of Things Journal, refType=null, unstructuredReference=TAO Y, ZHAO L. AIPS: An accurate indoor positioning system with fingerprint map adaptation[J]. IEEE Internet of Things Journal, 2021, 9(4): 3062-3073., articleTitle=AIPS: An accurate indoor positioning system with fingerprint map adaptation, refAbstract=null), Reference(id=1251458181034095103, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=12, pageStart=12152, pageEnd=12162, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=LAN T, WANG X, CHEN Z, journalName=IEEE Sensors Journal, refType=null, unstructuredReference=LAN T, WANG X, CHEN Z, et al. Fingerprint augment based on super-resolution for WiFi fingerprint based indoor localization[J]. IEEE Sensors Journal, 2022, 22(12): 12152-12162., articleTitle=Fingerprint augment based on super-resolution for WiFi fingerprint based indoor localization, refAbstract=null), Reference(id=1251458181097009665, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2016, volume=66, issue=1, pageStart=763, pageEnd=776, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=WANG X, GAO L, MAO S, journalName=IEEE Transactions on Vehicular Technology, refType=null, unstructuredReference=WANG X, GAO L, MAO S, et al. CSI-based fingerprinting for indoor localization: A deep learning approach[J]. IEEE Transactions on Vehicular Technology, 2016, 66(1): 763-776., articleTitle=CSI-based fingerprinting for indoor localization: A deep learning approach, refAbstract=null), Reference(id=1251458181176701446, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=17, pageStart=37, pageEnd=42, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=刘宇, 李汪润, 陈燕苹, journalName=电子测量技术, refType=null, unstructuredReference=刘宇,李汪润,陈燕苹.基于自适应峰值检测的PDR算法研究[J].电子测量技术, 2023, 46(17): 37-42., articleTitle=基于自适应峰值检测的PDR算法研究, refAbstract=null), Reference(id=1251458181256393225, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=17, pageStart=37, pageEnd=42, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=LIU Y, LI W R, CHEN Y P, journalName=Electronic Measurement Technology, refType=null, unstructuredReference=LIU Y, LI W R, CHEN Y P. Research on PDR algorithm based on adaptive peak detection[J]. Electronic Measurement Technology, 2023, 46(17): 37-42., articleTitle=Research on PDR algorithm based on adaptive peak detection, refAbstract=null), Reference(id=1251458181336085006, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2016, volume=12, issue=4, pageStart=1540, pageEnd=1549, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=CHEN Z, ZHU Q, SOH Y C, journalName=IEEE Transactions on Industrial Informatics, refType=null, unstructuredReference=CHEN Z, ZHU Q, SOH Y C. Smartphone inertial sensor-based indoor localization and tracking with iBeacon corrections[J]. IEEE Transactions on Industrial Informatics, 2016, 12(4): 1540-1549., articleTitle=Smartphone inertial sensor-based indoor localization and tracking with iBeacon corrections, refAbstract=null), Reference(id=1251458181419971089, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2023, volume=26, issue=3, pageStart=480, pageEnd=495, url=null, language=null, rfNumber=[13], rfOrder=13, authorNames=WU Y, CHEN R, FU W, journalName=Geo-spatial Information Science, refType=null, unstructuredReference=WU Y, CHEN R, FU W, et al. Indoor positioning based on tightly coupling of PDR and one single Wi-Fi FTM AP[J]. Geo-spatial Information Science, 2023, 26(3):480-495., articleTitle=Indoor positioning based on tightly coupling of PDR and one single Wi-Fi FTM AP, refAbstract=null), Reference(id=1251458181499662870, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=13, pageStart=4390, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=14, authorNames=YUAN D, ZHANG J, WANG J, journalName=Sensors, refType=null, unstructuredReference=YUAN D, ZHANG J, WANG J, et al. Robustly adaptive EKF PDR/UWB integrated navigation based on additional heading constraint[J]. Sensors, 2021, 21(13):4390., articleTitle=Robustly adaptive EKF PDR/UWB integrated navigation based on additional heading constraint, refAbstract=null), Reference(id=1251458183110275609, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2017, volume=6, issue=7, pageStart=214, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=15, authorNames=ZHANG X, CHEN Y, YU L, journalName=ISPRS International Journal of Geo-Information, refType=null, unstructuredReference=ZHANG X, CHEN Y, YU L, et al. Three-dimensional modeling and indoor positioning for urban emergency response[J]. ISPRS International Journal of Geo-Information, 2017, 6(7): 214., articleTitle=Three-dimensional modeling and indoor positioning for urban emergency response, refAbstract=null), Reference(id=1251458183198355996, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2015, volume=3, issue=null, pageStart=1089, pageEnd=1100, url=null, language=null, rfNumber=[16], rfOrder=16, authorNames=YUN Z, ISKANDER M F, journalName=IEEE access, refType=null, unstructuredReference=YUN Z, ISKANDER M F. Ray tracing for radio propagation modeling: Principles and applications[J]. IEEE access, 2015, 3: 1089-1100., articleTitle=Ray tracing for radio propagation modeling: Principles and applications, refAbstract=null), Reference(id=1251458183269659165, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2018, volume=21, issue=1, pageStart=10, pageEnd=27, url=null, language=null, rfNumber=[17], rfOrder=17, authorNames=HE D, AI B, GUAN K, journalName=IEEE Communications Surveys & Tutorials, refType=null, unstructuredReference=HE D, AI B, GUAN K,et al. The design and applications of high-performance ray-tracing simulation platform for 5G and beyond wireless communications: A tutorial[J]. IEEE Communications Surveys & Tutorials, 2018, 21(1): 10-27., articleTitle=The design and applications of high-performance ray-tracing simulation platform for 5G and beyond wireless communications: A tutorial, refAbstract=null), Reference(id=1251458183382905380, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2024, volume=56, issue=10, pageStart=1, pageEnd=40, url=null, language=null, rfNumber=[18], rfOrder=18, authorNames=LIANG S, PAN Z, LIU W, journalName=ACM Computing Surveys, refType=null, unstructuredReference=LIANG S, PAN Z, LIU W, et al. A survey on variational autoencoders in recommender systems[J]. ACM Computing Surveys, 2024, 56(10): 1-40., articleTitle=A survey on variational autoencoders in recommender systems, refAbstract=null), Reference(id=1251458183466791462, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2021, volume=10, issue=20, pageStart=2470, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=19, authorNames=BHATT D, PATEL C, TALSANIA H, journalName=Electronics, refType=null, unstructuredReference=BHATT D, PATEL C, TALSANIA H,et al. CNN variants for computer vision: History, architecture, application, challenges and future scope[J]. Electronics, 2021, 10(20): 2470., articleTitle=CNN variants for computer vision: History, architecture, application, challenges and future scope, refAbstract=null), Reference(id=1251458183550677544, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2020, volume=27, issue=5, pageStart=909, pageEnd=913, url=null, language=null, rfNumber=[20], rfOrder=20, authorNames=田昕, 魏国亮, 王建华, journalName=控制工程, refType=null, unstructuredReference=田昕,魏国亮,王建华,.NLOS环境下的改进EKF定位算法研究[J].控制工程, 2020, 27(5): 909-913., articleTitle=NLOS环境下的改进EKF定位算法研究, refAbstract=null), Reference(id=1251458183630369324, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2020, volume=27, issue=5, pageStart=909, pageEnd=913, url=null, language=null, rfNumber=[20], rfOrder=21, authorNames=TIAN X, WEI G L, WANG J H, journalName=Control Engineering of China, refType=null, unstructuredReference=TIAN X, WEI G L, WANG J H, et al. Research on improved EKF localization algorithm under NLOS environment[J]. Control Engineering of China, 2020, 27(5):909-913., articleTitle=Research on improved EKF localization algorithm under NLOS environment, refAbstract=null), Reference(id=1251458183714255403, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2007, volume=57, issue=1, pageStart=140, pageEnd=149, url=null, language=null, rfNumber=[21], rfOrder=22, authorNames=EL-SHEIMY N, HOU H, NIU X, journalName=IEEE Transactions on Instrumentation and Measurement, refType=null, unstructuredReference=EL-SHEIMY N, HOU H, NIU X. Analysis and modeling of inertial sensors using Allan variance[J]. IEEE Transactions on Instrumentation and Measurement, 2007, 57(1): 140-149., articleTitle=Analysis and modeling of inertial sensors using Allan variance, refAbstract=null), Reference(id=1251458183798141485, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=144, pageStart=334, pageEnd=341, url=null, language=null, rfNumber=[22], rfOrder=23, authorNames=LANDI F, BARALDI L, CORNIA M, journalName=Neural Networks, refType=null, unstructuredReference=LANDI F, BARALDI L, CORNIA M, et al. Working memory connections for LSTM[J]. Neural Networks, 2021(144): 334-341, articleTitle=Working memory connections for LSTM, refAbstract=null), Reference(id=1251458183882027568, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2022, volume=9, issue=22, pageStart=22582, pageEnd=22594, url=null, language=null, rfNumber=[23], rfOrder=24, authorNames=NGAMAKEUR K, YONGCHAREON S, YU J, journalName=IEEE Internet of Things Journal, refType=null, unstructuredReference=NGAMAKEUR K, YONGCHAREON S, YU J, et al. Deep CNN-LSTM network for indoor location estimation using analog signals of passive infrared sensors[J]. IEEE Internet of Things Journal, 2022, 9(22): 22582-22594., articleTitle=Deep CNN-LSTM network for indoor location estimation using analog signals of passive infrared sensors, refAbstract=null), Reference(id=1251458183965913654, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[24], rfOrder=25, authorNames=RAFIQUE H, PATTI D, PALESI M, journalName=null, refType=null, unstructuredReference=RAFIQUE H, PATTI D, PALESI M, et al. Fusing visuals with magnetic signals to improve indoor localization using vision transformer[C]//2024 14th International Conference on Indoor Positioning and Indoor Navigation (IPIN). Kowloon, Hong Kong, China:IEEE,2024:1-6., articleTitle=Fusing visuals with magnetic signals to improve indoor localization using vision transformer, refAbstract=null), Reference(id=1251458184062382651, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[25], rfOrder=26, authorNames=RENAUDIN O, ZEMEN T, BURGESS T, journalName=null, refType=null, unstructuredReference=RENAUDIN O, ZEMEN T, BURGESS T. Ray-tracing based fingerprinting for indoor localization[C]//2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). Kalamata, Greece: IEEE, 2018: 1-5., articleTitle=Ray-tracing based fingerprinting for indoor localization, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1251458172242833632, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, xref=null, ext=[AuthorCompanyExt(id=1251458172251222241, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, companyId=1251458172242833632, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, P R China), AuthorCompanyExt(id=1251458172255416546, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, companyId=1251458172242833632, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=重庆邮电大学 通信与信息工程学院,重庆 400065)])], figs=[ArticleFig(id=1251458175359201581, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.1, caption=Framework of BLE and PDR fusion localization algorithm based on ranging error correction, figureFileSmall=XT7duZ4CVn3UvMvD9hzVUg==, figureFileBig=Ch//cFgk7cTMFIPY7A+xXw==, tableContent=null), ArticleFig(id=1251458175455670577, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图1, caption=基于测距误差修正的BLE和PDR融合定位算法框架, figureFileSmall=XT7duZ4CVn3UvMvD9hzVUg==, figureFileBig=Ch//cFgk7cTMFIPY7A+xXw==, tableContent=null), ArticleFig(id=1251458175677968703, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.2, caption=SketchUp interior 3D model, figureFileSmall=YtwKdbgdcD4S6Tsa5/WO8w==, figureFileBig=hqJkARzmRzBYjxJxcq9tNg==, tableContent=null), ArticleFig(id=1251458175753466180, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图2, caption=SketchUp室内3D模型, figureFileSmall=YtwKdbgdcD4S6Tsa5/WO8w==, figureFileBig=hqJkARzmRzBYjxJxcq9tNg==, tableContent=null), ArticleFig(id=1251458175858323789, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.3, caption=Results of ray tracing simulation, figureFileSmall=IVJoO8JwD+MMfugZmbVpNQ==, figureFileBig=iku9h5Ne5oV3nGPrW5Ejcw==, tableContent=null), ArticleFig(id=1251458175938015570, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图3, caption=射线追踪仿真结果, figureFileSmall=IVJoO8JwD+MMfugZmbVpNQ==, figureFileBig=iku9h5Ne5oV3nGPrW5Ejcw==, tableContent=null), ArticleFig(id=1251458176034484573, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.4, caption=VAE module structure diagram, figureFileSmall=b61MC3cLDP7ruyIWTrOyXA==, figureFileBig=8bSigTzqNZmJPTid6K67XQ==, tableContent=null), ArticleFig(id=1251458176130953570, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图4, caption=VAE模块结构图, figureFileSmall=b61MC3cLDP7ruyIWTrOyXA==, figureFileBig=8bSigTzqNZmJPTid6K67XQ==, tableContent=null), ArticleFig(id=1251458176219033960, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.5, caption=Ranging error prediction model based on VAE-CNN, figureFileSmall=P16F7iGePodwEN56Q1cHzg==, figureFileBig=d4lzOXVj97KzB06n85doyw==, tableContent=null), ArticleFig(id=1251458176298725745, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图5, caption=基于VAE-CNN的测距误差预测模型, figureFileSmall=P16F7iGePodwEN56Q1cHzg==, figureFileBig=d4lzOXVj97KzB06n85doyw==, tableContent=null), ArticleFig(id=1251458176365834613, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.6, caption=Experimental environment and floor plan, figureFileSmall=gIuWBCOwCzt1fyKRNeggkA==, figureFileBig=SpYsBdnjKiE0aSKykW6dNw==, tableContent=null), ArticleFig(id=1251458176458109306, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图6, caption=实验环境与场景平面图, figureFileSmall=gIuWBCOwCzt1fyKRNeggkA==, figureFileBig=SpYsBdnjKiE0aSKykW6dNw==, tableContent=null), ArticleFig(id=1251458176554578305, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.7, caption=Ranging measurement error results, figureFileSmall=x4u3ITiegxoCi7kPBvJHIw==, figureFileBig=MLbeQs+wVaUtVuScuqkNlg==, tableContent=null), ArticleFig(id=1251458176625881477, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图7, caption=测距误差结果, figureFileSmall=x4u3ITiegxoCi7kPBvJHIw==, figureFileBig=MLbeQs+wVaUtVuScuqkNlg==, tableContent=null), ArticleFig(id=1251458176718156169, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.8, caption=Comparison results of relative ranging errors, figureFileSmall=SQD8LFROkvx6fBE3LiCH+w==, figureFileBig=eSEKDl4vKRscTexLvAoCaA==, tableContent=null), ArticleFig(id=1251458176818819470, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图8, caption=相对测距误差对比结果, figureFileSmall=SQD8LFROkvx6fBE3LiCH+w==, figureFileBig=eSEKDl4vKRscTexLvAoCaA==, tableContent=null), ArticleFig(id=1251458176885928337, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.9, caption=Obstruction ranging experimental setup, figureFileSmall=HGT8onNHRJDWlOSYpxWxgg==, figureFileBig=wXx1ICkFw8NgmCv1QsSNaw==, tableContent=null), ArticleFig(id=1251458176957231509, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图9, caption=遮挡物测距实验设置, figureFileSmall=HGT8onNHRJDWlOSYpxWxgg==, figureFileBig=wXx1ICkFw8NgmCv1QsSNaw==, tableContent=null), ArticleFig(id=1251458177036923290, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.10, caption=BLE ranging errors with different obstructions, figureFileSmall=h/bcNg64Mtjs5QRJL2IQ8A==, figureFileBig=x8FMJgDllNwJ1Z1iDhEGJQ==, tableContent=null), ArticleFig(id=1251458178643341726, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图10, caption=不同遮挡物的BLE测距误差, figureFileSmall=h/bcNg64Mtjs5QRJL2IQ8A==, figureFileBig=x8FMJgDllNwJ1Z1iDhEGJQ==, tableContent=null), ArticleFig(id=1251458178764976548, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Fig.11, caption=Positioning trajectory and error CDF curve, figureFileSmall=HkA8O/Goe7Phl/HSjJ/VyA==, figureFileBig=saFQyinZQ3suN2ntCFiz9A==, tableContent=null), ArticleFig(id=1251458178907582887, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=图11, caption=定位轨迹及误差CDF曲线, figureFileSmall=HkA8O/Goe7Phl/HSjJ/VyA==, figureFileBig=saFQyinZQ3suN2ntCFiz9A==, tableContent=null), ArticleFig(id=1251458179100520873, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Tab.1, caption=

Electromagnetic parameters of component materials

, figureFileSmall=null, figureFileBig=null, tableContent=
材料相对介电常数εr电导率σ/(S/m
混凝土60.01
石膏板墙40.02
木制品2.10.05
玻璃31×10-9
金属制品11×107
塑料制品21×10-7
), ArticleFig(id=1251458179247321515, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=表1, caption=

元件材料的电磁参数

, figureFileSmall=null, figureFileBig=null, tableContent=
材料相对介电常数εr电导率σ/(S/m
混凝土60.01
石膏板墙40.02
木制品2.10.05
玻璃31×10-9
金属制品11×107
塑料制品21×10-7
), ArticleFig(id=1251458179347984815, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Tab.2, caption=

RT simulation parameters based on BLE signals

, figureFileSmall=null, figureFileBig=null, tableContent=
参数
载波频率fc/GHz2.4
带宽B/MHz2
发射/接收端天线辐射模式全向
最大反射次数3
最大绕射次数2
BLE数据包格式LE1M
符号率/MHz1
采样率/MHz8
BLE数据包长度256
BLE信标输出功率/dBm0
载波频率fc/GHz2.4
), ArticleFig(id=1251458179452842418, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=表2, caption=

基于BLE信号的RT仿真参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数
载波频率fc/GHz2.4
带宽B/MHz2
发射/接收端天线辐射模式全向
最大反射次数3
最大绕射次数2
BLE数据包格式LE1M
符号率/MHz1
采样率/MHz8
BLE数据包长度256
BLE信标输出功率/dBm0
载波频率fc/GHz2.4
), ArticleFig(id=1251458179536728503, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Tab.3, caption=

Hyperparameters of the VAE-CNN

, figureFileSmall=null, figureFileBig=null, tableContent=
超参数参数值
输入尺寸1×6×1
卷积层1×2卷积核,步长为1
维度64
激活函数ReLU
卷积层数量2
优化器Adam
学习率0.001
Dropout比率0.5
批量大小100
训练周期500
), ArticleFig(id=1251458179645780413, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=表3, caption=

VAE-CNN模型超参数

, figureFileSmall=null, figureFileBig=null, tableContent=
超参数参数值
输入尺寸1×6×1
卷积层1×2卷积核,步长为1
维度64
激活函数ReLU
卷积层数量2
优化器Adam
学习率0.001
Dropout比率0.5
批量大小100
训练周期500
), ArticleFig(id=1251458179738055107, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Tab.4, caption=

Positioning performance metrics

, figureFileSmall=null, figureFileBig=null, tableContent=
误差指标RMSESTD
PDR6.832.97
BLE测距10.414.46
BLE指纹7.153.56
EKF4.732.34
测距修正的BLE2.421.53
测距修正的EKF0.810.28
), ArticleFig(id=1251458179805163976, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=表4, caption=

定位性能指标

, figureFileSmall=null, figureFileBig=null, tableContent=
误差指标RMSESTD
PDR6.832.97
BLE测距10.414.46
BLE指纹7.153.56
EKF4.732.34
测距修正的BLE2.421.53
测距修正的EKF0.810.28
), ArticleFig(id=1251458179876467147, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Tab.5, caption=

RMSE metrics for different numbers of beacons

, figureFileSmall=null, figureFileBig=null, tableContent=
RMSE5信标6信标8信标
BLE测距24.3815.7610.41
BLE指纹12.738.547.15
EKF10.466.924.73
测距误差修正的BLE定位4.363.762.42
测距误差修正的EKF定位2.071.230.81
), ArticleFig(id=1251458179947770318, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=表5, caption=

不同信标数量下的RMSE指标

, figureFileSmall=null, figureFileBig=null, tableContent=
RMSE5信标6信标8信标
BLE测距24.3815.7610.41
BLE指纹12.738.547.15
EKF10.466.924.73
测距误差修正的BLE定位4.363.762.42
测距误差修正的EKF定位2.071.230.81
), ArticleFig(id=1251458180014879187, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=EN, label=Tab.6, caption=

STD metrics for different numbers of beacons

, figureFileSmall=null, figureFileBig=null, tableContent=
STD5信标6信标8信标
BLE测距10.456.614.46
BLE指纹6.364.783.56
EKF5.933.722.34
测距误差修正的BLE定位2.781.951.53
测距误差修正的EKF定位1.821.360.28
), ArticleFig(id=1251458180094570964, tenantId=1146029695717560320, journalId=1251194880429441115, articleId=1251458158766535421, language=CN, label=表6, caption=

不同信标数量下的STD指标

, figureFileSmall=null, figureFileBig=null, tableContent=
STD5信标6信标8信标
BLE测距10.456.614.46
BLE指纹6.364.783.56
EKF5.933.722.34
测距误差修正的BLE定位2.781.951.53
测距误差修正的EKF定位1.821.360.28
)], attaches=null, journal=Journal(id=1251194162217791579, delFlag=0, nameCn=重庆邮电大学学报(自然科学版), nameEn=Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), nameHistory1=null, nameHistory2=null, issn=1673-825X, eissn=null, cn=50-1181/N, coden=null, periodic=1, 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=eIjswk9Qxcq7+V27dEZ90g==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), journalRemark=null, publicationField=null, createdTime=1776237534337, updatedTime=1776238167705, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Natural Sciences, subjectName=null, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=eIjswk9Qxcq7+V27dEZ90g==, picEn=PN1NU8XEwLhVlBzwQEoroA==, jcr=null, cjcr=null, exts=[JournalExt(id=1251196818869137642, language=CN, name=重庆邮电大学学报(自然科学版), 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=1776238167732, updatedTime=1776238167732, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://journal2.cqupt.edu.cn/jcuptnsecn/jcuptnse/author/login, submissionEditorUrl=http://journal2.cqupt.edu.cn/jcuptnsecn/jcuptnse/editor/login, submissionReviewUrl=http://journal2.cqupt.edu.cn/jcuptnsecn/jcuptnse/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1251196818936246507, language=EN, name=Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), 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=1776238167747, updatedTime=1776238167747, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://journal2.cqupt.edu.cn/jcuptnsecn/jcuptnse/author/login, submissionEditorUrl=http://journal2.cqupt.edu.cn/jcuptnsecn/jcuptnse/editor/login, submissionReviewUrl=http://journal2.cqupt.edu.cn/jcuptnsecn/jcuptnse/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1251194880429441115, websiteList=[Website(id=1251197148419797361, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251194880429441115, 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/cqyddxxb/CN, language=CN, createTime=1776238246302, createBy=18614031015, updateTime=1776238652182, updateBy=18614031015, name=重庆邮电大学学报(自然科学版)-中文, tplId=1146099689490845704, title=重庆邮电大学学报(自然科学版), delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251198981565530670, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=articleTextType, value=kx, createTime=1776238683358, updateTime=1776238683358, creator=18614031015, updator=18614031015), WebsiteProps(id=1251198981540364843, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=banner, value=null, createTime=1776238683352, updateTime=1776238683352, creator=18614031015, updator=18614031015), WebsiteProps(id=1251198981590696497, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=grayFlag, value=0, createTime=1776238683364, updateTime=1776238683364, creator=18614031015, updator=18614031015), WebsiteProps(id=1251198981531976234, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=logo, value=https://castjournals.cast.org.cn/joweb/cqyddxxb/CN/file/pic?fileId=X24gYotabwCg03WC1YllbA==, createTime=1776238683350, updateTime=1776238683350, creator=18614031015, updator=18614031015), WebsiteProps(id=1251198981607473715, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=minRunFlag, value=0, createTime=1776238683368, updateTime=1776238683368, creator=18614031015, updator=18614031015), WebsiteProps(id=1251198981557142061, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/cqyddxxb/CN/file/pic, createTime=1776238683356, updateTime=1776238683356, creator=18614031015, updator=18614031015), WebsiteProps(id=1251198981599085106, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=silenceFlag, value=0, createTime=1776238683366, updateTime=1776238683366, creator=18614031015, updator=18614031015), WebsiteProps(id=1251198981548753452, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1776238683354, updateTime=1776238683354, creator=18614031015, updator=18614031015), WebsiteProps(id=1251198981578113583, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=themeColor, value=null, createTime=1776238683361, updateTime=1776238683361, creator=18614031015, updator=18614031015), WebsiteProps(id=1251198981582307888, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148419797361, code=themeStyle, value=null, createTime=1776238683362, updateTime=1776238683362, creator=18614031015, updator=18614031015)]), Website(id=1251197148516266372, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251194880429441115, 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/cqyddxxb/EN, language=EN, createTime=1776238246325, createBy=18614031015, updateTime=1776238647495, updateBy=18614031015, name=重庆邮电大学学报(自然科学版)-英文, tplId=1146101810881728533, title=Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251199007897371192, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=articleTextType, value=kx, createTime=1776238689636, updateTime=1776238689636, creator=18614031015, updator=18614031015), WebsiteProps(id=1251199007872205365, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=banner, value=null, createTime=1776238689630, updateTime=1776238689630, creator=18614031015, updator=18614031015), WebsiteProps(id=1251199007914148411, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=grayFlag, value=0, createTime=1776238689640, updateTime=1776238689640, creator=18614031015, updator=18614031015), WebsiteProps(id=1251199007863816756, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=logo, value=https://castjournals.cast.org.cn/joweb/cqyddxxb/EN/file/pic?fileId=X24gYotabwCg03WC1YllbA==, createTime=1776238689628, updateTime=1776238689628, creator=18614031015, updator=18614031015), WebsiteProps(id=1251199007930925629, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=minRunFlag, value=0, createTime=1776238689644, updateTime=1776238689644, creator=18614031015, updator=18614031015), WebsiteProps(id=1251199007888982583, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/cqyddxxb/EN/file/pic, createTime=1776238689634, updateTime=1776238689634, creator=18614031015, updator=18614031015), WebsiteProps(id=1251199007922537020, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=silenceFlag, value=0, createTime=1776238689642, updateTime=1776238689642, creator=18614031015, updator=18614031015), WebsiteProps(id=1251199007880593974, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1776238689632, updateTime=1776238689632, creator=18614031015, updator=18614031015), WebsiteProps(id=1251199007901565497, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=themeColor, value=null, createTime=1776238689637, updateTime=1776238689637, creator=18614031015, updator=18614031015), WebsiteProps(id=1251199007909954106, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251197148516266372, code=themeStyle, value=null, createTime=1776238689639, updateTime=1776238689639, creator=18614031015, updator=18614031015)])], journalTitle=重庆邮电大学学报(自然科学版), weixinUrl=null, journalUrl=http://journal2.cqupt.edu.cn/jcuptnsecn, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), journalPhotoCn=eIjswk9Qxcq7+V27dEZ90g==, journalPhotoEn=PN1NU8XEwLhVlBzwQEoroA==, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/cqyddxxb/CN/10.3979/j.issn.1673-825X.202501180025, detailUrlEn=https://castjournals.cast.org.cn/joweb/cqyddxxb/EN/10.3979/j.issn.1673-825X.202501180025, pdfUrlCn=https://castjournals.cast.org.cn/joweb/cqyddxxb/CN/PDF/10.3979/j.issn.1673-825X.202501180025, pdfUrlEn=https://castjournals.cast.org.cn/joweb/cqyddxxb/EN/PDF/10.3979/j.issn.1673-825X.202501180025, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于测距修正的BLE和PDR融合定位方法研究
收藏切换
PDF下载
刘辉 , 何航川
重庆邮电大学学报(自然科学版) | 新一代移动通信 2025,37(5): 627-637
收起
收藏切换
重庆邮电大学学报(自然科学版) | 新一代移动通信 2025, 37(5): 627-637
基于测距修正的BLE和PDR融合定位方法研究
全屏
刘辉 , 何航川
作者信息
  • 重庆邮电大学 通信与信息工程学院,重庆 400065
  • 刘辉,正高级工程师,硕士,主要研究方向为目标检测、深度学习、室内定位。E-mail:

    何航川,硕士研究生,主要研究方向为深度学习、室内定位。E-mail:

通讯作者:

Research on BLE and PDR fusion localization method based on ranging correction
Hui LIU , Hangchuan HE
Affiliations
  • School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, P R China
doi: 10.3979/j.issn.1673-825X.202501180025
文章导航
收藏切换

为解决室内非视距(non line of sight,NLOS)环境以及低信标部署密度下传统定位算法精度急剧下降的问题,提出一种基于测距修正的低功耗蓝牙(bluetooth low energy,BLE)和行人航位推算(pedestrian dead reckoning,PDR)融合定位方法。通过SketchUp室内3D建模软件联合射线追踪算法实现BLE的接收信号强度(received signal strength,RSS)快速构建,避免人工繁琐的RSS实地采集。设计一种基于卷积神经网络的变分自编码器(variational autoencoder based on convolution neural network,VAE-CNN)模型对BLE测距误差进行预测和修正,提升BLE定位精度。采用扩展卡尔曼滤波(extended Kalman filter,EKF)融合BLE和PDR的定位结果。实验结果表明,采用测距修正后的BLE测距定位以及EKF融合定位在NLOS以及信标部署密度低的环境下具有较好的定位性能。

低功耗蓝牙  /  行人航位推算  /  射线追踪  /  变分自编码器  /  扩展卡尔曼滤波

To address the significant decline in positioning accuracy of traditional algorithms under indoor non line of sight(NLOS)conditions and low beacon deployment density, this paper proposes a fused positioning method based on ranging correction, combining bluetooth low energy(BLE)and pedestrian dead reckoning(PDR). Firstly, the received signal strength(RSS)of BLE is rapidly constructed using SketchUp indoor 3D modeling software integrated with a ray-tracing algorithm, eliminating the need for tedious manual RSS field collection. Subsequently, a variational autoencoder based on convolutional neural network(VAE-CNN)is designed to predict and correct BLE ranging errors, thereby improving BLE positioning accuracy. Finally, an extended Kalman filter(EKF)is employed to fuse the positioning results from BLE and PDR. Experimental results demonstrate that the proposed ranging-corrected BLE positioning and EKF-based fusion positioning achieve superior performance in environments with NLOS interference and low beacon deployment density.

bluetooth low energy  /  pedestrian dead reckoning  /  ray tracing  /  variational autoencoder  /  extended Kalman filter
刘辉, 何航川. 基于测距修正的BLE和PDR融合定位方法研究. 重庆邮电大学学报(自然科学版), 2025 , 37 (5) : 627 -637 . DOI: 10.3979/j.issn.1673-825X.202501180025
Hui LIU, Hangchuan HE. Research on BLE and PDR fusion localization method based on ranging correction[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), 2025 , 37 (5) : 627 -637 . DOI: 10.3979/j.issn.1673-825X.202501180025
近年来,商场大楼、图书馆、博物馆等对室内定位系统的需求越来越大。同时,智能手机集成了许多传感器,其功能越来越完善,利用智能手机进行室内定位成为一种趋势。目前的定位技术主要有全球导航卫星系统(global navigation satellite system,GNSS)[1]、超宽带(ultra wideband,UWB)[2]、无线保真(wireless fidelity,WiFi)[3]、低功耗蓝牙(bluetooth low energy,BLE)[4]、惯性测量单元(inertial measurement unit,IMU)[5]等。
然而,受建筑结构或天气因素的影响,GNSS通常难以在室内接收到有效的定位信号,无法实现准确的室内定位[6]。UWB在视距环境下具有很高的定位精度,而在非视距环境下,由于障碍物的阻挡和信号的反射使得定位精度较低。此外,UWB定位必须使用昂贵的专用设备[7]。Wi-Fi指纹定位通常基于接收信号强度(receive signal strength,RSS)来实现,定位精度高,但对接入点(access point,AP)的部署密度要求高。文献[8]在75 m×25 m的实验场景中部署了100多个AP,而文献[9]在5.5 m×9.5 m的实验场景中部署了7个AP,并且前期需要建立Wi-Fi指纹数据库,需要大量的资源和高昂的成本[10]。此外,安卓(Android)系统限制了智能手机扫描Wi-Fi的频率,导致Wi-Fi定位的刷新频率不高。BLE易于使用且不需要专用设备,这使得基于BLE的定位方法得到了广泛应用,但BLE的定位精度高度依赖于部署密度,从而增加了成本。常用的基于智能手机IMU的定位方法是行人航位推算(pedestrian dead reckoning,PDR)[11]。然而,智能手机中的IMU因成本限制存在精度缺陷,导致PDR定位误差随时间累积显著增加。
PDR算法不依赖于任何外部信息,仅依靠IMU信息即可实现自主定位导航,在短时间内具有良好的定位精度。而BLE可以很容易地扩展场景,并且BLE测距观测值具有较好的物理意义,为此相关研究人员尝试将这2种技术进行融合,发挥各自的技术优势,提升室内定位精度。基于BLE的RSS定位方法包括三角法、最小二乘(least squares,LS)法、指纹法和最大似然估计法,这些算法的定位精度与所处环境以及BLE的部署密度密切相关。一方面,室内(non line of sight,NLOS)环境会导致这些算法定位精度恶化;另一方面,当BLE信标的部署密度高时,定位精度高,但成本也会增加;当BLE信标的部署密度降低时,这些算法可能无法有效工作,定位精度将大大降低[12]。在以往的研究中,已经提出了多种基于扩展卡尔曼滤波(extended Kalman filter,EKF)的PDR和无线信号测距融合算法[13-14]。这些算法主要将测距值作为观测量,与PDR进行松耦合,未能充分考虑测距值的误差大小,使其在NLOS和BLE信标部署密度较低的场景中定位精度低、鲁棒性差。
为解决上述问题,本文提出了一种基于测距误差修正的BLE和PDR融合定位方法。该方法的核心在于利用深度学习模型对BLE测距误差进行预测和修正,以提升融合定位性能。首先,在离线阶段通过SketchUp室内3D建模联合射线追踪方法实现RSS相关特征数据集的快速构建。然后,设计一种基于卷积神经网络的变分自编码器(variational autoencoder based on convolution neural network,VAECNN)模型对BLE测距误差进行预测和修正,提升BLE定位精度。最后,采用EKF算法融合BLE和PDR的定位结果。与现有EKF融合定位算法不同,本文方法充分考虑了测距误差的大小,并对此进行修正,极大地提升了定位性能。
基于测距误差修正的BLE和PDR融合室内定位算法主要分为3个部分:PDR、BLE和EKF融合,如图1所示。
在PDR定位中,首先对IMU输出的加速度和角速度数据进行低通滤波,使得加速度和角速度数据更加稳定,然后利用滤波后的加速度数据进行步态检测和步长估计,其次通过四元数法进行航向估计,最后利用得到的步长和航向角进行位置推算[11],输出PDR定位结果,以便采用EKF算法融合。
BLE定位过程主要分为离线阶段和在线阶段。离线阶段中,通过地图信息进行SketchUp室内3D建模,并联合射线追踪(ray tracing,RT)传播模型得到RSS值,以此构建特征数据集(包括信标位置、发射信号强度、RSS值、测距值),然后采用VAE-CNN网络模型对数据集进行训练。在线阶段中,首先将采集到的RSS值进行高斯-中值滤波预处理,通过路径损耗函数获得距离信息,然后利用训练好的网络模型对测距误差进行预测,以实现对测距值的修正,最后通过LS法获得BLE定位信息。
在EKF融合定位中,将PDR定位结果和BLE定位结果进行松耦合,获得最终的位置估计。
为构建特征数据与测距误差之间的相互关系,需要大量的数据集作为支撑。本文采用SketchUp室内3D建模联合RT传播模型的方法获得RSS特征数据,以避免RSS采集工作费时费力的问题。下面将简要介绍SketchUp在室内建模方面的应用以及RT传播模型。
SketchUp是一款由Trimble公司开发的易于使用的3D建模软件[15]。它支持多种文件格式(如stl、glb、dwg等)的导入导出操作,方便与其他软件进行数据交互。本节采用该软件实现室内3D场景的可视化,如图2所示。
RT传播模型是一种用于预测无线信号传播路径和损耗的高精度模型[16]。它通过模拟电磁波的传播路径,包括直射、反射、绕射和透射等现象,来准确预测信号在复杂环境中的传播特性。RT模型中的路径损耗表式为
式(1)中:LFS为自由空间损耗;Lref为反射损耗;Ldiff为绕射损耗。各项损耗的计算公式为
式(2)中:d为发射源和接收点之间的距离;f为信号频率;c为光速;R为反射系数,取决于反射面的材料和信号入射角;h为障碍物的高度;λ是信号波长;d1d2分别是发射源和接收点到障碍物的距离。
在实际RT建模过程中,为简化对测试环境的分析,将信标建模为配备了全向半波偶极子的天线,同时假设接收端也使用全向天线。此外,为了实现较为确切的RT仿真,还必须为墙壁和其他结构元件添加电磁参数,包括相对介电常数和电导率,这些元件材料参数根据国际电联发布文件中的推荐值给出[17],如表1所示。
通过设置RT的仿真参数,如表2所示,模拟模拟BLE信号的路径,其结果如图3所示。
为实现测距量的修正,准确地获得测距误差大小至关重要。本节提出了一种测距误差预测的方法。通过建立VAE-CNN深度学习模型,对RT信号传播模型得到的数据集进行特征提取和分析,建立了室内BLE信号与测距误差之间的映射关系,实现测距误差的预测。
变分自编码器(variational autoencoders,VAE)[18]是一种基于高斯混合模型的无监督生成模型。简单地说,任何分布都可以分解成几个高斯分布的叠加,而VAE是从概率的角度来描述隐藏变量的。通过提取数据在不同位置的分布特征,实现隐藏空间下数据的特征聚类。
VAE结构框图如图4所示,主要分为编码和解码2个过程,首先通过构建2个神经网络来将原始数据X借助其均值和方差使用重参数化方法生成隐变量z,然后通过解码器生成重构数据X′。
算法的具体流程为以高斯混合模型为理论基础,假设数据服从高斯分布,将X输入编码器网络,分别计算出X中每个元素对应的均值和方差,为简化训练过程以及提升优化效率,使数据经过一个均值为0,方差为1的正态分布池,即学习到的概率pz)服从正态分布N(0,1)。构建出来的编码器神经网络pX)为
式(3)中:XzNμz),σ2z))。
为使得输出的数据尽可能接近原始样本,引入KL散度。其核心思想是利用相对好计算的后验概率qzX)来接近先验概率pXz),从而只要最小化它们之间的KL散度即可近似估算出特征的潜在表示。因此,定义目标函数为
式(4)中:左边为样本数据X的似然函数;右边第一项为变分下界,θ为编码器参数,φ为解码器参数,第二项为KL散度。在左边概率函数不变的情况下,想要通过最小化KL散度来缩小差距,更便利的方法是提高变分下界,从而减小KL散度和重构损失之和。通过对先前得出的方差和交叉熵,可以推导出重构损失为
最终的目标函数可以表示为
卷积神经网络(convolutional neural network,CNN)是一种前馈神经网络,能够从具有卷积结构的数据中提取特征[19]。本文将信标坐标、测量距离、发射信号强度以及RSS值作为数据集构成形式,即输入到VAE网络的数据实际上是一个类似于二维图像的数据。因此,本文选择使用CNN来处理特征提取。基于多层卷积运算,可以学习不同数据类型之间的相关性,从而提高模型的泛化能力。将CNN与其他方法相结合,有助于网络在空间关系方面表现更优。同时,卷积层是深度神经网络的重要组成部分,与VAE强大的生成模型相结合,有助于通过深度特征识别以及高保真编码来重建其输出。
具体来说,在编码过程中使用CNN进行特征提取。假设w为输入矩阵的尺度,K为卷积核的尺度,s为滑动步长,p为零填充大小,则卷积计算得到的特征图尺度为
卷积操作完成后,通常通过池化来减少特征量,也即数据压缩,一般有最大池化和平均池化两种。在本节中,获得数据映射V后,通过卷积网络cKVs)得到中间变量Z,并将其共享给整个网络进而计算损失函数JVK)。此时,经过反向传播可得到满足式(8)的张量G
若该层不是网络的最后一层,则需要根据式(9)求V的梯度,使误差进一步反向传播。
式(9)中:i表示第i个输出通道,输出的行和列分别对应jkl表示第l个输入通道,输入行偏移量和列偏移量分别对应mn。一般来说,从输入到输出的变换过程中,非线性运算是通过加入偏移项来实现的。
VAE-CNN测距误差预测模型的整体结构如图5所示,其中,(xnynzn)表示信标坐标;dn表示测量距离;Prn表示接收信号强度;Ptn表示发射信号强度。
在构建VAE-CNN预测模型的基础上,需要先训练一个二维的CNN辅助VAE来获得特征提取模型,再训练一个全连接网络来获得预测模型。具体来说,VAE的编码器采用CNN对数据信息进行特征提取,并通过最大池化方法获得最具代表性的特征。在解码器中,还使用反卷积对采样后的潜在特征向量进行恢复,得到重构数据,通过优化重构损失和KL散度对网络进行训练,直到模型收敛。在输出端,通过Dropout层防止网络的过拟合,最终通过回归预测输出预测误差。
在线阶段,通过VAE-CNN网络预测得到的测距误差对实际测得距离值进行修正,表达式为
进一步地,采用LS算法获得BLE定位结果。
卡尔曼滤波是一种经典的最优线性系统估计算法,由于PDR定位方程为非线性,不能直接采用卡尔曼滤波,需要对非线性方程线性化。本文采用EKF方法[20],对非线性方程作一阶泰勒级数展开,将其转换成近似线性化系统,从而获得PDR与BLE的融合定位结果。其系统的状态转移方程和观测方程表达式分别为
式(11)—(12)中:w为状态转移方程的过程噪声向量,wN(0,Q);v为观测方程的测量噪声向量,vN(0,R);wv相互独立,(xtytzt)表示预测的第t步位置;Lt为预测的步长;θt为预测的俯仰角;αt为预测的航向角;()表示第t步的BLE定位结果。
EKF线性化与状态初始化后,系统的先验估计为
卡尔曼增益矩阵可以表示为
更新系统状态与协方差矩阵,可得到系统的后验估计为
式(15)中,状态转移矩阵A
观测矩阵为
由BLE定位给出融合定位系统的初始位置(x1y1z1T,初始协方差矩阵为P1,系统的过程噪声协方差矩阵Q由PDR定位的位置、步长和航向角估计的平均误差构成,观测噪声协方差矩阵R由BLE定位的平均误差构成。融合定位系统状态初始值的表达式为
式(18)—(20)中:δLδα分别表示PDR定位X轴、Y轴、Z轴、步长估计和航向角估计的平均误差,各指标通过Allan方差进行标定[21]分别表示BLE定位X轴、Y轴、Z轴的平均误差。由于在估计R矩阵前对BLE测距量进行了修正,使测距精度得到了有效提升,定位误差随之减小。为此,将R矩阵中各指标采用VAECNN模型预测得到的相对测距误差进行标定。
实验环境与场景平面图如图6所示。房间长7.7 m、宽6.8 m、高3m,中间有一处挡风玻璃,长4.6 m、宽0.1 m、高2.2 m,作为NLOS障碍物。行进路线外围的6个信标部署在距地面1m高的位置,中间的2个信标部署在距地面2.2 m高的位置。实验采用iBeacon-AK51型号的BLE信标作为信号发射器,信标发射功率设置为0 dBm,WT9011DCL BT50作为惯导器件与智能手机连接,通过智能手机进行数据采集,采样频率设置为50 Hz。行人以1.2 m高度水平手持手机从起点出发,匀速行走一圈。
在VAE-CNN模型参数中设置训练的优化算法、迭代次数、学习率等参数初始值,损失函数为均方误差损失函数,然后将RT算法生成的数据作为训练集,室内环境中实际得到的数据作为测试集,模型优化的对象为测距误差值。根据当前样本的数据分布,选择合适的卷积核,通过不断的迭代操作,最终预测出当前状态的测距误差值。
训练模型的目的是获得一组参数,使模型的预测精度满足后续的定位要求。为了使所提出的模型尽可能轻量化,对具有不同层数的几种体系结构进行了比较。为了使其在预测速度和准确性方面更有效,最终模型结构的超参数设置如表3所示。
在VAE-CNN网络的构建中,设计了由卷积网络组成的输入层、编码层和解码层。其中,特征提取通过两层的卷积运算实现,首先将数据转换为1×6× 1格式的输入数据,然后用2个1×2卷积核对数据进行卷积,并采用注意力机制增强对有用特征的提取。在解码器中,将编码器的结果作为输入,输出重构数据。在测距误差预测中,采用ReLU激活函数,使神经元具有稀疏性。为了防止过度拟合,没有使用复杂的模型结构,全连接层前的dropout值为0.5,学习率为0.001,批量大小为100,训练周期为500轮。
用实际环境中测得的RSS等数据进行测试,可以得到8个信标下行人每一步的实际测距误差与预测测距误差的对比结果如图7所示。此外,本文将实际的测距误差值与CNN、LSTM[22]、CNNLSTM[23]、Transformer[24]、VAE-CNN网络预测出的测距误差值作差并取绝对值,得到相对测距误差,对比以显示出所提VAE-CNN网络在测距误差预测中的优异性能,其相对测距误差值的分布结果对比如图8所示。
从上述结果中不难发现,采用VAE-CNN模型预测的测距误差与实际的测距误差较为接近能够很好地捕捉到测距误差的变化规律。与CNN、LSTM、CNN-LSTM、Transformer模型相比,其相对测距误差较小,均在1.2 m范围内,且70%的相对测距误差均在0.5 m范围内,具有较好的测距误差预测性能。
为评估VAE-CNN模型在不同NLOS遮挡类型下的测距误差预测性能,本文分析了多种遮挡物对BLE测距误差的影响及该模型的预测效果。
实验设置如图9所示,手机与BLE信标分别放置在高为1.5 m的支架上,两者相距4m,确保初始条件下视距测距基准。信标发射功率设置为0 dBm,手机端通过安卓应用实时采集RSS值,并通过路径损耗模型转换为距离值。随后添加不同的遮挡物测试对测距误差的影响,遮挡物包括:纸制品、玻璃、木制品、金属物和人体,每组遮挡物实验进行30次以评估其测距误差。
实验结果如图10所示,不同遮挡物对测距结果影响显著。金属物遮挡导致的测距误差最大,实际最大误差可达到6m,反映出金属物电磁特性对信号传播的强烈干扰。而在人体、木制品、玻璃或纸质品的遮挡条件下,实际的测距误差和预测的测距误差基本保持一致,论证了VAE-CNN网络模型在不同遮挡物情况下良好的测距误差预测性能。
在线阶段,按图6设置进行实验,根据VAECNN网络预测出来的测距误差对BLE测距定位进行修正,从而提高BLE测距定位精度,进而提升EKF融合定位性能。将基于RSS的BLE测距定位、基于RSS无线地图的BLE指纹定位[25]、EKF融合定位以及测距修正后的BLE和EKF定位进行对比,其定位轨迹及误差CDF如图11所示。
图11a中可以看到,BLE指纹定位受室内环境(多径效应、NLOS干扰等)影响以及参考点选取的密集程度限制,定位轨迹较为凌乱,主要集中在中心区域。而采用BLE测距定位通过VAE-CNN模型进行测距误差预测修正,提高测距的精确度,从而提升了其定位精度,使其与未进行测距修正的BLE定位相比更接近真实轨迹。进一步地,通过EKF融合定位后,轨迹更加平滑,定位效果更优。图11b显示,BLE定位最大误差在8.2 m左右,EKF定位的最大误差为3.8 m,而采用VAE-CNN测距误差预测修正后BLE定位的最大误差为2.8m左右,对应的EKF融合定位的最大误差可控制在2m内,取得了较好的定位性能。
表4给出了PDR定位、BLE测距定位、BLE指纹定位以及EKF定位算法与采用VAE-CNN模型预测测距误差修正的定位算法的定位误差指标值。其中,均方根误差(root mean squared error,RMSE)和标准差(standard deviation,STD)表示为
式(21)中:(xiyizi)为目标真实位置;()为估计位置;()为多次估计位置的平均结果;n为计算的样本个数,即待定位点的个数,本文中n=29。
可以看到,BLE测距定位的RMSE和STD分别为10.41 m、4.46 m,通过与PDR定位算法进行EKF融合可使两指标分别降至4.73 m、2.34 m,对BLE测距定位效果有着一定程度的改善,但NLOS的影响未能从根本上进行解决。BLE指纹定位同样也受NLOS影响,其定位性能不佳。而通过测距修正后的BLE定位RMSE和STD分别为2.42 m和1.53 m。这是因为采用VAE-CNN深度学习模型对测距误差与信标位置、RSS等相关因素之间的关系进行建模,在实际测试中对测距值进行误差修正,从根本上消除了NLOS对测距的影响,进而提升了定位性能。进一步地,采用测距修正后的EKF融合定位的RMSE和STD可分别降至0.81 m和0.28 m。
另一方面,设置不同的BLE信标部署数量,分别选择5个信标(4个信标放置在各角落,距地面1m高的位置,房间的中央放置一个信标,距地面2.2 m高的位置)、6个信标(按图6所示去掉中间靠墙一侧的两个信标即可)、8个信标(即图6所示)进行实验,得到每种信标部署下的RMSE及STD值分别如表5表6所示。
不难发现,当信标数量为6时,相比8个BLE信标,各定位算法误差增大趋势各有不同,这表明信标数量减小后测量信息随之减少,未采用测距修正的定位算法更易受NLOS影响导致定位精度急剧下降,而采用测距修正的定位方法通过修正NLOS误差进行定位,仍具有鲁棒的定位性能。特别地,当信标数量只有5时,未经过测距修正的BLE测距定位和EKF定位的RMSE和STD值呈现指数级增长,而基于测距误差修正的定位算法可以适应这种BLE信标稀疏部署的情形,其RMSE值分别为4.36 m和2.07 m,而STD值分别为2.78 m和1.82 m,进一步说明了该方法具有较好的定位性能。
本文利用VAE-CNN深度学习模型预测BLE测距误差,在定位过程中进行修正,提升了BLE和PDR融合的定位精度。其中,为减少实际RSS采集工作量,通过SketchUp室内3D建模结合RT算法尽可能地模拟真实环境中RSS值,在实际测试过程中证实了这种方法的有效性。根据实验结果,采用测距修正后的BLE测距定位以及EKF融合定位的最大定位误差分别在3 m、2 m以内,较未进行测距修正的BLE测距定位和EKF融合定位有着较大的性能提升。另一方面,在BLE部署密度较低时,所提算法仍能获得较好的定位精度,具有普遍的适用性。在后续研究中,将增加更多的观测信息量以提升定位性能。
参考文献 引证文献
排序方式:
[1]
KOUASSI H K W, STIENNE G, REBOUL S. GNSS phase positioning without ambiguity resolution[C]//2024 International Conference on Localization and GNSS (ICL-GNSS). Antwerp, Belgium: IEEE, 2024: 1-7.
[2]
XU Y, SHMALIY Y S, BI S, et al. Extended Kalman/UFIR filters for UWB-based indoor robot localization under time-varying colored measurement noise[J]. IEEE Internet of Things Journal,2023,10(17):15632-15641.
[3]
QI H, SONG X, ZHANG Y, et al. Multi-scale sensing network for WiFi Indoor localization[C]//2023 IEEE 23rd International Conference on Communication Technology(ICCT).Wuxi,China:IEEE,2023:1087-1092.
[4]
GUO G, CHEN R, YAN K, et al. Multi-channel and multi-RSS based BLE range estimation for indoor tracking of commercial smartphones[J]. IEEE Sensors Jour nal, 2023, 23(24): 30728-30738.
[5]
SUN M, WANG Y, JOSEPH W, et al. Indoor localization using mind evolutionary algorithm-based geomagnetic positioning and smartphone IMU sensors[J]. IEEE Sensors Journal, 2022, 22(7): 7130-7141.
[6]
ROSE C, BRITT J, ALLEN J, et al. An integrated vehicle navigation system utilizing lane-detection and lateral position estimation systems in difficult environments for GPS[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(6): 2615-2629.
[7]
WEN K, YU K, LI Y, et al. A new quaternion Kalman filter based foot-mounted IMU and UWB tightly-coupled method for indoor pedestrian navigation[J]. IEEE Transactions on Vehicular Technology, 2020, 69(4): 4340-4352.
[8]
TAO Y, ZHAO L. AIPS: An accurate indoor positioning system with fingerprint map adaptation[J]. IEEE Internet of Things Journal, 2021, 9(4): 3062-3073.
[9]
LAN T, WANG X, CHEN Z, et al. Fingerprint augment based on super-resolution for WiFi fingerprint based indoor localization[J]. IEEE Sensors Journal, 2022, 22(12): 12152-12162.
[10]
WANG X, GAO L, MAO S, et al. CSI-based fingerprinting for indoor localization: A deep learning approach[J]. IEEE Transactions on Vehicular Technology, 2016, 66(1): 763-776.
[11]
刘宇,李汪润,陈燕苹.基于自适应峰值检测的PDR算法研究[J].电子测量技术, 2023, 46(17): 37-42.
LIU Y, LI W R, CHEN Y P. Research on PDR algorithm based on adaptive peak detection[J]. Electronic Measurement Technology, 2023, 46(17): 37-42.
[12]
CHEN Z, ZHU Q, SOH Y C. Smartphone inertial sensor-based indoor localization and tracking with iBeacon corrections[J]. IEEE Transactions on Industrial Informatics, 2016, 12(4): 1540-1549.
[13]
WU Y, CHEN R, FU W, et al. Indoor positioning based on tightly coupling of PDR and one single Wi-Fi FTM AP[J]. Geo-spatial Information Science, 2023, 26(3):480-495.
[14]
YUAN D, ZHANG J, WANG J, et al. Robustly adaptive EKF PDR/UWB integrated navigation based on additional heading constraint[J]. Sensors, 2021, 21(13):4390.
[15]
ZHANG X, CHEN Y, YU L, et al. Three-dimensional modeling and indoor positioning for urban emergency response[J]. ISPRS International Journal of Geo-Information, 2017, 6(7): 214.
[16]
YUN Z, ISKANDER M F. Ray tracing for radio propagation modeling: Principles and applications[J]. IEEE access, 2015, 3: 1089-1100.
[17]
HE D, AI B, GUAN K,et al. The design and applications of high-performance ray-tracing simulation platform for 5G and beyond wireless communications: A tutorial[J]. IEEE Communications Surveys & Tutorials, 2018, 21(1): 10-27.
[18]
LIANG S, PAN Z, LIU W, et al. A survey on variational autoencoders in recommender systems[J]. ACM Computing Surveys, 2024, 56(10): 1-40.
[19]
BHATT D, PATEL C, TALSANIA H,et al. CNN variants for computer vision: History, architecture, application, challenges and future scope[J]. Electronics, 2021, 10(20): 2470.
[20]
田昕,魏国亮,王建华,.NLOS环境下的改进EKF定位算法研究[J].控制工程, 2020, 27(5): 909-913.
TIAN X, WEI G L, WANG J H, et al. Research on improved EKF localization algorithm under NLOS environment[J]. Control Engineering of China, 2020, 27(5):909-913.
[21]
EL-SHEIMY N, HOU H, NIU X. Analysis and modeling of inertial sensors using Allan variance[J]. IEEE Transactions on Instrumentation and Measurement, 2007, 57(1): 140-149.
[22]
LANDI F, BARALDI L, CORNIA M, et al. Working memory connections for LSTM[J]. Neural Networks, 2021(144): 334-341
[23]
NGAMAKEUR K, YONGCHAREON S, YU J, et al. Deep CNN-LSTM network for indoor location estimation using analog signals of passive infrared sensors[J]. IEEE Internet of Things Journal, 2022, 9(22): 22582-22594.
[24]
RAFIQUE H, PATTI D, PALESI M, et al. Fusing visuals with magnetic signals to improve indoor localization using vision transformer[C]//2024 14th International Conference on Indoor Positioning and Indoor Navigation (IPIN). Kowloon, Hong Kong, China:IEEE,2024:1-6.
[25]
RENAUDIN O, ZEMEN T, BURGESS T. Ray-tracing based fingerprinting for indoor localization[C]//2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). Kalamata, Greece: IEEE, 2018: 1-5.
2025年第37卷第5期
PDF下载
171
93
引用本文
BibTeX
文章信息
doi: 10.3979/j.issn.1673-825X.202501180025
  • 接收时间:2025-01-18
  • 首发时间:2026-04-16
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-01-18
  • 修回日期:2025-09-10
基金
作者信息
    重庆邮电大学 通信与信息工程学院,重庆 400065

通讯作者:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/cqyddxxb/CN/10.3979/j.issn.1673-825X.202501180025
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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