Indoor Radio Map Construction and Localization With Deep Gaussian Processes

With the increasing demand for location-based service, WiFi-based localization has become one of the most popular methods due to the wide deployment of WiFi and its low cost. To improve this technology, we propose DeepMap, a deep Gaussian process for indoor radio map construction and location estima...

Full description

Saved in:
Bibliographic Details
Published inIEEE internet of things journal Vol. 7; no. 11; pp. 11238 - 11249
Main Authors Wang, Xiangyu, Wang, Xuyu, Mao, Shiwen, Zhang, Jian, Periaswamy, Senthilkumar C. G., Patton, Justin
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.11.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Bayes methods
Bayesian analysis
Deep Gaussian process
deep learning
Electronic devices
Estimation
Gaussian process
Gaussian processes
indoor localization
Internet of Things
Localization
Location based services
Mobile handsets
Parameter identification
Radio
radio map construction
Signal processing
Signal strength
Training
Training data
Online AccessGet full text

Cover

Abstract With the increasing demand for location-based service, WiFi-based localization has become one of the most popular methods due to the wide deployment of WiFi and its low cost. To improve this technology, we propose DeepMap, a deep Gaussian process for indoor radio map construction and location estimation. Received signal strength (RSS) samples are used in DeepMap to generate accurate and fine-grained radio maps. A two-layer deep Gaussian process model is designed to determine the relationship between the location and RSS samples, while the model parameters are optimized with an offline Bayesian training method. To identify the location of a mobile device, a Bayesian fusion method is proposed, which leverages RSS samples from multiple access points (APs) to achieve high location estimation accuracy. We conduct comprehensive experiments to verify the performance of DeepMap in two indoor settings. DeepMap's robustness is validated using limited training data.
AbstractList With the increasing demand for location-based service, WiFi-based localization has become one of the most popular methods due to the wide deployment of WiFi and its low cost. To improve this technology, we propose DeepMap, a deep Gaussian process for indoor radio map construction and location estimation. Received signal strength (RSS) samples are used in DeepMap to generate accurate and fine-grained radio maps. A two-layer deep Gaussian process model is designed to determine the relationship between the location and RSS samples, while the model parameters are optimized with an offline Bayesian training method. To identify the location of a mobile device, a Bayesian fusion method is proposed, which leverages RSS samples from multiple access points (APs) to achieve high location estimation accuracy. We conduct comprehensive experiments to verify the performance of DeepMap in two indoor settings. DeepMap's robustness is validated using limited training data.
Author Wang, Xuyu
Mao, Shiwen
Patton, Justin
Wang, Xiangyu
Zhang, Jian
Periaswamy, Senthilkumar C. G.
Author_xml – sequence: 1
  givenname: Xiangyu
  surname: Wang
  fullname: Wang, Xiangyu
  email: xzw0042@auburn.edu
  organization: Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA
– sequence: 2
  givenname: Xuyu
  surname: Wang
  fullname: Wang, Xuyu
  email: xuyu.wang@csus.edu
  organization: Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA
– sequence: 3
  givenname: Shiwen
  orcidid: 0000-0002-7052-0007
  surname: Mao
  fullname: Mao, Shiwen
  email: smao@ieee.org
  organization: Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA
– sequence: 4
  givenname: Jian
  orcidid: 0000-0003-0813-2350
  surname: Zhang
  fullname: Zhang, Jian
  email: jzz0043@auburn.edu
  organization: RFID Laboratory, Auburn University, Auburn, AL, USA
– sequence: 5
  givenname: Senthilkumar C. G.
  surname: Periaswamy
  fullname: Periaswamy, Senthilkumar C. G.
  email: szc0089@auburn.edu
  organization: RFID Laboratory, Auburn University, Auburn, AL, USA
– sequence: 6
  givenname: Justin
  surname: Patton
  fullname: Patton, Justin
  email: jbp0033@auburn.edu
  organization: RFID Laboratory, Auburn University, Auburn, AL, USA
BookMark eNpNkN9LwzAQx4NMcM79AeJLwOfOS9Km7aNMndXJRCY-hjQ_sGMmNWkf9K-3c0N8uuP4fu6OzykaOe8MQucEZoRAefVQrdYzChRmtCx5xtMjNKaM5knKOR3960_QNMYNAAxYRko-Ro-V094H_CJ14_GTbPHcu9iFXnWNd1g6jZdeyW3zLX8Hb033jm-MafFC9jE20uHn4JWJ0cQzdGzlNprpoU7Q693ten6fLFeLan69TBRjvEvyNKN1zlSaS0tTqAtLNS-ssQpMXiupwerC5MPPRcYJ1WVWg2WMkCzTOUkVm6DL_d42-M_exE5sfB_ccFLQlEPBB7IYUmSfUsHHGIwVbWg-ZPgSBMROm9hpEztt4qBtYC72TGOM-cuXUA6vAPsB7Vtp0g
CODEN IITJAU
CitedBy_id crossref_primary_10_1109_ACCESS_2021_3111083
crossref_primary_10_1145_3582555
crossref_primary_10_1016_j_pmcj_2023_101784
crossref_primary_10_1109_ACCESS_2023_3254912
crossref_primary_10_1109_JIOT_2023_3278235
crossref_primary_10_3390_a13120327
crossref_primary_10_1109_JIOT_2022_3215714
crossref_primary_10_1109_JSEN_2022_3190454
crossref_primary_10_1109_JIOT_2024_3386397
crossref_primary_10_1109_JIOT_2023_3262619
crossref_primary_10_1109_TITS_2022_3208245
crossref_primary_10_1109_ACCESS_2022_3174702
crossref_primary_10_1109_JSEN_2022_3227539
crossref_primary_10_1109_ACCESS_2021_3122011
crossref_primary_10_3390_info15060336
crossref_primary_10_1007_s00521_023_08684_w
crossref_primary_10_1016_j_comnet_2024_110626
crossref_primary_10_1007_s13369_022_07095_8
crossref_primary_10_1109_ACCESS_2023_3267973
crossref_primary_10_1109_MWC_002_2200372
crossref_primary_10_1109_ACCESS_2021_3070837
crossref_primary_10_1109_ACCESS_2023_3250466
crossref_primary_10_1109_JIOT_2022_3232740
crossref_primary_10_1007_s10479_021_04164_3
crossref_primary_10_1109_JIOT_2020_3026608
crossref_primary_10_1109_TIM_2023_3345905
crossref_primary_10_1145_3596239
crossref_primary_10_1016_j_sigpro_2021_108252
crossref_primary_10_1080_24751839_2021_1975425
crossref_primary_10_1109_JIOT_2024_3371385
crossref_primary_10_1109_TSP_2024_3368769
Cites_doi 10.1109/PERCOM.2019.8767421
10.1109/TWC.2017.2757472
10.1109/PIMRC.2017.8292236
10.1109/IROS.2008.4650910
10.1109/TNSE.2018.2871165
10.1109/ICC.2018.8422562
10.1109/INFOCOM.2017.8057185
10.1109/TVT.2016.2635161
10.1109/GLOCOMW.2015.7414106
10.1109/INFCOM.2000.832252
10.1109/ICCCN.2012.6289200
10.1109/GLOCOM.2018.8647266
10.1109/TCOMM.2012.042712.110035
10.1109/ICC.2017.7997235
10.1109/ICDCS.2019.00073
10.1109/TVT.2016.2545523
10.1109/ACCESS.2018.2884193
10.1109/SAHCN.2019.8824865
10.1145/2639108.2639111
10.1109/WCSP.2017.8171090
10.1109/GLOCOM.2015.7417517
10.1109/TIE.2018.2803720
10.1016/j.adhoc.2016.07.014
10.1109/SAHCN.2017.7964901
10.1145/3286978.3286983
10.1109/TVT.2018.2867065
10.1016/j.dcan.2019.05.001
10.1145/2307636.2307654
10.1109/IPIN.2010.5647095
10.1109/JIOT.2016.2558659
10.1109/ACCESS.2017.2688362
10.1145/3300061.3300133
10.1109/TSMCC.2007.905750
10.1016/j.procs.2014.07.044
10.1145/1067170.1067193
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/JIOT.2020.2996564
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library
CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Computer and Information Systems Abstracts
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2327-4662
EndPage 11249
ExternalDocumentID 10_1109_JIOT_2020_2996564
9097850
Genre orig-research
GrantInformation_xml – fundername: NSF
  grantid: ECCS-1923163
  funderid: 10.13039/100000001
– fundername: Wireless Engineering Research and Education Center and RFID Laboratory at Auburn University, Auburn, AL, USA
  funderid: 10.13039/100007579
GroupedDBID 0R~
4.4
6IK
97E
AAJGR
AASAJ
ABQJQ
ABVLG
AKJIK
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IFIPE
IPLJI
JAVBF
M43
OCL
PQQKQ
RIA
RIE
RIG
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c336t-7452b73c47af240b8f2d68fefc0e7bcad0fd8e732785612d95b0f331155d714c3
IEDL.DBID RIE
ISSN 2327-4662
IngestDate Thu Oct 10 15:50:32 EDT 2024
Fri Aug 23 03:58:48 EDT 2024
Wed Jun 26 19:26:42 EDT 2024
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Issue 11
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c336t-7452b73c47af240b8f2d68fefc0e7bcad0fd8e732785612d95b0f331155d714c3
ORCID 0000-0002-7052-0007
0000-0003-0813-2350
OpenAccessLink https://doi.org/10.1109/jiot.2020.2996564
PQID 2460862788
PQPubID 2040421
PageCount 12
ParticipantIDs ieee_primary_9097850
proquest_journals_2460862788
crossref_primary_10_1109_JIOT_2020_2996564
PublicationCentury 2000
PublicationDate 2020-11-01
PublicationDateYYYYMMDD 2020-11-01
PublicationDate_xml – month: 11
  year: 2020
  text: 2020-11-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE internet of things journal
PublicationTitleAbbrev JIoT
PublicationYear 2020
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref35
ref13
ref34
ref12
ref37
ref15
ref36
ref14
ref31
ref30
ref33
ref11
ref10
ref2
ref1
ref39
ref17
ref38
ref16
ref19
ref18
wang (ref7) 2015
kullback (ref42) 1959
damianou (ref29) 2013
wang (ref32) 2015
ref24
ref23
ref26
ref25
titsias (ref41) 2010
ref22
ref21
ref28
rasmussen (ref27) 2006
ref8
ref9
jekabsons (ref43) 2010
ref4
ref3
ref6
ref5
schwaighofer (ref20) 2003
ref40
References_xml – ident: ref35
  doi: 10.1109/PERCOM.2019.8767421
– ident: ref39
  doi: 10.1109/TWC.2017.2757472
– start-page: 1666
  year: 2015
  ident: ref32
  article-title: DeepFi: Deep learning for indoor fingerprinting using channel state information
  publication-title: Proc WCNC
  contributor:
    fullname: wang
– ident: ref19
  doi: 10.1109/PIMRC.2017.8292236
– ident: ref22
  doi: 10.1109/IROS.2008.4650910
– ident: ref18
  doi: 10.1109/TNSE.2018.2871165
– ident: ref2
  doi: 10.1109/ICC.2018.8422562
– ident: ref36
  doi: 10.1109/INFOCOM.2017.8057185
– ident: ref34
  doi: 10.1109/TVT.2016.2635161
– ident: ref23
  doi: 10.1109/GLOCOMW.2015.7414106
– start-page: 579
  year: 2003
  ident: ref20
  article-title: GPPS: A Gaussian process positioning system for cellular networks
  publication-title: Proc NIPS
  contributor:
    fullname: schwaighofer
– ident: ref12
  doi: 10.1109/INFCOM.2000.832252
– ident: ref30
  doi: 10.1109/ICCCN.2012.6289200
– ident: ref28
  doi: 10.1109/GLOCOM.2018.8647266
– ident: ref26
  doi: 10.1109/TCOMM.2012.042712.110035
– ident: ref17
  doi: 10.1109/ICC.2017.7997235
– ident: ref4
  doi: 10.1109/ICDCS.2019.00073
– year: 2006
  ident: ref27
  publication-title: Gaussian Processes for Machine Learning
  contributor:
    fullname: rasmussen
– ident: ref14
  doi: 10.1109/TVT.2016.2545523
– ident: ref37
  doi: 10.1109/ACCESS.2018.2884193
– year: 1959
  ident: ref42
  publication-title: Information Theory and Statistics
  contributor:
    fullname: kullback
– ident: ref3
  doi: 10.1109/SAHCN.2019.8824865
– start-page: 207
  year: 2013
  ident: ref29
  article-title: Deep Gaussian processes
  publication-title: Proc Int Conf Artif Intell Statist
  contributor:
    fullname: damianou
– ident: ref5
  doi: 10.1145/2639108.2639111
– ident: ref24
  doi: 10.1109/WCSP.2017.8171090
– ident: ref33
  doi: 10.1109/GLOCOM.2015.7417517
– ident: ref1
  doi: 10.1109/TIE.2018.2803720
– ident: ref38
  doi: 10.1016/j.adhoc.2016.07.014
– ident: ref21
  doi: 10.1109/SAHCN.2017.7964901
– ident: ref8
  doi: 10.1145/3286978.3286983
– ident: ref40
  doi: 10.1109/TVT.2018.2867065
– ident: ref9
  doi: 10.1016/j.dcan.2019.05.001
– start-page: 2215
  year: 2015
  ident: ref7
  article-title: Mobility improves LMI-based cooperative indoor localization
  publication-title: Proc IEEE Wireless Commun Netw Conf (WCNC)
  contributor:
    fullname: wang
– ident: ref31
  doi: 10.1145/2307636.2307654
– ident: ref25
  doi: 10.1109/IPIN.2010.5647095
– start-page: 844
  year: 2010
  ident: ref41
  article-title: Bayesian Gaussian process latent variable model
  publication-title: Proc 13th Int Conf Artif Intell Stat
  contributor:
    fullname: titsias
– start-page: 87
  year: 2010
  ident: ref43
  article-title: Refining Wi-Fi based indoor positioning
  publication-title: Proc 4th Int Sci Conf Appl Inf Commun Technol (AICT)
  contributor:
    fullname: jekabsons
– ident: ref15
  doi: 10.1109/JIOT.2016.2558659
– ident: ref16
  doi: 10.1109/ACCESS.2017.2688362
– ident: ref10
  doi: 10.1145/3300061.3300133
– ident: ref11
  doi: 10.1109/TSMCC.2007.905750
– ident: ref6
  doi: 10.1016/j.procs.2014.07.044
– ident: ref13
  doi: 10.1145/1067170.1067193
SSID ssj0001105196
Score 2.4756544
Snippet With the increasing demand for location-based service, WiFi-based localization has become one of the most popular methods due to the wide deployment of WiFi...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Publisher
StartPage 11238
SubjectTerms Bayes methods
Bayesian analysis
Deep Gaussian process
deep learning
Electronic devices
Estimation
Gaussian process
Gaussian processes
indoor localization
Internet of Things
Localization
Location based services
Mobile handsets
Parameter identification
Radio
radio map construction
Signal processing
Signal strength
Training
Training data
Title Indoor Radio Map Construction and Localization With Deep Gaussian Processes
URI https://ieeexplore.ieee.org/document/9097850
https://www.proquest.com/docview/2460862788
Volume 7
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV09T8MwELVKJxYKFEShIA9MiLROnMTJiIDSFgoSakW3yB8XUSElFU0Xfj124hTxMbBlSKLTne13z_a7Q-jcTbnGGc1OpAo0QaGKORxccMKYClCxJDw0eufJYzic-eN5MG-gy40WBgDKy2fQM4_lWb7K5dpslfVjIzowBH0rIl6l1fraT3FNMhLag0uXxP3x6GmqCaBHenrJ1WmL_w16yl4qvxbgElUGLTSp7akuk7z11oXoyY8fpRr_a_Au2rHpJb6qxsMeakC2j1p16wZsZ3Ib3Y8ylefv-JmrRY4nfIlN5866lizmmcIPBuWsShO_LIpXfAOwxHd8vTLCS2wlBrA6QLPB7fR66Ni-Co6kNCwc5geeYFT6jKca0EWUeiqMUkglASYkVyRVETDqadt1AqTiQJCUmrI8gWKuL-khamZ5BkcIgx8J6qVMQcB8UG4EbizcmJuqZjyQooMuapcny6p8RlLSDhInJj6JiU9i49NBbePCzYvWex3UrYOU2Am2Sjw_NGRME_jjv786Qdvm35VssIua2oNwqvOHQpyVA-cTSCDD5w
link.rule.ids 315,786,790,802,27955,27956,55107
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3JTsMwEB1VcIALO6KsPnBCpE3iJE6OiK1bQEJFcIu8TESFlFS0vfD12IkDYjlwyyFRRjO23zzbbwbg1Mu5xhnNTqQKNUGhijkcPXSihApUiXR5ZPTO6V3UewwGz-FzC84_tTCIWF0-w455rM7yVSkXZqusmxjRgSHoyxrnXVartb52VDyTjkT26NJzk-6gfz_WFNB3O3rR1YlL8A18qm4qv5bgCldu1iFtLKqvk7x2FnPRke8_ijX-1-QNWLMJJrmoR8QmtLDYgvWmeQOxc3kbhv1CleUbeeBqUpKUT4np3dlUkyW8UGRkcM7qNMnTZP5CrhCn5JYvZkZ6SazIAGc78HhzPb7sObazgiMpjeYOC0JfMCoDxnMN6SLOfRXFOebSRSYkV26uYmTU17brFEgloXBzagrzhIp5gaS7sFSUBe4BwSAW1M-ZwpAFqLwYvUR4CTd1zXgoRRvOGpdn07qARlYRDzfJTHwyE5_MxqcN28aFny9a77XhsAlSZqfYLPODyNAxTeH3__7qBFZ643SUjfp3wwNYNf-pRYSHsKS9iUc6m5iL42oQfQDGecc7
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Indoor+Radio+Map+Construction+and+Localization+With+Deep+Gaussian+Processes&rft.jtitle=IEEE+internet+of+things+journal&rft.au=Wang%2C+Xiangyu&rft.au=Wang%2C+Xuyu&rft.au=Mao%2C+Shiwen&rft.au=Zhang%2C+Jian&rft.date=2020-11-01&rft.issn=2327-4662&rft.eissn=2327-4662&rft.volume=7&rft.issue=11&rft.spage=11238&rft.epage=11249&rft_id=info:doi/10.1109%2FJIOT.2020.2996564&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JIOT_2020_2996564
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2327-4662&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2327-4662&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2327-4662&client=summon