A Deep Dictionary Learning Framework for Device-Free Localization Based on Nonconvex Sparse Regularization and DC Programming

Received signal strength (RSS)-based device-free localization (DFL) is commonly used in the Internet-of-Things (IoT) field. However, the current DFL algorithms have limitations in terms of stability and accuracy, which hinders the widespread application of DFL. Current research on DFL predominantly...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE sensors journal Ročník 25; číslo 21; s. 40877 - 40891
Hlavní autoři:	Tan, Benying, Wang, Manman, Li, Yujie, Lu, Yongyun, Ding, Shuxue
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.11.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Accuracy Algorithms Data mining Data models Datasets Deep dictionary learning (DDL) Deep learning device-free localization (DFL) Dictionaries difference-of-convex (DC) programming Feature extraction Internet of Things Localization Location awareness Machine learning nonconvex sparse regularization received signal strength (RSS) Regularization Representations Signal strength Sparse approximation Wireless sensor networks
ISSN:	1530-437X, 1558-1748
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Received signal strength (RSS)-based device-free localization (DFL) is commonly used in the Internet-of-Things (IoT) field. However, the current DFL algorithms have limitations in terms of stability and accuracy, which hinders the widespread application of DFL. Current research on DFL predominantly revolves around sparse representation and deep learning. The sparse representation method requires building a suitable dictionary to achieve higher accuracy, while the deep learning method is affected by data volume and computational complexity. In contrast to traditional localization methods that rely on raw data features, this article suggests using the deep dictionary learning (DDL) framework to extract depth features. Then, the extracted low-level and high-level features are not only used to construct a dictionary but also to reconstruct the testing data for DFL using the sparse representation classification. This approach leverages the advantages of sparse representation and deep learning to achieve highly accurate localization. The proposed DDL model involves learning multiple dictionaries with varying descriptive capabilities to extract deep features from the observed signal through a layer-by-layer DDL process. For better dictionary learning, we introduce the minimax-concave penalty (MCP) for each layer of dictionary learning. Utilizing the difference-of-convex (DC) programming, the formulated nonconvex problems are efficiently optimized. Furthermore, to enhance localization accuracy, the data are expanded to reinforce the essential features of DDL. The performance of the DCDDL algorithm was assessed using collected laboratory datasets and public datasets, demonstrating its superiority over existing localization algorithms.
AbstractList	Received signal strength (RSS)-based device-free localization (DFL) is commonly used in the Internet-of-Things (IoT) field. However, the current DFL algorithms have limitations in terms of stability and accuracy, which hinders the widespread application of DFL. Current research on DFL predominantly revolves around sparse representation and deep learning. The sparse representation method requires building a suitable dictionary to achieve higher accuracy, while the deep learning method is affected by data volume and computational complexity. In contrast to traditional localization methods that rely on raw data features, this article suggests using the deep dictionary learning (DDL) framework to extract depth features. Then, the extracted low-level and high-level features are not only used to construct a dictionary but also to reconstruct the testing data for DFL using the sparse representation classification. This approach leverages the advantages of sparse representation and deep learning to achieve highly accurate localization. The proposed DDL model involves learning multiple dictionaries with varying descriptive capabilities to extract deep features from the observed signal through a layer-by-layer DDL process. For better dictionary learning, we introduce the minimax-concave penalty (MCP) for each layer of dictionary learning. Utilizing the difference-of-convex (DC) programming, the formulated nonconvex problems are efficiently optimized. Furthermore, to enhance localization accuracy, the data are expanded to reinforce the essential features of DDL. The performance of the DCDDL algorithm was assessed using collected laboratory datasets and public datasets, demonstrating its superiority over existing localization algorithms.
Author	Ding, Shuxue Tan, Benying Wang, Manman Lu, Yongyun Li, Yujie
Author_xml	– sequence: 1 givenname: Benying orcidid: 0000-0002-9121-8499 surname: Tan fullname: Tan, Benying email: by-tan@guet.edu.cn organization: School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China – sequence: 2 givenname: Manman surname: Wang fullname: Wang, Manman organization: School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China – sequence: 3 givenname: Yujie orcidid: 0000-0002-5801-4937 surname: Li fullname: Li, Yujie email: yujieli@guet.edu.cn organization: School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China – sequence: 4 givenname: Yongyun surname: Lu fullname: Lu, Yongyun organization: School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China – sequence: 5 givenname: Shuxue orcidid: 0000-0002-4963-3883 surname: Ding fullname: Ding, Shuxue email: sding@guet.edu.cn organization: School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China
BookMark	eNpFkMlKBDEQhoMouD6A4CHguceks3T6qLO4MKi4gLemJl0ZWmeSMT3jBr67aUbxUlWH7_8Lvl2y6YNHQg4563HOypOr--F1L2e56gnNlJZ6g-xwpUzGC2k2u1uwTIriaZvstu0zY7wsVLFDvk_pAHFBB41dNsFD_KRjhOgbP6WjCHN8D_GFuhAT9tZYzEYRkY6DhVnzBV2EnkGLNU3HdfA2-Df8oPcLiC3SO5yuZhD_QPA1HfTpbQzT1DxPL_bJloNZiwe_e488joYP_YtsfHN-2T8dZzaXZpkBBzVxdsIcaOVk6YxUztWTUhtIQztUdSG1YXUB2glmgGlrcrAiF7IWTOyR43XvIobXFbbL6jmsok8vK5HrFJVG6kTxNWVjaNuIrlrEZp6UVJxVneWqs1x1lqtfyylztM40iPjPc16ovNTiB-KLfDQ
CODEN	ISJEAZ
Cites_doi	10.3390/s22124447 10.1109/SMC.2018.00399 10.1109/JSEN.2018.2806564 10.1109/ACCESS.2021.3111083 10.1214/09-AOS729 10.1007/s10462-021-09967-1 10.1007/BF00332918 10.1109/SLAAI-ICAI59257.2023.10365021 10.1016/j.ejor.2014.11.031 10.1109/JIOT.2019.2907580 10.1109/TNNLS.2021.3114400 10.3390/jsan7010007 10.1109/TIM.2021.3065426 10.1016/j.asoc.2023.110164 10.1109/JSEN.2022.3231611 10.1109/JIOT.2016.2558659 10.1016/j.sigpro.2016.07.005 10.1162/NECO_a_00763 10.1109/ACCESS.2016.2611583 10.1109/JIOT.2018.2849375 10.1145/3234150 10.1007/978-1-4419-7011-4 10.1198/016214506000000735 10.1162/NECO_a_00836 10.1016/j.dsp.2018.08.005 10.1109/TMC.2009.174 10.1109/JIOT.2018.2812300 10.1109/TMC.2015.2504965 10.1109/TVT.2016.2635161 10.1109/JIOT.2016.2624800 10.1109/CITS55221.2022.9832985 10.1109/ICEICT55736.2022.9909163 10.1109/ACCESS.2018.2843325 10.1016/j.neucom.2020.07.085 10.1109/ACCESS.2019.2911004 10.1145/1287853.1287880 10.1155/2018/4201367 10.1016/j.jnca.2017.08.014 10.1155/2022/2323293 10.1109/TVT.2017.2701399 10.1007/s10479-004-5022-1 10.1109/ACCESS.2018.2876034 10.1016/j.dsp.2022.103420 10.1109/WCNC55385.2023.10118744 10.1109/TII.2022.3218666 10.1109/JIOT.2021.3067515 10.1109/PERCOM.2007.8 10.1007/s13042-022-01559-x 10.1109/JIOT.2020.3019732 10.1007/978-3-031-20500-2_31 10.1109/TCSS.2022.3153660 10.1109/JSEN.2017.2730226
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/JSEN.2025.3605646
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography Engineering
EISSN	1558-1748
EndPage	40891
ExternalDocumentID	10_1109_JSEN_2025_3605646 11175296
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 62076077; 62001126 funderid: 10.13039/501100001809 – fundername: Guangxi Science and Technology Major Project grantid: AA22068057 – fundername: Guangxi Natural Science Foundation through the Youth Science Fund Project grantid: 62076077; 62001126; AA22068057; 2021GXNSFBA220039 funderid: 10.13039/501100004607
GroupedDBID	-~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AGQYO AHBIQ AJQPL AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI O9- OCL P2P RIA RIE RNS TWZ AAYXX CITATION M43 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c248t-a1a5bfcb0fa65f49f845ffdb968ab966fe5d74680d7a6f308a06c82ac3234d303
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001606677500030&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1530-437X
IngestDate	Thu Nov 20 00:54:47 EST 2025 Sat Nov 29 06:59:18 EST 2025 Wed Nov 05 07:06:52 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	21
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c248t-a1a5bfcb0fa65f49f845ffdb968ab966fe5d74680d7a6f308a06c82ac3234d303
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-4963-3883 0000-0002-9121-8499 0000-0002-5801-4937
PQID	3267464846
PQPubID	75733
PageCount	15
ParticipantIDs	ieee_primary_11175296 proquest_journals_3267464846 crossref_primary_10_1109_JSEN_2025_3605646
PublicationCentury	2000
PublicationDate	2025-11-01
PublicationDateYYYYMMDD	2025-11-01
PublicationDate_xml	– month: 11 year: 2025 text: 2025-11-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE sensors journal
PublicationTitleAbbrev	JSEN
PublicationYear	2025
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	ref13 ref12 ref15 ref53 ref52 ref10 Zhao (ref11) 2023; 137 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref47 ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 Zhang (ref1) 2023; 19 ref36 ref31 Xue (ref14) 2023; 23 ref30 ref33 ref32 ref2 ref39 ref38 ref24 ref23 ref26 ref25 ref20 ref22 Xu (ref48) 2014 ref21 ref28 ref27 ref29
References_xml	– ident: ref19 doi: 10.3390/s22124447 – ident: ref33 doi: 10.1109/SMC.2018.00399 – ident: ref7 doi: 10.1109/JSEN.2018.2806564 – ident: ref4 doi: 10.1109/ACCESS.2021.3111083 – ident: ref26 doi: 10.1214/09-AOS729 – ident: ref18 doi: 10.1007/s10462-021-09967-1 – ident: ref24 doi: 10.1007/BF00332918 – ident: ref23 doi: 10.1109/SLAAI-ICAI59257.2023.10365021 – ident: ref29 doi: 10.1016/j.ejor.2014.11.031 – ident: ref43 doi: 10.1109/JIOT.2019.2907580 – ident: ref49 doi: 10.1109/TNNLS.2021.3114400 – ident: ref52 doi: 10.3390/jsan7010007 – ident: ref53 doi: 10.1109/TIM.2021.3065426 – volume: 137 year: 2023 ident: ref11 article-title: An accurate approach of device-free localization with attention empowered residual network publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2023.110164 – volume: 23 start-page: 2750 issue: 3 year: 2023 ident: ref14 article-title: Enhanced WiFi CSI fingerprints for device-free localization with deep learning representations publication-title: IEEE Sensors J. doi: 10.1109/JSEN.2022.3231611 – ident: ref36 doi: 10.1109/JIOT.2016.2558659 – ident: ref38 doi: 10.1016/j.sigpro.2016.07.005 – ident: ref20 doi: 10.1162/NECO_a_00763 – ident: ref46 doi: 10.1109/ACCESS.2016.2611583 – ident: ref37 doi: 10.1109/JIOT.2018.2849375 – ident: ref17 doi: 10.1145/3234150 – ident: ref27 doi: 10.1007/978-1-4419-7011-4 – ident: ref28 doi: 10.1198/016214506000000735 – ident: ref50 doi: 10.1162/NECO_a_00836 – ident: ref31 doi: 10.1016/j.dsp.2018.08.005 – ident: ref40 doi: 10.1109/TMC.2009.174 – ident: ref3 doi: 10.1109/JIOT.2018.2812300 – ident: ref32 doi: 10.1109/TMC.2015.2504965 – ident: ref41 doi: 10.1109/TVT.2016.2635161 – ident: ref8 doi: 10.1109/JIOT.2016.2624800 – ident: ref6 doi: 10.1109/CITS55221.2022.9832985 – ident: ref45 doi: 10.1109/ICEICT55736.2022.9909163 – ident: ref5 doi: 10.1109/ACCESS.2018.2843325 – ident: ref21 doi: 10.1016/j.neucom.2020.07.085 – ident: ref51 doi: 10.1109/ACCESS.2019.2911004 – ident: ref39 doi: 10.1145/1287853.1287880 – ident: ref42 doi: 10.1155/2018/4201367 – ident: ref12 doi: 10.1016/j.jnca.2017.08.014 – ident: ref10 doi: 10.1155/2022/2323293 – ident: ref9 doi: 10.1109/TVT.2017.2701399 – ident: ref30 doi: 10.1007/s10479-004-5022-1 – ident: ref34 doi: 10.1109/ACCESS.2018.2876034 – ident: ref15 doi: 10.1016/j.dsp.2022.103420 – ident: ref22 doi: 10.1109/WCNC55385.2023.10118744 – volume: 19 start-page: 8528 issue: 7 year: 2023 ident: ref1 article-title: Online spatiotemporal modeling for robust and lightweight device-free localization in nonstationary environments publication-title: IEEE Trans. Ind. Informat. doi: 10.1109/TII.2022.3218666 – ident: ref2 doi: 10.1109/JIOT.2021.3067515 – ident: ref35 doi: 10.1109/PERCOM.2007.8 – year: 2014 ident: ref48 article-title: A fast patch-dictionary method for whole image recovery publication-title: arXiv:1408.3740 – ident: ref44 doi: 10.1007/s13042-022-01559-x – ident: ref13 doi: 10.1109/JIOT.2020.3019732 – ident: ref47 doi: 10.1007/978-3-031-20500-2_31 – ident: ref16 doi: 10.1109/TCSS.2022.3153660 – ident: ref25 doi: 10.1109/JSEN.2017.2730226
SSID	ssj0019757
Score	2.4429312
Snippet	Received signal strength (RSS)-based device-free localization (DFL) is commonly used in the Internet-of-Things (IoT) field. However, the current DFL algorithms...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Index Database Publisher
StartPage	40877
SubjectTerms	Accuracy Algorithms Data mining Data models Datasets Deep dictionary learning (DDL) Deep learning device-free localization (DFL) Dictionaries difference-of-convex (DC) programming Feature extraction Internet of Things Localization Location awareness Machine learning nonconvex sparse regularization received signal strength (RSS) Regularization Representations Signal strength Sparse approximation Wireless sensor networks
Title	A Deep Dictionary Learning Framework for Device-Free Localization Based on Nonconvex Sparse Regularization and DC Programming
URI	https://ieeexplore.ieee.org/document/11175296 https://www.proquest.com/docview/3267464846
Volume	25
WOSCitedRecordID	wos001606677500030&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-1748 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0019757 issn: 1530-437X databaseCode: RIE dateStart: 20010101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB0BQmp7KJSCuoUiH3qqZHASxx9HYFlVFVohaKW9RY49LhzIrsJSlUP_e23H2yJVHHqJfJgklsf2PHvmzQB85F46qzXSVhhDOZY1VZ4xajDgU29cVdg2FZuQ06mazfRlJqsnLgwipuAzPIrN5Mt3c_sQr8qOi5hXstRiHdalFANZ64_LQMuU1jOsYEZ5JWfZhVkwffzl-nwajoJlfVQF9C4i2H1ihFJVlX-24mRfJlv_2bNteJ2BJDkZNP8G1rDbgVdP0gvuwItc4fzm8S38OiFjxAUZ3yYig-kfSU6t-p1MVgFaJCDYIBY3DzrpEclFtHSZqUlOg8FzJDSm8y4Fq_8k14twLkZylQra9ytB0zkyPiOXQ-jXXfjFLnybnH89-0xz6QVqS66W1BSmbr1tmTei9lx7xWvvXauFMuEhPNZOcqGYk0b4iinDhFWlsVVZcRfM4h5sdPMO3wHxRSUdatY6oXihrfJC2jAnTK2UdtaN4NNKF81iyLDRpJMJ001UXBMV12TFjWA3Dv5fwTzuIzhYqa_Ji_C-Ccg09JEHhPX-mdf24WX8-sAtPICNZf-AH2DT_lje3veHaX79Bm-c0Bk
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1BTxQxFH5RNEEPqIhhBbUHTyaFzkyn0x6RZYO6TohgsrdJp31FDs5uhoXIgf9O2-kqifHgZdJDmzZ9bd_35r3vPYD33FXWKIW0FVpTjnlJpWOMavT41GlbZKaNxSaqupazmTpJZPXIhUHEGHyGe6EZffl2bq7Cr7L9LOSVzJV4CI9KznM20LV-Ow1UFRN7-jvMKC-qWXJiZkztfz49qr0xmJd7hcfvIsDde2oo1lX56zGOGmby7D_X9hw2EpQkB4PsX8AD7Dbh6b0Eg5uwnmqc_7h5CbcHZIy4IOOLSGXQ_Q1JyVXPyWQVokU8hvXdwvNBJz0imQZdl7ia5KNXeZb4Rj3vYrj6L3K68JYxkm-xpH2_6qg7S8aH5GQI_vrpp9iC75Ojs8NjmoovUJNzuaQ602XrTMucFqXjykleOmdbJaT2H-GwtBUXktlKC1cwqZkwMtemyAtuvWJ8BWvdvMNtIC4rKouKtVZInikjnaiMPxW6lFJZY0fwYSWLZjHk2GiibcJUEwTXBME1SXAj2Aqb_6dj2vcR7K7E16RreNl4bOrXyD3Gev2PYe9g_fjs67SZfqq_7MCTMNPANNyFtWV_hW_gsbleXlz2b-NZuwNqbdNg
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=A+Deep+Dictionary+Learning+Framework+for+Device-Free+Localization+Based+on+Nonconvex+Sparse+Regularization+and+DC+Programming&rft.jtitle=IEEE+sensors+journal&rft.au=Tan%2C+Benying&rft.au=Wang%2C+Manman&rft.au=Li%2C+Yujie&rft.au=Lu%2C+Yongyun&rft.date=2025-11-01&rft.issn=1530-437X&rft.eissn=1558-1748&rft.volume=25&rft.issue=21&rft.spage=40877&rft.epage=40891&rft_id=info:doi/10.1109%2FJSEN.2025.3605646&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSEN_2025_3605646
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon