EfficientFi: Toward Large-Scale Lightweight WiFi Sensing via CSI Compression

WiFi technology has been applied to various places due to the increasing requirement of high-speed Internet access. Recently, besides network services, WiFi sensing is appealing in smart homes since it is device free, cost effective and privacy preserving. Though numerous WiFi sensing methods have b...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE internet of things journal Ročník 9; číslo 15; s. 13086 - 13095
Hlavní autori:	Yang, Jianfei, Chen, Xinyan, Zou, Han, Wang, Dazhuo, Xu, Qianwen, Xie, Lihua
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Piscataway IEEE 01.08.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Artificial neural networks Channel state information (CSI) Cloud computing Deep learning deep neural network discrete representation learning Edge computing Feature extraction Human activity recognition Internet access Internet of Things multitask learning Sensors Servers Smart buildings Smart houses variational autoencoder WiFi-based sensing Wireless access points Wireless fidelity
ISSN:	2327-4662, 2327-4662
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	WiFi technology has been applied to various places due to the increasing requirement of high-speed Internet access. Recently, besides network services, WiFi sensing is appealing in smart homes since it is device free, cost effective and privacy preserving. Though numerous WiFi sensing methods have been developed, most of them only consider single smart home scenario. Without the connection of powerful cloud server and massive users, large-scale WiFi sensing is still difficult. In this article, we first analyze and summarize these obstacles, and propose an efficient large-scale WiFi sensing framework, namely, EfficientFi. The EfficientFi works with edge computing at WiFi access points and cloud computing at center servers. It consists of a novel deep neural network that can compress fine-grained WiFi channel state information (CSI) at edge, restore CSI at cloud, and perform sensing tasks simultaneously. A quantized autoencoder and a joint classifier are designed to achieve these goals in an end-to-end fashion. To the best of our knowledge, the EfficientFi is the first Internet of Things-cloud-enabled WiFi sensing framework that significantly reduces communication overhead while realizing sensing tasks accurately. We utilized human activity recognition (HAR) and identification via WiFi sensing as two case studies, and conduct extensive experiments to evaluate the EfficientFi. The results show that it compresses CSI data from 1.368 Mb/s to 0.768 kb/s with extremely low error of data reconstruction and achieves over 98% accuracy for HAR.
AbstractList	WiFi technology has been applied to various places due to the increasing requirement of high-speed Internet access. Recently, besides network services, WiFi sensing is appealing in smart homes since it is device free, cost effective and privacy preserving. Though numerous WiFi sensing methods have been developed, most of them only consider single smart home scenario. Without the connection of powerful cloud server and massive users, large-scale WiFi sensing is still difficult. In this article, we first analyze and summarize these obstacles, and propose an efficient large-scale WiFi sensing framework, namely, EfficientFi. The EfficientFi works with edge computing at WiFi access points and cloud computing at center servers. It consists of a novel deep neural network that can compress fine-grained WiFi channel state information (CSI) at edge, restore CSI at cloud, and perform sensing tasks simultaneously. A quantized autoencoder and a joint classifier are designed to achieve these goals in an end-to-end fashion. To the best of our knowledge, the EfficientFi is the first Internet of Things-cloud-enabled WiFi sensing framework that significantly reduces communication overhead while realizing sensing tasks accurately. We utilized human activity recognition (HAR) and identification via WiFi sensing as two case studies, and conduct extensive experiments to evaluate the EfficientFi. The results show that it compresses CSI data from 1.368 Mb/s to 0.768 kb/s with extremely low error of data reconstruction and achieves over 98% accuracy for HAR.
Author	Zou, Han Yang, Jianfei Chen, Xinyan Xie, Lihua Xu, Qianwen Wang, Dazhuo
Author_xml	– sequence: 1 givenname: Jianfei orcidid: 0000-0002-8075-0439 surname: Yang fullname: Yang, Jianfei email: yang0478@ntu.edu.sg organization: School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore – sequence: 2 givenname: Xinyan orcidid: 0000-0002-9174-6558 surname: Chen fullname: Chen, Xinyan organization: School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore – sequence: 3 givenname: Han orcidid: 0000-0002-8063-5211 surname: Zou fullname: Zou, Han email: enthalpyzou@gmail.com organization: Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, CA, USA – sequence: 4 givenname: Dazhuo orcidid: 0000-0002-1667-0573 surname: Wang fullname: Wang, Dazhuo organization: School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore – sequence: 5 givenname: Qianwen orcidid: 0000-0002-2793-9048 surname: Xu fullname: Xu, Qianwen email: qianwenx@kth.se organization: Department of Electric Power and Energy Systems, KTH Royal Institute of Technology, Stockholm, Sweden – sequence: 6 givenname: Lihua orcidid: 0000-0002-7137-4136 surname: Xie fullname: Xie, Lihua email: elhxie@ntu.edu.sg organization: School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore
BookMark	eNp9kE1PwkAQhjcGExH5AcbLJp6L-13WmyGgmCYcaOJxs7SzuARa3C0S_71tIMZ48DIzh_eZyTzXqFfVFSB0S8mIUqIfXueLfMQIoyNOudZyfIH6jLM0EUqx3q_5Cg1j3BBCWkxSrfoomzrnCw9VM_OPOK-PNpQ4s2ENybKwW8CZX783R-gqfvMzj5dQRV-t8ae3eLKc40m92weI0dfVDbp0dhtheO4DlM-m-eQlyRbP88lTlhRc6iaxshCOSQ6OU-FUqZwC5py1Kk0J52MlQHJeWlqyFNRKCKdXjowFE2VqqeMDdH9auw_1xwFiYzb1IVTtRcOUllRoKWiboqdUEeoYAzizD35nw5ehxHTaTKfNdNrMWVvLpH-Ywje2aV9rgvXbf8m7E-kB4OeSVioVVPBvf_Z7Ig
CODEN	IITJAU
CitedBy_id	crossref_primary_10_1109_TIM_2025_3568952 crossref_primary_10_1109_JSAC_2023_3288231 crossref_primary_10_1109_TWC_2024_3381211 crossref_primary_10_1109_JSEN_2024_3520857 crossref_primary_10_1109_JSEN_2024_3406588 crossref_primary_10_1109_JIOT_2024_3397708 crossref_primary_10_1109_TCE_2024_3435881 crossref_primary_10_3390_math13111753 crossref_primary_10_1109_JIOT_2025_3580141 crossref_primary_10_1109_JIOT_2024_3434738 crossref_primary_10_1109_LWC_2024_3415633 crossref_primary_10_1109_TCCN_2023_3322983 crossref_primary_10_1007_s13735_025_00369_5 crossref_primary_10_1109_JSEN_2023_3326490 crossref_primary_10_1109_JIOT_2022_3228820 crossref_primary_10_1016_j_eswa_2025_128912 crossref_primary_10_1109_JSEN_2025_3546619 crossref_primary_10_3390_electronics12214500 crossref_primary_10_1109_JIOT_2024_3351838 crossref_primary_10_3390_electronics12183935 crossref_primary_10_1109_JIOT_2022_3156099 crossref_primary_10_1145_3705893 crossref_primary_10_1145_3708323 crossref_primary_10_1109_TCE_2023_3245821 crossref_primary_10_1109_ACCESS_2024_3415359 crossref_primary_10_1109_JIOT_2022_3224134 crossref_primary_10_1109_JSEN_2024_3414862 crossref_primary_10_1109_ACCESS_2025_3568505 crossref_primary_10_1109_JIOT_2022_3203559 crossref_primary_10_3390_app15020890 crossref_primary_10_1109_ACCESS_2024_3517417 crossref_primary_10_1109_JIOT_2024_3375337 crossref_primary_10_1109_TCCN_2024_3476491 crossref_primary_10_1109_LSENS_2025_3551337 crossref_primary_10_1109_TMC_2023_3296987 crossref_primary_10_1109_JIOT_2024_3369856 crossref_primary_10_1109_MNET_2025_3579496 crossref_primary_10_1109_JIOT_2025_3544388 crossref_primary_10_1109_TMC_2023_3321306 crossref_primary_10_1109_TCOMM_2023_3317924 crossref_primary_10_1109_OJCOMS_2025_3600616 crossref_primary_10_1007_s13042_024_02396_w crossref_primary_10_1109_TNSE_2024_3496496 crossref_primary_10_1109_JIOT_2023_3312941 crossref_primary_10_1109_JIOT_2025_3574568 crossref_primary_10_1109_LWC_2024_3510215 crossref_primary_10_1109_JIOT_2024_3384872 crossref_primary_10_3390_s23239534 crossref_primary_10_1145_3632177 crossref_primary_10_3390_s25030918 crossref_primary_10_3390_bioengineering11111124 crossref_primary_10_1109_JIOT_2024_3476149 crossref_primary_10_1109_TMC_2024_3374046 crossref_primary_10_3390_s25134216 crossref_primary_10_1109_TCOMM_2022_3217777 crossref_primary_10_1145_3643543 crossref_primary_10_3390_en17020485 crossref_primary_10_1016_j_pmcj_2024_101963 crossref_primary_10_3390_s24227195 crossref_primary_10_3390_app14177850 crossref_primary_10_1016_j_iot_2025_101634
Cites_doi	10.1145/3448092 10.1109/CVPRW.2019.00056 10.1109/JIOT.2016.2579198 10.1109/TII.2017.2712746 10.1145/2789168.2790093 10.1073/pnas.0909892106 10.1109/TIT.2016.2556683 10.1145/2639108.2639143 10.1145/2789168.2790124 10.1109/ICMLA.2017.0-148 10.1145/3241539.3241570 10.1007/978-981-16-0575-8_6 10.1109/MCOM.2014.6736761 10.1007/978-3-319-24702-1_11 10.1145/3210240.3210333 10.1109/TWC.2020.3043502 10.1609/aaai.v32i1.11497 10.1007/978-3-030-68590-4_5 10.1109/MASSP.1984.1162229 10.1145/3290605.3300766 10.1109/TVT.2017.2780121 10.1016/j.future.2020.06.032 10.1109/SCC.2015.47 10.1109/JIOT.2019.2941527 10.1109/ICC.2018.8422895 10.1145/1925861.1925870 10.1109/TVT.2016.2545523 10.1109/TMC.2018.2878233 10.1109/IPSN.2016.7460727 10.1016/j.fcij.2017.02.001 10.1145/3310194 10.1002/cpa.20042 10.1109/JIOT.2018.2849655 10.1109/JIOT.2020.3024234 10.1016/j.enbuild.2018.06.040 10.1109/ICCCN.2018.8487345 10.1109/TIT.2003.817466 10.1109/SECONW.2017.8011040 10.1109/LWC.2018.2818160
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1109/JIOT.2021.3139958
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://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	2327-4662
EndPage	13095
ExternalDocumentID	10_1109_JIOT_2021_3139958 9667414
Genre	orig-research
GrantInformation_xml	– fundername: NTU Presidential Postdoctoral Fellowship, “Adaptive Multimodal Learning for Robust Sensing and Recognition in Smart Cities” Project Fund, in Nanyang Technological University, Singapore funderid: 10.13039/501100001475
GroupedDBID	0R~ 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS IFIPE IPLJI JAVBF M43 OCL PQQKQ RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c359t-a5c4f253ef314f6d6f6e2ffaa677033864e533da1d27e6b44f9bf08424d7a1f3
IEDL.DBID	RIE
ISICitedReferencesCount	88
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000831217100022&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2327-4662
IngestDate	Sun Jun 29 12:41:59 EDT 2025 Sat Nov 29 06:17:03 EST 2025 Tue Nov 18 22:38:05 EST 2025 Wed Aug 27 02:25:28 EDT 2025
IsPeerReviewed	false
IsScholarly	true
Issue	15
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-c359t-a5c4f253ef314f6d6f6e2ffaa677033864e533da1d27e6b44f9bf08424d7a1f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-9174-6558 0000-0002-2793-9048 0000-0002-8063-5211 0000-0002-8075-0439 0000-0002-1667-0573 0000-0002-7137-4136
PQID	2695149541
PQPubID	2040421
PageCount	10
ParticipantIDs	proquest_journals_2695149541 crossref_primary_10_1109_JIOT_2021_3139958 ieee_primary_9667414 crossref_citationtrail_10_1109_JIOT_2021_3139958
PublicationCentury	2000
PublicationDate	2022-08-01
PublicationDateYYYYMMDD	2022-08-01
PublicationDate_xml	– month: 08 year: 2022 text: 2022-08-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE internet of things journal
PublicationTitleAbbrev	JIoT
PublicationYear	2022
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 ref35 ref12 ref34 ref15 Polino (ref43) ref14 ref31 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref39 ref16 ref19 ref18 ref24 ref23 van den Oord (ref36) ref26 ref25 ref20 ref42 ref41 ref22 ref21 ref28 ref27 ref29 ref8 LeCun (ref37); 1 ref7 Bengio (ref38) 2013 ref9 ref4 ref3 ref6 ref5 ref40
References_xml	– volume: 1 start-page: 21 volume-title: Proc. Connectionist Models Summer School ident: ref37 article-title: A theoretical framework for back-propagation – ident: ref19 doi: 10.1145/3448092 – ident: ref18 doi: 10.1109/CVPRW.2019.00056 – start-page: 1 volume-title: Proc. 6th Int. Conf. Learn. Represent. ident: ref43 article-title: Model compression via distillation and quantization – ident: ref9 doi: 10.1109/JIOT.2016.2579198 – ident: ref7 doi: 10.1109/TII.2017.2712746 – ident: ref41 doi: 10.1145/2789168.2790093 – ident: ref28 doi: 10.1073/pnas.0909892106 – year: 2013 ident: ref38 article-title: Estimating or propagating gradients through stochastic neurons for conditional computation publication-title: arXiv:1308.3432 – ident: ref30 doi: 10.1109/TIT.2016.2556683 – ident: ref40 doi: 10.1145/2639108.2639143 – ident: ref15 doi: 10.1145/2789168.2790124 – ident: ref17 doi: 10.1109/ICMLA.2017.0-148 – ident: ref34 doi: 10.1145/3241539.3241570 – ident: ref8 doi: 10.1007/978-981-16-0575-8_6 – ident: ref27 doi: 10.1109/MCOM.2014.6736761 – ident: ref35 doi: 10.1007/978-3-319-24702-1_11 – ident: ref21 doi: 10.1145/3210240.3210333 – ident: ref32 doi: 10.1109/TWC.2020.3043502 – ident: ref6 doi: 10.1609/aaai.v32i1.11497 – ident: ref22 doi: 10.1007/978-3-030-68590-4_5 – ident: ref39 doi: 10.1109/MASSP.1984.1162229 – ident: ref33 doi: 10.1145/3290605.3300766 – ident: ref25 doi: 10.1109/TVT.2017.2780121 – start-page: 6309 volume-title: Proc. 31st Int. Conf. Neural Inf. Process. Syst. ident: ref36 article-title: Neural discrete representation learning – ident: ref12 doi: 10.1016/j.future.2020.06.032 – ident: ref11 doi: 10.1109/SCC.2015.47 – ident: ref3 doi: 10.1109/JIOT.2019.2941527 – ident: ref5 doi: 10.1109/ICC.2018.8422895 – ident: ref14 doi: 10.1145/1925861.1925870 – ident: ref26 doi: 10.1109/TVT.2016.2545523 – ident: ref24 doi: 10.1109/TMC.2018.2878233 – ident: ref42 doi: 10.1109/IPSN.2016.7460727 – ident: ref10 doi: 10.1016/j.fcij.2017.02.001 – ident: ref23 doi: 10.1145/3310194 – ident: ref29 doi: 10.1002/cpa.20042 – ident: ref2 doi: 10.1109/JIOT.2018.2849655 – ident: ref13 doi: 10.1109/JIOT.2020.3024234 – ident: ref16 doi: 10.1016/j.enbuild.2018.06.040 – ident: ref20 doi: 10.1109/ICCCN.2018.8487345 – ident: ref1 doi: 10.1109/TIT.2003.817466 – ident: ref4 doi: 10.1109/SECONW.2017.8011040 – ident: ref31 doi: 10.1109/LWC.2018.2818160
SSID	ssj0001105196
Score	2.58912
Snippet	WiFi technology has been applied to various places due to the increasing requirement of high-speed Internet access. Recently, besides network services, WiFi...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	13086
SubjectTerms	Artificial neural networks Channel state information (CSI) Cloud computing Deep learning deep neural network discrete representation learning Edge computing Feature extraction Human activity recognition Internet access Internet of Things multitask learning Sensors Servers Smart buildings Smart houses variational autoencoder WiFi-based sensing Wireless access points Wireless fidelity
Title	EfficientFi: Toward Large-Scale Lightweight WiFi Sensing via CSI Compression
URI	https://ieeexplore.ieee.org/document/9667414 https://www.proquest.com/docview/2695149541
Volume	9
WOSCitedRecordID	wos000831217100022&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: 2327-4662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001105196 issn: 2327-4662 databaseCode: RIE dateStart: 20140101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwEA5z-OCLU6c4nZIHn8S6pk2TxjcZG07KFFZwbyVtEilIJ_vlv2-SZhNRBN_6kCvlvl5yd_nuDoArLiPTZrzwsAqEh7mQHqMF9nKuKOFMb8vcFgondDyOp1P23AA321oYKaUln8lb82jv8sWsWJlUWU-75tROrd6hlNS1Wl_5FGScEeIuLpHPeo-jp1QHgAHScakp4Iy_HT12lsqPDdieKsPW_77nAOw77xHe13AfgoasjkBrM5kBOkNtg2RgO0No6WF5B1NLjYWJIX17Ew2KhImJyT9sWhS-lMMSTgyRvXqF65LD_mQEzTtrimx1DNLhIO0_eG5ugleEEVt6PCq05qNQqhBhRQRRRAZKcU6otu8wJlhqJ09wJAIqSY6xYrnyYxxgQTlS4QloVrNKngIYcaqUwFSFYaEDTcVRzCJM4ihHgmhfogP8jUazwvUUN6Mt3jIbW_gsMyBkBoTMgdAB11uR97qhxl-L20br24VO4R3Q3cCWOZNbZAHRzqIO9zA6-13qHOwFpnbBsve6oLmcr-QF2C3Wy3Ixv7R_0yckmci8
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1RS8MwED5EBX1x6hSnU_Pgk1ht2jRpfRNZcVqnsIK-lbRJpCCduKl_3yTLJqIIvvUhV8pdL_nucncfwBGXkRkzXnlEBcIjXEgvYRXxSq4Y5YnelrltFM7YYBA_Pib3C3Ay74WRUtriM3lqHu1dvhhVbyZVdqahObOs1UuGOct1a31lVLCBI9RdXWI_Obvu3-U6BAywjkxNC2f87fCxbCo_tmB7rqSt_33ROqw5_IgupgbfgAXZbEJrxs2AnKu2IevZ2RBaOq3PUW6LY1Fmyr69oTaLRJmJyj9sYhQ91GmNhqaUvXlC7zVHl8M-Mu-cFsk2W5CnvfzyynPMCV4VRsnE41GldR-FUoWYKCqoojJQinPKtIeHMSVSwzzBsQiYpCUhKimVH5OACMaxCrdhsRk1cgdQxJlSgjAVhpUONRXHcRIRGkclFlSjiQ74M40WlZsqbsgtngsbXfhJYYxQGCMUzggdOJ6LvExHavy1uG20Pl_oFN6B7sxshXO6cRFQDRd1wEfw7u9Sh7Byld9mRdYf3OzBamA6GWwtXxcWJ69vch-Wq_dJPX49sH_WJ8WKzAU
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=EfficientFi%3A+Toward+Large-Scale+Lightweight+WiFi+Sensing+via+CSI+Compression&rft.jtitle=IEEE+internet+of+things+journal&rft.au=Yang%2C+Jianfei&rft.au=Chen%2C+Xinyan&rft.au=Zou%2C+Han&rft.au=Wang%2C+Dazhuo&rft.date=2022-08-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2327-4662&rft.volume=9&rft.issue=15&rft.spage=13086&rft_id=info:doi/10.1109%2FJIOT.2021.3139958&rft.externalDBID=NO_FULL_TEXT
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