Two-Phase Multitask Autoencoder-Based Deep Learning Framework for Subject-Independent EEG Motor Imagery Classification

Electroencephalography (EEG)-based motor imagery (MI) has potential applications in diverse fields including rehabilitation, drone control, and virtual reality. However, its practical use is hindered by low generalization performance in decoding brain signals, primarily due to the subject-dependency...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE access Ročník 12; s. 77356 - 77367
Hlavní autori:	Jin, Changgyun, Song, Andrew H., Kim, Seong-Eun
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Piscataway IEEE 2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Brain modeling Classification Classification algorithms Data models Decoding Deep learning EEG Electroencephalography Feature extraction Image capture Image classification Machine learning Motor coordination motor imagery multitask autoencoder Reconstruction subject-independent Task analysis Training Virtual reality
ISSN:	2169-3536, 2169-3536
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Electroencephalography (EEG)-based motor imagery (MI) has potential applications in diverse fields including rehabilitation, drone control, and virtual reality. However, its practical use is hindered by low generalization performance in decoding brain signals, primarily due to the subject-dependency of EEG signals. Although multitask autoencoder (MTAE) techniques have recently been used to mitigate this issue, these approaches encounter an imbalance problem between loss functions with different objectives, particularly between reconstruction loss and cross-entropy. To address this, we propose a novel two-phase multitask autoencoder (2PMTAE) framework that not only rectifies the imbalance issue but also ensures stable training of the MTAE. Our framework comprises two phases: first, the generation of a class-specific target signal, and second, the calculation of the reconstruction loss based on the generated target signals, effectively aligning the objectives of the two loss functions. In subject-independent experiments, our proposed method significantly outperformed state-of-the-art techniques, achieving accuracies of 71.68% and 75.78% on the BCI competition IV-2a and OpenBMI datasets, respectively. We also show that 2PMTAE is a generic framework for MI applications that can accept any encoder the practitioner wishes to employ. These results highlight the efficacy of our approach in enhancing the generalization performance of MI-EEG decoding.
AbstractList	Electroencephalography (EEG)-based motor imagery (MI) has potential applications in diverse fields including rehabilitation, drone control, and virtual reality. However, its practical use is hindered by low generalization performance in decoding brain signals, primarily due to the subject-dependency of EEG signals. Although multitask autoencoder (MTAE) techniques have recently been used to mitigate this issue, these approaches encounter an imbalance problem between loss functions with different objectives, particularly between reconstruction loss and cross-entropy. To address this, we propose a novel two-phase multitask autoencoder (2PMTAE) framework that not only rectifies the imbalance issue but also ensures stable training of the MTAE. Our framework comprises two phases: first, the generation of a class-specific target signal, and second, the calculation of the reconstruction loss based on the generated target signals, effectively aligning the objectives of the two loss functions. In subject-independent experiments, our proposed method significantly outperformed state-of-the-art techniques, achieving accuracies of 71.68% and 75.78% on the BCI competition IV-2a and OpenBMI datasets, respectively. We also show that 2PMTAE is a generic framework for MI applications that can accept any encoder the practitioner wishes to employ. These results highlight the efficacy of our approach in enhancing the generalization performance of MI-EEG decoding.
Author	Song, Andrew H. Kim, Seong-Eun Jin, Changgyun
Author_xml	– sequence: 1 givenname: Changgyun orcidid: 0009-0001-0558-8427 surname: Jin fullname: Jin, Changgyun organization: Department of Applied Artificial Intelligence, Seoul National University of Science and Technology, Seoul, South Korea – sequence: 2 givenname: Andrew H. orcidid: 0000-0001-9356-9156 surname: Song fullname: Song, Andrew H. organization: Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA – sequence: 3 givenname: Seong-Eun orcidid: 0000-0002-4518-4208 surname: Kim fullname: Kim, Seong-Eun email: sekim@seoultech.ac.kr organization: Department of Applied Artificial Intelligence, Seoul National University of Science and Technology, Seoul, South Korea
BookMark	eNp9kV9v2yAUxdHUSuvafoLtAWnPzrD5Y_yYeWkXKdUmpXtGGK4zUsdkgFf124_UnVTtYTwAuvf-jg6cd-hs9CMg9L4ki7Ikzadl266220VFKragjIiaijfooipFU1BOxdmr-1t0HeOe5CVzidcX6Pf9oy--_9QR8N00JJd0fMDLKXkYjbcQis-5ZfEXgCPegA6jG3f4JugDPPrwgHsf8Hbq9mBSsR4tHCFvY8Kr1S2-8yl31we9g_CE20HH6HpndHJ-vELnvR4iXL-cl-jHzeq-_Vpsvt2u2-WmMIw0qeis5oR2ggsrmRSsroWQQte9oZ3kwFndGUnKqqtNA53thCFN3XSUcwtWNoZeovWsa73eq2NwBx2elNdOPRd82CkdkjMDKKgqJjmzUljBaFNLwiVUjBIjaM-rKmt9nLWOwf-aICa191MYs31FSfZWUvE81cxTJvgYA_TK5E89vTkF7QZVEnVKTc2pqVNq6iW1zNJ_2L-O_099mCkHAK8IzggXnP4BPMKksg
CODEN	IAECCG
CitedBy_id	crossref_primary_10_1080_03091902_2025_2463577 crossref_primary_10_1016_j_rser_2025_116188 crossref_primary_10_1007_s00521_025_10979_z
Cites_doi	10.1109/JBHI.2023.3239053 10.1007/978-3-319-95918-4_9 10.1109/JBHI.2022.3224506 10.1109/TNSRE.2017.2757519 10.3389/fnhum.2022.1068165 10.1109/TNSRE.2022.3191869 10.1109/JBHI.2022.3198688 10.1109/JBHI.2023.3292452 10.1109/TII.2022.3227736 10.1088/1741-2552/ab0ab5 10.3389/fnagi.2016.00273 10.1109/TNNLS.2019.2946869 10.1007/s00521-021-06352-5 10.1109/TII.2022.3197419 10.1109/TII.2021.3132340 10.1109/BHI56158.2022.9926806 10.1093/gigascience/giz002 10.1109/86.895946 10.1109/TCDS.2023.3314351 10.1109/TBME.2021.3137184 10.1109/MSP.2008.4408441 10.1016/j.bspc.2021.102826 10.1109/JBHI.2023.3285268 10.1109/TNSRE.2023.3259730 10.1109/TIM.2021.3051996 10.1126/science.abd0380 10.1109/ACCESS.2022.3161489 10.3389/fnins.2012.00039 10.1007/s11042-021-10637-1 10.1109/TNSRE.2016.2646763 10.1109/TNNLS.2021.3084827 10.3390/brainsci13071109 10.1109/JBHI.2023.3243698 10.1038/s41586-021-03506-2 10.1109/ACCESS.2019.2919143 10.1109/TBME.2016.2631620 10.1002/hbm.23730 10.21236/ada164453 10.1109/TNSRE.2022.3149899 10.1016/j.patcog.2017.10.013 10.1109/TII.2022.3146552 10.1109/TNSRE.2018.2839116 10.1109/SMC42975.2020.9283028 10.1109/TCYB.2021.3073210 10.1126/scirobotics.aaw6844 10.1038/nature04968 10.1073/pnas.1817207116 10.1109/TNNLS.2018.2789927 10.1109/JBHI.2023.3242090 10.1109/JBHI.2023.3238421
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2024.3406736
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	77367
ExternalDocumentID	oai_doaj_org_article_e224854d86d643978058e2430c63f522 10_1109_ACCESS_2024_3406736 10540565
Genre	orig-research
GrantInformation_xml	– fundername: National Research Foundation of Korea funded by the Korean Government grantid: RS-2023-002084912; 2020M3C1B8081320 funderid: 10.13039/501100003725
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c409t-bda503b656d84864776686a7fc3b85e547bc8012b7c9ebdb6c0979b355ded89c3
IEDL.DBID	RIE
ISICitedReferencesCount	3
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001242940700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:47:41 EDT 2025 Mon Jun 30 07:23:59 EDT 2025 Tue Nov 18 22:11:50 EST 2025 Sat Nov 29 06:25:46 EST 2025 Wed Aug 27 02:06:32 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c409t-bda503b656d84864776686a7fc3b85e547bc8012b7c9ebdb6c0979b355ded89c3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0001-0558-8427 0000-0002-4518-4208 0000-0001-9356-9156
OpenAccessLink	https://ieeexplore.ieee.org/document/10540565
PQID	3064713622
PQPubID	4845423
PageCount	12
ParticipantIDs	crossref_primary_10_1109_ACCESS_2024_3406736 proquest_journals_3064713622 ieee_primary_10540565 doaj_primary_oai_doaj_org_article_e224854d86d643978058e2430c63f522 crossref_citationtrail_10_1109_ACCESS_2024_3406736
PublicationCentury	2000
PublicationDate	20240000 2024-00-00 20240101 2024-01-01
PublicationDateYYYYMMDD	2024-01-01
PublicationDate_xml	– year: 2024 text: 20240000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2024
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 ref14 ref11 ref10 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref4 ref3 Brunner (ref1) 2008; 16 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref39 ref38 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29
References_xml	– ident: ref6 doi: 10.1109/JBHI.2023.3239053 – ident: ref8 doi: 10.1007/978-3-319-95918-4_9 – volume: 16 start-page: 1 year: 2008 ident: ref1 publication-title: BCI Competition 2008–Graz Data Set A – ident: ref26 doi: 10.1109/JBHI.2022.3224506 – ident: ref42 doi: 10.1109/TNSRE.2017.2757519 – ident: ref18 doi: 10.3389/fnhum.2022.1068165 – ident: ref20 doi: 10.1109/TNSRE.2022.3191869 – ident: ref27 doi: 10.1109/JBHI.2022.3198688 – ident: ref24 doi: 10.1109/JBHI.2023.3292452 – ident: ref32 doi: 10.1109/TII.2022.3227736 – ident: ref7 doi: 10.1088/1741-2552/ab0ab5 – ident: ref23 doi: 10.3389/fnagi.2016.00273 – ident: ref16 doi: 10.1109/TNNLS.2019.2946869 – ident: ref11 doi: 10.1007/s00521-021-06352-5 – ident: ref49 doi: 10.1109/TII.2022.3197419 – ident: ref31 doi: 10.1109/TII.2021.3132340 – ident: ref33 doi: 10.1109/BHI56158.2022.9926806 – ident: ref51 doi: 10.1093/gigascience/giz002 – ident: ref41 doi: 10.1109/86.895946 – ident: ref21 doi: 10.1109/TCDS.2023.3314351 – ident: ref39 doi: 10.1109/TBME.2021.3137184 – ident: ref40 doi: 10.1109/MSP.2008.4408441 – ident: ref48 doi: 10.1016/j.bspc.2021.102826 – ident: ref28 doi: 10.1109/JBHI.2023.3285268 – ident: ref19 doi: 10.1109/TNSRE.2023.3259730 – ident: ref43 doi: 10.1109/TIM.2021.3051996 – ident: ref3 doi: 10.1126/science.abd0380 – ident: ref47 doi: 10.1109/ACCESS.2022.3161489 – ident: ref22 doi: 10.3389/fnins.2012.00039 – ident: ref38 doi: 10.1007/s11042-021-10637-1 – ident: ref13 doi: 10.1109/TNSRE.2016.2646763 – ident: ref45 doi: 10.1109/TNNLS.2021.3084827 – ident: ref50 doi: 10.3390/brainsci13071109 – ident: ref35 doi: 10.1109/JBHI.2023.3243698 – ident: ref4 doi: 10.1038/s41586-021-03506-2 – ident: ref37 doi: 10.1109/ACCESS.2019.2919143 – ident: ref34 doi: 10.1109/TBME.2016.2631620 – ident: ref29 doi: 10.1002/hbm.23730 – ident: ref36 doi: 10.21236/ada164453 – ident: ref15 doi: 10.1109/TNSRE.2022.3149899 – ident: ref44 doi: 10.1016/j.patcog.2017.10.013 – ident: ref9 doi: 10.1109/TII.2022.3146552 – ident: ref5 doi: 10.1109/TNSRE.2018.2839116 – ident: ref46 doi: 10.1109/SMC42975.2020.9283028 – ident: ref12 doi: 10.1109/TCYB.2021.3073210 – ident: ref14 doi: 10.1126/scirobotics.aaw6844 – ident: ref2 doi: 10.1038/nature04968 – ident: ref10 doi: 10.1073/pnas.1817207116 – ident: ref30 doi: 10.1109/TNNLS.2018.2789927 – ident: ref25 doi: 10.1109/JBHI.2023.3242090 – ident: ref17 doi: 10.1109/JBHI.2023.3238421
SSID	ssj0000816957
Score	2.3508525
Snippet	Electroencephalography (EEG)-based motor imagery (MI) has potential applications in diverse fields including rehabilitation, drone control, and virtual...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	77356
SubjectTerms	Brain modeling Classification Classification algorithms Data models Decoding Deep learning EEG Electroencephalography Feature extraction Image capture Image classification Machine learning Motor coordination motor imagery multitask autoencoder Reconstruction subject-independent Task analysis Training Virtual reality
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NT9wwELUq1EN7QLQFdVta-dBjDU7i-OO4bHdbpBZxoBI3Kx47BQG7q90A4t_jcbyrrSqVC9fEkRPPZGaeNX6PkC_GQ-EVtIyr0DABRcuMxg4ALUXTIj-6TySuP9XJiT4_N6cbUl_YE9bTA_cLdxhKJN0SXkufkqfmtQ6lqDjIqo3FA0ZfrswGmEoxWBfS1CrTDBXcHA5Ho_hFERCW4qASKM8i_0pFibE_S6z8E5dTspnskO1cJdJh_3ZvyIswfUteb3AHviN3Z_czdnoRkxDtD9E2yys6vO1myEzpw4IdxVuefgthTjOJ6h86WbVi0Vir0hg0cBeGHa-lcDs6Hn-nv2YRiNPjG6S3eKBJNhMbipINd8nvyfhs9INlEQUGEbp1zPmm5pWLZZvXQuOxUym1bFQLldN1qIVygFnKKTDBeSeBG2VcLEN88NpAtUe2prNpeE-oM00lQ6kDktoE4A2IEgAiwnS6qIMZkHK1nhYywzgKXVzbhDS4sb0RLBrBZiMMyNf1Q_OeYOP_w4_QUOuhyI6dLkSfsdln7FM-MyC7aOaN-bBulfWA7K_sbvOvvLQI0SKSl2X54Tnm_khe4ff0uzj7ZKtb3IZP5CXcdZfLxefkxY8aovCK priority: 102 providerName: Directory of Open Access Journals
Title	Two-Phase Multitask Autoencoder-Based Deep Learning Framework for Subject-Independent EEG Motor Imagery Classification
URI	https://ieeexplore.ieee.org/document/10540565 https://www.proquest.com/docview/3064713622 https://doaj.org/article/e224854d86d643978058e2430c63f522
Volume	12
WOSCitedRecordID	wos001242940700001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELZoxQEOPIvYUiofOOKSTRw_jttlFyrRqoci9WbF4wkgYFPtZltx4bfjcbyrIgQSlyhKbMXJZ3semfmGsVc2wDhoaEWhsRESxq2whiIAjJJNS_zoIZG4ftBnZ-by0p7nZPWUC4OIKfgMj-g0_csPHazJVRZXOOkXqt5hO1qrIVlr61ChChK21plZaFzYN5PpNL5EtAFLeVRJqsiifpM-iaQ_V1X5YytO8mX-8D9H9og9yIoknwzIP2Z3cPGE3b9FL_iUXV_cdOL8c5RTfMizbVZf-WTdd0ReGXApjuOtwN8iXvHMs_qJzzfRWjyqszzuK-SoESfbark9n83e8dMu2ur85DsxYPzgqbImxRwlmPfYx_nsYvpe5DoLAqJ11wsfmrqofNTsgpGGMlOVMqrRLVTe1FhL7YEEmddg0QevoLDa-qipBAzGQvWM7S66BT5n3NumUlgaJN4bhKIBWQJANEK9GddoR6zcfH8HmYScamF8c8kYKawbQHMEmsugjdjrbaergYPj382PCdhtUyLQThciYi6vR4clcbnJYFRIOpkpaoOlrApQVRt10hHbI5RvPW8AeMQONvPE5dW-cmTFRWNfleX-X7q9YPdoiIPv5oDt9ss1vmR34br_sloeJkdAPJ7-nB2mSf0Lff_yUw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Nb9MwFLdgIAGH8bWJwgAfOJLhOo5jH7uuZRVdtUORdrNi-2UgWDO16RD_PX6OW21CQ-IWJbZi52f7feS93yPkg_au70tXZ6yEKhOuX2daYQSAkqKqkR_dRxLXaTmbqfNzfZaS1WMuDADE4DM4xMv4L983bo2usrDDUb-QxX3yoBCCsy5da-tSwRoSuigTt1Cf6U-D4TBMI1iBXBzmAmuyyFvyJ9L0p7oqfx3GUcKMn_7n2J6R3aRK0kGH_XNyDxYvyJMbBIMvyfX8V5OdfQuSinaZttXqBx2s2wbpKz0ss6PwyNNjgCuamFYv6HgTr0WDQkvDyYKummyyrZfb0tHoMz1tgrVOJ5fIgfGbxtqaGHUUgd4jX8ej-fAkS5UWMhfsuzazvipYboNu55VQmJsqpZJVWbvcqgIKUVqHosyWToP1VjqmS22DruLBK-3yfbKzaBbwilCrq1wCV4DMN-BY5QR3zgUz1Kp-AbpH-Ob7G5doyLEaxk8TzRGmTQeaQdBMAq1HPm47XXUsHP9ufoTAbpsihXa8ERAzaUca4MjmJrySPmplihUKuMiZk3kdtNIe2UOUb7yvA7hHDjbrxKT9vjJoxwVzX3L--o5u78mjk_np1Ewnsy9vyGMcbufJOSA77XINb8lDd91-Xy3fxUX9B8_Y83Q
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=Two-Phase+Multitask+Autoencoder-Based+Deep+Learning+Framework+for+Subject-Independent+EEG+Motor+Imagery+Classification&rft.jtitle=IEEE+access&rft.au=Jin%2C+Changgyun&rft.au=Song%2C+Andrew+H.&rft.au=Kim%2C+Seong-Eun&rft.date=2024&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=12&rft.spage=77356&rft.epage=77367&rft_id=info:doi/10.1109%2FACCESS.2024.3406736&rft.externalDocID=10540565
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon