MDJSCC: Multiscale Feature Learning-Based Semantic Communications for Maritime Vessel Networks

Maritime vessel networks face critical communication challenges due to severe signal attenuation induced by dynamic oceanic conditions, including vessel mobility, wave disturbances, and atmospheric variability. These conditions result in high transmission latency and poor communication reliability,...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE sensors journal Ročník 25; číslo 22; s. 42251 - 42264
Hlavní autoři:	Li, Shibao, Wang, Xinkun, Li, Dongyang, Wang, Chongyang, Meng, Zihan, Zhu, Jinze, Li, Lianghai
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 15.11.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Adaptation models Communication Computer architecture Data exchange Deep learning Encoding Feature extraction Joint source–channel coding marine communication Maritime communications maritime vessel networks Multilayers Networks Reliability Sea vessels semantic Semantic communication Semantics Sensors Signal to noise ratio Wireless communication
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	Maritime vessel networks face critical communication challenges due to severe signal attenuation induced by dynamic oceanic conditions, including vessel mobility, wave disturbances, and atmospheric variability. These conditions result in high transmission latency and poor communication reliability, making traditional bit-level communication techniques insufficient for supporting efficient and stable data exchange. To~address this issue, this work proposes multiscale feature learning (ML)-driven semantic communications for maritime vessel networks. Specifically, a maritime vessel communication model is constructed with consideration for flexibility and scalability in maritime communications, and the propagation characteristics of marine signals were simulated based on the Rician fading channel. Building upon this model, a~novel semantic communication framework named multiscale deep joint source-channel coding (MDJSCC) is developed. Combining deep learning techniques, MDJSCC enables adaptive transmission strategies based on varying channel states and compression requirements, thereby improving robustness in complex maritime environments. More importantly, a~multiscale learning block is introduced to enhance the feature extraction capability for maritime data by integrating multilayer convolutional networks. Extensive experiments are conducted on the public ocean buoy and marine image datasets. The results demonstrate that the proposed MDJSCC can achieve significant gains over traditional marine communication at low signal-to-noise ratios (SNRs) and outperforms state-of-the-art methods, yielding 22.5% and 12.4% PSNR improvements over DeepJSCC and SwinJSCC while concurrently reducing transmission volume and ensuring robust marine communication performance.
AbstractList	Maritime vessel networks face critical communication challenges due to severe signal attenuation induced by dynamic oceanic conditions, including vessel mobility, wave disturbances, and atmospheric variability. These conditions result in high transmission latency and poor communication reliability, making traditional bit-level communication techniques insufficient for supporting efficient and stable data exchange. To~address this issue, this work proposes multiscale feature learning (ML)-driven semantic communications for maritime vessel networks. Specifically, a maritime vessel communication model is constructed with consideration for flexibility and scalability in maritime communications, and the propagation characteristics of marine signals were simulated based on the Rician fading channel. Building upon this model, a~novel semantic communication framework named multiscale deep joint source-channel coding (MDJSCC) is developed. Combining deep learning techniques, MDJSCC enables adaptive transmission strategies based on varying channel states and compression requirements, thereby improving robustness in complex maritime environments. More importantly, a~multiscale learning block is introduced to enhance the feature extraction capability for maritime data by integrating multilayer convolutional networks. Extensive experiments are conducted on the public ocean buoy and marine image datasets. The results demonstrate that the proposed MDJSCC can achieve significant gains over traditional marine communication at low signal-to-noise ratios (SNRs) and outperforms state-of-the-art methods, yielding 22.5% and 12.4% PSNR improvements over DeepJSCC and SwinJSCC while concurrently reducing transmission volume and ensuring robust marine communication performance.
Author	Wang, Chongyang Wang, Xinkun Li, Dongyang Zhu, Jinze Meng, Zihan Li, Lianghai Li, Shibao
Author_xml	– sequence: 1 givenname: Shibao orcidid: 0000-0002-3924-9001 surname: Li fullname: Li, Shibao email: lishibao@upc.edu.cn organization: College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China – sequence: 2 givenname: Xinkun surname: Wang fullname: Wang, Xinkun email: z24160150@s.upc.edu.cn organization: College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China – sequence: 3 givenname: Dongyang orcidid: 0009-0009-9779-4815 surname: Li fullname: Li, Dongyang email: lidongyang@upc.edu.cn organization: College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China – sequence: 4 givenname: Chongyang surname: Wang fullname: Wang, Chongyang email: 2116040221@s.upc.edu.cn organization: College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China – sequence: 5 givenname: Zihan surname: Meng fullname: Meng, Zihan email: S24160037@s.upc.edu.cn organization: College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China – sequence: 6 givenname: Jinze surname: Zhu fullname: Zhu, Jinze email: B23160008@s.upc.edu.cn organization: College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China – sequence: 7 givenname: Lianghai surname: Li fullname: Li, Lianghai email: llianghai@163.com organization: Beijing Research Institute of Telemetry, Beijing, China
BookMark	eNpFkMtOwzAQRS1UJErhA5BYWGKd4rEd22EH4a0WFgXEish1JsilSYqdCPH3tGolVnMX596RziEZNG2DhJwAGwOw7PxxdvM05oynY6FASsX3yBDS1CSgpRlssmCJFPr9gBzGuGAMMp3qIfmYXj_O8vyCTvtl56OzS6S3aLs-IJ2gDY1vPpMrG7GkM6xt03lH87au-8Y72_m2ibRqA53a4DtfI33DGHFJn7D7acNXPCL7lV1GPN7dEXm9vXnJ75PJ891DfjlJHCjRJUKWylgusVJGloxXvNTArTPMSeWUs0aVKTCepVnmhJ4zo0C4OdhM6kqnlRiRs-3uKrTfPcauWLR9aNYvC8E1ZCaVWq0p2FIutDEGrIpV8LUNvwWwYqOx2GgsNhqLncZ153Tb8Yj4zwMYLZkWf136b6U
CODEN	ISJEAZ
Cites_doi	10.1109/TIT.2010.2053897 10.3390/electronics11091358 10.3390/s24030957 10.1109/ICC.2003.1204109 10.1109/MWC.101.2100269 10.1109/IConSCEPT61884.2024.10627891 10.1109/TSP.2021.3071210 10.1109/MWC.013.2100642 10.1109/TCSVT.2021.3082521 10.1186/s40537-022-00652-w 10.1109/ACCESS.2018.2879902 10.1109/OCEANSE.2005.1511792 10.1162/tacl_a_00477 10.7763/IJFCC.2012.V1.95 10.23919/JCC.2022.09.005 10.1007/s11042-020-10035-z 10.1109/COMST.2022.3223224 10.1109/TCCN.2024.3424842 10.1109/JIOT.2020.2993411 10.1109/TCCN.2019.2919300 10.1109/CECIT53797.2021.00088 10.1109/IWCMC51323.2021.9498601 10.1109/TWC.2023.3234408 10.1109/ACCESS.2017.2771342 10.1109/ICID52250.2020.00033 10.1109/JIOT.2022.3219674 10.1007/s11082-023-05721-9 10.1080/00207217.2019.1692373 10.1002/mop.32202 10.1007/s11082-024-07426-z 10.1016/j.rsma.2021.102031
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.2025.3614462
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	42264
ExternalDocumentID	10_1109_JSEN_2025_3614462 11187407
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China; NSFC grantid: 62401630 funderid: 10.13039/501100001809 – fundername: Innovative Development Joint Fund Key Projects of Shandong NSF grantid: ZR2023LZH010; ZR2024LZH013
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 M43 O9- OCL P2P RIA RIE RNS TWZ AAYXX CITATION 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c163t-34d68a24ef684d02f2d712ac80c46c6ca86d51029599c37b08613cb1a947f75f3
IEDL.DBID	RIE
ISSN	1530-437X
IngestDate	Thu Nov 20 00:43:58 EST 2025 Sat Nov 29 06:48:57 EST 2025 Wed Nov 19 08:27:20 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	22
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-c163t-34d68a24ef684d02f2d712ac80c46c6ca86d51029599c37b08613cb1a947f75f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-3924-9001 0009-0009-9779-4815
PQID	3271985476
PQPubID	75733
PageCount	14
ParticipantIDs	proquest_journals_3271985476 ieee_primary_11187407 crossref_primary_10_1109_JSEN_2025_3614462
PublicationCentury	2000
PublicationDate	2025-Nov.15,-15
PublicationDateYYYYMMDD	2025-11-15
PublicationDate_xml	– month: 11 year: 2025 text: 2025-Nov.15,-15 day: 15
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 ref35 ref12 ref15 ref31 ref30 ref11 Han (ref20) ref33 ref10 Pan (ref21) 2020; 21 ref2 ref1 ref17 ref16 ref19 ref18 Liu (ref14) 2022; 11 Chen (ref26) 2021; 48 ref24 Tan (ref36) 2022 ref23 Ballé (ref34) 2015 Liu (ref25) 2024; 24 ref22 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 Muneer (ref32) 2007
References_xml	– ident: ref10 doi: 10.1109/TIT.2010.2053897 – volume: 11 start-page: 1358 issue: 9 year: 2022 ident: ref14 article-title: Enhancing communication reliability from the semantic level under low SNR publication-title: Electronics doi: 10.3390/electronics11091358 – volume: 24 start-page: 957 issue: 3 year: 2024 ident: ref25 article-title: CNN and attention-based joint source channel coding for semantic communications in WSNs publication-title: Sensors doi: 10.3390/s24030957 – ident: ref31 doi: 10.1109/ICC.2003.1204109 – ident: ref11 doi: 10.1109/MWC.101.2100269 – ident: ref15 doi: 10.1109/IConSCEPT61884.2024.10627891 – start-page: 15908 volume-title: Proc. NIPS ident: ref20 article-title: Transformer in transformer – ident: ref19 doi: 10.1109/TSP.2021.3071210 – ident: ref12 doi: 10.1109/MWC.013.2100642 – ident: ref17 doi: 10.1109/TCSVT.2021.3082521 – ident: ref22 doi: 10.1186/s40537-022-00652-w – ident: ref3 doi: 10.1109/ACCESS.2018.2879902 – year: 2022 ident: ref36 article-title: SSD: Towards better text-image consistency metric in text-to-image generation publication-title: arXiv:2210.15235 – ident: ref30 doi: 10.1109/OCEANSE.2005.1511792 – ident: ref23 doi: 10.1162/tacl_a_00477 – ident: ref27 doi: 10.7763/IJFCC.2012.V1.95 – ident: ref7 doi: 10.23919/JCC.2022.09.005 – volume: 21 start-page: 1 year: 2020 ident: ref21 article-title: Transfer learning publication-title: Learning – ident: ref35 doi: 10.1007/s11042-020-10035-z – ident: ref13 doi: 10.1109/COMST.2022.3223224 – ident: ref24 doi: 10.1109/TCCN.2024.3424842 – ident: ref1 doi: 10.1109/JIOT.2020.2993411 – ident: ref16 doi: 10.1109/TCCN.2019.2919300 – ident: ref6 doi: 10.1109/CECIT53797.2021.00088 – ident: ref28 doi: 10.1109/IWCMC51323.2021.9498601 – ident: ref18 doi: 10.1109/TWC.2023.3234408 – ident: ref29 doi: 10.1109/ACCESS.2017.2771342 – ident: ref5 doi: 10.1109/ICID52250.2020.00033 – ident: ref4 doi: 10.1109/JIOT.2022.3219674 – ident: ref9 doi: 10.1007/s11082-023-05721-9 – ident: ref2 doi: 10.1080/00207217.2019.1692373 – year: 2007 ident: ref32 article-title: Rician-k factor study for temporal and spatial variations – ident: ref33 doi: 10.1002/mop.32202 – year: 2015 ident: ref34 article-title: Density modeling of images using a generalized normalization transformation publication-title: arXiv:1511.06281 – ident: ref8 doi: 10.1007/s11082-024-07426-z – volume: 48 year: 2021 ident: ref26 article-title: A survey of maritime communications: From the wireless channel measurements and modeling perspective publication-title: Regional Stud. Mar. Sci. doi: 10.1016/j.rsma.2021.102031
SSID	ssj0019757
Score	2.4444194
Snippet	Maritime vessel networks face critical communication challenges due to severe signal attenuation induced by dynamic oceanic conditions, including vessel...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Index Database Publisher
StartPage	42251
SubjectTerms	Adaptation models Communication Computer architecture Data exchange Deep learning Encoding Feature extraction Joint source–channel coding marine communication Maritime communications maritime vessel networks Multilayers Networks Reliability Sea vessels semantic Semantic communication Semantics Sensors Signal to noise ratio Wireless communication
Title	MDJSCC: Multiscale Feature Learning-Based Semantic Communications for Maritime Vessel Networks
URI	https://ieeexplore.ieee.org/document/11187407 https://www.proquest.com/docview/3271985476
Volume	25
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/eLvHCXMwlV3PS1wxEB6qFKwHW63SVVty8FSIJnl5-eHNbpUiuBTWlj35yCYTFeoqu26h_71JNrZK6aG3d3i_mC_zZuZNvm8A9lAjRoeaco6eyoiMpixDUJdilRChZU7FMmxCDwZmNLJfK1m9cGEQsWw-w_18WHr54dbP86-yA87LBDm9BEtaqwVZ63fLwOoi65k8mFHZ6FFtYXJmD06Hx4NUCop2vyn1j3gWhMpUlb8-xSW-nLz-zzd7A2s1kSRHC-TX4QVONmD1ibzgBqzUCedXv97Cxdnn02G_f0gK43aWkEGS07_5FEnVWL2kn1JIC2SIN8nc1548I4_MSEpvyZnLIkg3SL5nzfEfZLDYRT7bhG8nx-f9L7TOVqA-ZWD3tJFBGSckRmVkYCKKoLlw3jAvlVfeGRWSuwrbWusbPU6VD2_8mDsrddRtbLZgeXI7wXdAfHQ2auNxrFoprTAheBPTAzQLDfPjHnx8NHZ3t5DQ6ErpwWyXkekyMl1Fpgeb2bp_TqyG7cHuIz5d9bJZ1wjNrWmlVtv_uGwHXuW7Z_Igb3dh-X46x_fw0v9Mlp5-KAvoAdp7w4A
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1RTxQxEJ4gmIAPoAjxBLQPPpkU2m532_oGJwSR25gcmnty02unaiKHueNM_Pe2vaIS4gNv-7Cbbubr7Mzs9PsG4BUqxGBRUc7RURmQ0ZhlCGpjrBLC18w2IQ-bUG2rRyPzoZDVMxcGEfPhM9xPl7mX76_cPP0qO-A8T5BTD2ClllKwBV3rT9PAqCzsGX2YUVmpUWlicmYOzobHbSwGRb1f5QpI3ApDea7KnY9xjjAnG_d8t8ewXlJJcrjA_gks4WQTHv0jMLgJq2XG-ddfT-Hz4O3ZsN9_QzLndhaxQZISwPkUSVFZ_UKPYlDzZIiX0eDfHLlFH5mRmOCSgU0ySJdIPiXV8e-kXZwjn23Bx5Pji_4pLdMVqIs52DWtpG-0FRJDo6VnIgivuLBOMycb1zirGx8dVpjaGFepcax9eOXG3BqpgqpDtQ3Lk6sJPgPigjVBaYfjJuJihPbe6RAXUMxXzI178PrG2N2PhYhGl4sPZrqETJeQ6QoyPdhK1v17YzFsD3Zv8OmKn826SihudC1V8_w_j72E1dOLwXl3_q59vwNraaVEJeT1LixfT-e4Bw_dz2j16Yu8mX4DMenGxw
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=MDJSCC%3A+Multiscale+Feature+Learning-Based+Semantic+Communications+for+Maritime+Vessel+Networks&rft.jtitle=IEEE+sensors+journal&rft.au=Li%2C+Shibao&rft.au=Wang%2C+Xinkun&rft.au=Li%2C+Dongyang&rft.au=Wang%2C+Chongyang&rft.date=2025-11-15&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1530-437X&rft.eissn=1558-1748&rft.volume=25&rft.issue=22&rft.spage=42251&rft.epage=42264&rft_id=info:doi/10.1109%2FJSEN.2025.3614462&rft.externalDBID=NO_FULL_TEXT
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