Please use this identifier to cite or link to this item: https://bura.brunel.ac.uk/handle/2438/32054
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPeng, Yubo-
dc.contributor.authorXiang, Luping-
dc.contributor.authorYang, Kun-
dc.contributor.authorJiang, Feibo-
dc.contributor.authorWang, Kezhi-
dc.contributor.authorWu, Dapeng Oliver-
dc.date.accessioned2025-09-26T19:57:11Z-
dc.date.available2025-09-26T19:57:11Z-
dc.date.issued2025-09-16-
dc.identifierORCiD: Yubo Peng https://orcid.org/0000-0001-9684-2971-
dc.identifierORCiD: Luping Xiang https://orcid.org/0000-0003-1465-6708-
dc.identifierORCiD: Kun Yang https://orcid.org/0000-0002-6782-6689-
dc.identifierORCiD: Feibo Jiang https://orcid.org/0000-0002-0235-0253-
dc.identifierORCiD: Kezhi Wang https://orcid.org/0000-0001-8602-0800-
dc.identifierORCiD: Dapeng Oliver Wu https://orcid.org/0000-0003-1755-0183-
dc.identifier.citationPeng, Y. et al. (2026) 'SIMAC: A Semantic-Driven Integrated Multimodal Sensing And Communication Framework', IEEE Journal on Selected Areas in Communications, 44, pp. 673–688. doi: 10.1109/jsac.2025.3610398.en_US
dc.identifier.issn0733-8716-
dc.identifier.urihttps://bura.brunel.ac.uk/handle/2438/32054-
dc.description.abstractTraditional unimodal sensing faces limitations in accuracy and capability, and its decoupled implementation with communication systems increases latency in bandwidth-constrained environments. Additionally, single-task-oriented sensing systems fail to address users’ diverse demands. To overcome these challenges, we propose a semantic-driven integrated multimodal sensing and communication (SIMAC) framework. This framework leverages a joint source-channel coding architecture to achieve simultaneous sensing, decoding, and transmission of sensing results. Specifically, SIMAC first introduces a multimodal semantic fusion (MSF) network, which employs two extractors to extract semantic information from radar signals and images, respectively. MSF then applies cross-attention mechanisms to fuse these unimodal features and generate multimodal semantic representations. Secondly, we present a large language model (LLM)-based semantic encoder (LSE), where relevant communication parameters and multimodal semantics are mapped into a unified latent space and input to the LLM, enabling channel-adaptive semantic encoding. Thirdly, a task-oriented sensing semantic decoder (SSD) is proposed, in which different decoded heads are designed according to the specific needs of tasks. Simultaneously, a multi-task learning strategy is introduced to train the SIMAC framework, achieving diverse sensing services. Finally, experimental simulations demonstrate that the proposed framework achieves diverse and higher-accuracy sensing services.en_US
dc.description.sponsorshipJiangsu Major Project on Fundamental Research (Grant Number: BK20243059)-
dc.description.sponsorshipGusu Innovation Project (Grant Number: ZXL2024360)-
dc.description.sponsorshipHigh-Tech District of Suzhou City (Grant Number: RC2025001)-
dc.description.sponsorship10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 62132004 and 62301122)-
dc.description.sponsorshipMajor Program Project of Xiangjiang Laboratory (Grant Number: XJ2023001 and XJ2022001)-
dc.description.sponsorship10.13039/100017413-Qiyuan Laboratory Innovation Fund (Grant Number: 2022-JCJQ-LA-001-088)-
dc.description.sponsorshipSEC-
dc.format.extentpp. 673–688-
dc.format.mediumPrint-Electronic-
dc.language.isoen_USen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.rightsRe-use licence for this version: Creative Commons Attribution 4.0 International-
dc.rightsLicence for published version: Publisher's own licence-
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/-
dc.subjectintegrated multimodal sensing and communicationsen_US
dc.subjectsemantic communicationen_US
dc.subjectlarge language modelen_US
dc.subjectmulti-task learningen_US
dc.titleSIMAC: A Semantic-Driven Integrated Multimodal Sensing And Communication Frameworken_US
dc.typeArticleen_US
dc.date.dateAccepted2025-09-07-
dc.identifier.doihttps://doi.org/10.1109/jsac.2025.3610398-
dc.relation.isPartOfIEEE Journal on Selected Areas in Communicationsen_US
pubs.publication-statusPublished-
pubs.volume44-
dc.identifier.eissn1558-0008-
dc.rights.licensehttps://creativecommons.org/licenses/by/4.0/legalcode.en-
dcterms.dateAccepted2025-09-07-
dcterms.issued2025-09-16-
dc.rights.holderThe Author(s)-
dc.contributor.orcidPeng, Yubo [0000-0001-9684-2971]-
dc.contributor.orcidXiang, Luping [0000-0003-1465-6708]-
dc.contributor.orcidYang, Kun [0000-0002-6782-6689]-
dc.contributor.orcidJiang, Feibo [0000-0002-0235-0253]-
dc.contributor.orcidWang, Kezhi [0000-0001-8602-0800]-
dc.contributor.orcidWu, Dapeng Oliver [0000-0003-1755-0183]-
Appears in Collections:Department of Computer Science Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdf“For the purpose of open access, the author(s) has applied a Creative Commons Attribution (CC BY) license to any Accepted Manuscript version arising.”7.56 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons