Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/27172
Title: | Large AI Model-Based Semantic Communications |
Authors: | Jiang, F Peng, Y Dong, L Wang, K Yang, K Pan, C You, X |
Keywords: | semantic communication;large AI models;knowledge base;artificial intelligence (cs.AI);networking and internet architecture (cs.NI) |
Issue Date: | 14-Jun-2024 |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Citation: | Jiang, F. et al. (2024) 'Large AI Model-Based Semantic Communications', IEEE Wireless Communications, 31 (3), pp. 68 - 75. doi: 10.1109/MWC.001.2300346. |
Abstract: | Semantic communication (SC) is an emerging intelligent paradigm, offering solutions for various future applications like metaverse, mixed reality, and the Internet of everything. However, in current SC systems, the construction of the knowledge base (KB) faces several issues, including limited knowledge representation, frequent knowledge updates, and insecure knowledge sharing. Fortunately, the development of the large AI model (LAM) provides new solutions to overcome the above issues. Here, we propose a LAM-based SC framework (LAM-SC) specifically designed for image data, where we first apply the segment anything model (SAM)-based KB (SKB) that can split the original image into different semantic segments by universal semantic knowledge. Then, we present an attention-based semantic integration (ASI) to weigh the semantic segments generated by SKB without human participation and integrate them as the semantic-aware image. Additionally, we propose an adaptive semantic compression (ASC) encoding to remove redundant information in semantic features, thereby reducing communication overhead. Finally, through simulations, we demonstrate the effectiveness of the LAM-SC framework and the possibility of applying the LAM-based KB in future SC paradigms. |
Description: | The article version on this institutional repository is available at arXiv:2307.03492v2 [cs.AI], https://arxiv.org/abs/2307.03492 (Sat, 3 Aug 2024 13:59:24 UTC (14,879 KB)). The source code of this article is available at: https://github.com/jiangfeibo/LAMSC.git . |
URI: | https://bura.brunel.ac.uk/handle/2438/27172 |
DOI: | https://doi.org/10.1109/MWC.001.2300346 |
ISSN: | 1536-1284 |
Other Identifiers: | ORCiD: Kezhi Wang https://orcid.org/0000-0001-8602-0800 arXiv:2307.03492v2 [cs.AI] |
Appears in Collections: | Dept of Computer Science Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | The article version on this institutional repository is available at arXiv:2307.03492v2 [cs.AI], https://arxiv.org/abs/2307.03492. Comments: accepted by IEEE WCM. [v2] Sat, 3 Aug 2024 13:59:24 UTC (14,879 KB). Copyright © 2024 The Author(s). arXiv.org perpetual, non-exclusive license 1.0 (https://arxiv.org/licenses/nonexclusive-distrib/1.0/). This license gives limited rights to arXiv to distribute the article, and also limits re-use of any type from other entities or individuals. | 3.73 MB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.