Reconfigurable intelligent surface assisted semantic communication systems

Jiajia SHI, Tse Tin David CHAN, Haoyuan PAN, Tat-Ming LOK

Research output: Chapter in Book/Report/Conference proceedingChapters

Abstract

Semantic communication, which focuses on conveying the meaning of information rather than exact bit reconstruction, has gained considerable attention in recent years. Meanwhile, reconfigurable intelligent surface (RIS) is a promising technology that can achieve high spectral and energy efficiency by dynamically reflecting incident signals through programmable passive components. In this paper, we put forth a semantic communication scheme aided by RIS. Using text transmission as an example, experimental results demonstrate that the RIS-Assisted semantic communication system outperforms the point-To-point semantic communication system in terms of bilingual evaluation understudy (BLEU) scores in Rayleigh fading channels, especially at low signal-To-noise ratio (SNR) regimes. In addition, the RIS-Assisted semantic communication system exhibits superior robustness against channel estimation errors compared to its point-To-point counterpart. RIS can improve performance as it provides extra line-of-sight (LoS) paths and enhances signal propagation conditions compared to point-To-point systems. Copyright © 2023 IEEE.

Original languageEnglish
Title of host publicationProceedings of 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023
PublisherIEEE
ISBN (Electronic)9798350316728
DOIs
Publication statusPublished - 2023

Citation

Shi, J., Chan, T.-T., Pan, H., & Lok, T.-M. (2023). Reconfigurable intelligent surface assisted semantic communication systems. In Proceedings of 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023. IEEE. https://doi.org/10.1109/ICSPCC59353.2023.10400366

Fingerprint

Dive into the research topics of 'Reconfigurable intelligent surface assisted semantic communication systems'. Together they form a unique fingerprint.