SAFE: Semantic Adaptive Feature Extraction with Rate Control for 6G Wireless Communications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Yuna, Li, Lixin, Zhang, Xin, Lin, Wensheng, Cheng, Wenchi, Han, Zhu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910628863541248
author Yan, Yuna
Li, Lixin
Zhang, Xin
Lin, Wensheng
Cheng, Wenchi
Han, Zhu
author_facet Yan, Yuna
Li, Lixin
Zhang, Xin
Lin, Wensheng
Cheng, Wenchi
Han, Zhu
contents Most current Deep Learning-based Semantic Communication (DeepSC) systems are designed and trained exclusively for particular single-channel conditions, which restricts their adaptability and overall bandwidth utilization. To address this, we propose an innovative Semantic Adaptive Feature Extraction (SAFE) framework, which significantly improves bandwidth efficiency by allowing users to select different sub-semantic combinations based on their channel conditions. This paper also introduces three advanced learning algorithms to optimize the performance of SAFE framework as a whole. Through a series of simulation experiments, we demonstrate that the SAFE framework can effectively and adaptively extract and transmit semantics under different channel bandwidth conditions, of which effectiveness is verified through objective and subjective quality evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01597
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAFE: Semantic Adaptive Feature Extraction with Rate Control for 6G Wireless Communications
Yan, Yuna
Li, Lixin
Zhang, Xin
Lin, Wensheng
Cheng, Wenchi
Han, Zhu
Networking and Internet Architecture
Machine Learning
Signal Processing
Most current Deep Learning-based Semantic Communication (DeepSC) systems are designed and trained exclusively for particular single-channel conditions, which restricts their adaptability and overall bandwidth utilization. To address this, we propose an innovative Semantic Adaptive Feature Extraction (SAFE) framework, which significantly improves bandwidth efficiency by allowing users to select different sub-semantic combinations based on their channel conditions. This paper also introduces three advanced learning algorithms to optimize the performance of SAFE framework as a whole. Through a series of simulation experiments, we demonstrate that the SAFE framework can effectively and adaptively extract and transmit semantics under different channel bandwidth conditions, of which effectiveness is verified through objective and subjective quality evaluations.
title SAFE: Semantic Adaptive Feature Extraction with Rate Control for 6G Wireless Communications
topic Networking and Internet Architecture
Machine Learning
Signal Processing
url https://arxiv.org/abs/2410.01597