arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.09595eess.SPcs.AI
收藏

通过分子构建语义通信系统:一种端到端训练方法

Building Semantic Communication System via Molecules: An End-to-End Training Approach

School of Electronic and Information Engineering(电子与信息工程学院);Beijing Jiaotong University(北京交通大学)

Yukun Cheng, Wei Chen, Bo Ai

AI总结:

针对通信资源受限场景,本文提出端到端语义分子通信系统,采用联合信源信道编码将任务信息编码为分子浓度,设计信道网络实现不可微分信道的端到端学习,在分类任务中性能优于传统方法。

摘要:

语义通信的概念为通信资源受限场景下的应用提供了一种新途径。本文提出了一种端到端(E2E)语义分子通信系统,旨在通过减少传输信息量来提升分子通信系统的效率。具体而言,该网络遵循联合信源信道编码范式,将与任务相关的信息编码为信息分子的浓度,该浓度对分子通信信道的劣化具有鲁棒性。此外,我们提出了一种信道网络,以实现不可微分分子信道上的端到端学习。实验结果表明,在分类任务中,该语义分子通信系统的性能优于传统方法。

英文摘要:

The concept of semantic communication provides a novel approach for applications in scenarios with limited communication resources. In this paper, we propose an end-to-end (E2E) semantic molecular communication system, aiming to enhance the efficiency of molecular communication systems by reducing the transmitted information. Specifically, following the joint source channel coding paradigm, the network is designed to encode the task-relevant information into the concentration of the information molecules, which is robust to the degradation of the molecular communication channel. Furthermore, we propose a channel network to enable the E2E learning over the non-differentiable molecular channel. Experimental results demonstrate the superior performance of the semantic molecular communication system over the conventional methods in classification tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑