计算机科学
卷积神经网络
卷积码
稳健性(进化)
无线
软件无线电
计算机工程
人工智能
计算机体系结构
解码方法
电信
生物化学
化学
基因
作者
Han-Ju Yoo,Linglong Dai,Songkuk Kim,Chan‐Byoung Chae
出处
期刊:IEEE Access
[Institute of Electrical and Electronics Engineers]
日期:2023-01-01
卷期号:11: 71528-71541
被引量:14
标识
DOI:10.1109/access.2023.3291405
摘要
Semantic communications have shown promising advancements by optimizing source and channel coding jointly. However, the dynamics of these systems remain understudied, limiting research and performance gains. Inspired by the robustness of Vision Transformers (ViTs) in handling image nuisances, we propose a ViT-based model for semantic communications. Our approach achieves a peak signal-to-noise ratio (PSNR) gain of +0.5 dB over convolutional neural network variants. We introduce novel measures, average cosine similarity and Fourier analysis, to analyze the inner workings of semantic communications and optimize the system's performance. We also validate our approach through a real wireless channel prototype using software-defined radio (SDR). To the best of our knowledge, this is the first investigation of the fundamental workings of a semantic communications system, accompanied by the pioneering hardware implementation. To facilitate reproducibility and encourage further research, we provide open-source code, including neural network implementations and LabVIEW codes for SDR-based wireless transmission systems.
科研通智能强力驱动
Strongly Powered by AbleSci AI