Incorporating both semantic level information and effectiveness level performance, the task-oriented semantic communication system has been designed for various tasks of different datatype. Although semantic communication improves the spectral utilization to some extent, indiscriminate transmission of semantic information for task-oriented semantic communication can still result in waste of wireless resources. In this paper, we propose an importance-aware joint source-channel coding (I-JSCC) framework for task-oriented semantic communications. A joint semantic-channel transmission (JSCT) mechanism is designed by selectively transmitting task-important features to reduce communication overhead. We define a new metric named task-oriented semantic spectral efficiency (TOSSE) to evaluate the effectiveness and efficiency of the proposed system, which measures the effective semantic information carried by each semantic symbol. An importance-aware semantic resource allocation problem is formulated to maximize the total TOSSE of all users by jointly optimizing the channel assignment and feature selection vector. To solve this problem, a knowledge-assisted proximal policy optimization (K-PPO) based reinforcement learning (RL) algorithm is proposed. The experimental results conducted on CIFAR100 dataset demonstrate the efficacy of the K-PPO algorithm, while also highlighting the superiority of the importance-aware semantic communication system in terms of the TOSSE.

Yining Wang

Shujun Han

Xiaodong Xu

Haotai Liang

Rui Meng

Chen Dong

Ping Zhang

IEEE Transactions on Cognitive Communications and Networking

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING (TCCN) 致力于及时出版高质量的手稿，推动认知通信和网络研究的最新发展。交易的重点将放在通信和网络控制各个方面的“认知”行为，从 PHY 功能（包括硬件）到应用程序（包括架构），以及在各种类型的通信网络和系统中，无论其类型如何流量、传输媒体、操作环境或通信设备的能力。 TCCN 将欢迎有关认知通信和网络系统的设计、分析、评估、实验和测试的论文。鼓励跨学科方法。专注于认知通信和网络的实验基础设施或工具的论文也将被考虑，前提是它们包含在通信或网络领域的重要原创贡献。

The IEEE Transactions on Cognitive Communications and Networking (TCCN) is dedicated to the timely publication of high-quality manuscripts that advance the latest developments in cognitive communications and networking research. The journal focuses on the 'cognitive' behaviors in various aspects of communication and network control, ranging from physical layer functionalities (including hardware) to applications (including architecture), applicable to various types of communication networks and systems, regardless of their traffic, transmission media, operational environments, or capabilities of communication devices. TCCN welcomes papers on the design, analysis, evaluation, experimentation, and testing of cognitive communication and networking systems, and encourages interdisciplinary approaches. Papers focusing on experimental infrastructures or tools for cognitive communications and networking will also be considered, provided they contain significant original contributions to the field of communications or networking.

《IEEE Transactions on Cognitive Communications and Networking》致力于及时出版高质量的手稿，推动认知通信和网络研究的最新发展。期刊重点关注通信和网络控制各个方面的“认知”行为，涵盖从物理层功能（包括硬件）到应用程序（包括架构）的广泛主题，适用于各种类型的通信网络和系统，无论其流量、传输媒体、操作环境或通信设备的能力如何。期刊欢迎有关认知通信和网络系统的设计、分析、评估、实验和测试的论文，并鼓励跨学科的方法。同时，专注于认知通信和网络的实验基础设施或工具的论文也将被考虑，前提是它们在通信或网络领域具有重要的原创贡献。

Category	Quartile
计算机科学	1
计算机科学, 电信学	1

Feature Importance-Aware Task-Oriented Semantic Transmission and Optimization

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info