Data-driven machine learning techniques have been advocated for signal detection in complex wireless environments. However, when applied to wideband spectrum sensing scenarios, they face practical challenges including very large data dimensionality, insufficient training data, and implicit inter-band dependencies. Current literature focuses on deep convolutional models, whose inherent model structure is not well suited for representing the diverse spectrum occupancy patterns of practical wideband networks, causing inefficient performance-complexity tradeoff and excessive sensing time. To address these issues, this paper develops a novel Spectrum Transformer with multi-task learning for wideband spectrum sensing at high sample efficiency. Empowered by the multi-head self-attention mechanism, the transformer architecture is designed to effectively learn both the inner-band spectral features and the inter-band spectrum occupancy correlations in the wideband regime. Simulations show that the proposed Spectrum Transformer outperforms the existing methods based on convolutional neural networks especially in the small-data case, by achieving higher sensing accuracy with an 89% reduction in model complexity.

Weishan Zhang

Yue Wang

Xiang Chen

Zhipeng Cai

Zhi Tian

IEEE Transactions on Wireless Communications

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 发表了有关无线通信最新技术进展的高质量手稿。鼓励理论贡献（包括新技术、概念和分析）和实践贡献（包括系统实验和原型以及新应用）。交易的一般范围包括但不限于以下内容：调制和编码、检测和估计、分集技术和均衡、传播和信道表征、衰落对策、多用户检测、信号分离和干扰抑制、DSP 应用到无线系统、宽带无线通信、网络架构和协议，重点是物理和链路层通信、无线系统的自适应天线、多址技术、时空处理、同步技术、软件无线电、资源分配和干扰管理、多速率和多载波通信、安全、隐私和身份验证、实验和原型结果、系统和服务，包括移动卫星、无线本地环路、无线局域网、无线 PBX 和 PCS/蜂窝。此外，关于特定主题或更多非与特定应用相关的传统主题关于领域，值得鼓励。示例包括用于设计、分析、快速原型制作、性能预测和蜂窝系统工程的仿真工具和方法；正交频分复用； MIMO 系统，以及基于光纤的无线。

The IEEE Transactions on Wireless Communications publishes high-quality manuscripts on the latest advancements in wireless communication technologies. We encourage theoretical contributions (including new technologies, concepts, and analyses) as well as practical contributions (including system experiments, prototypes, and new applications). The general scope of the journal includes, but is not limited to, the following topics: modulation and coding, detection and estimation, diversity techniques and equalization, propagation and channel characterization, fading mitigation, multi-user detection, signal separation and interference suppression, DSP applications to wireless systems, broadband wireless communications, network architectures and protocols, with a focus on physical and link layer communications, adaptive antennas for wireless systems, multiple access techniques, space-time processing, synchronization techniques, software-defined radio, resource allocation and interference management, multi-rate and multi-carrier communications, security, privacy, and authentication, experimental and prototype results, systems and services, including mobile satellite, wireless local loop, wireless LAN, wireless PBX, and PCS/cellular. Additionally, we encourage research on specific topics or more traditional themes not necessarily tied to specific applications. Examples include simulation tools and methods for design, analysis, rapid prototyping, performance prediction, and cellular system engineering; orthogonal frequency division multiplexing; MIMO systems; and fiber-based wireless.

《IEEE Transactions on Wireless Communications》发表关于无线通信最新技术进展的高质量手稿。我们鼓励理论贡献（包括新技术、概念和分析）以及实践贡献（包括系统实验、原型和新应用）。期刊的范围包括但不限于以下内容：调制与编码、检测与估计、分集技术与均衡、传播与信道特征、衰落对策、多用户检测、信号分离与干扰抑制、数字信号处理在无线系统中的应用、宽带无线通信、网络架构与协议，重点关注物理层和链路层通信、无线系统的自适应天线、多址技术、时空处理、同步技术、软件无线电、资源分配与干扰管理、多速率与多载波通信、安全、隐私与身份验证、实验与原型结果、系统与服务，包括移动卫星、无线本地环路、无线局域网、无线PBX和PCS/蜂窝。此外，我们也鼓励关于特定主题或更传统的非特定应用相关领域的研究。示例包括用于设计、分析、快速原型制作、性能预测和蜂窝系统工程的仿真工具和方法；正交频分复用；MIMO系统，以及基于光纤的无线。

Category	Quartile
计算机科学	1
计算机科学, 工程电子与电气	1
计算机科学, 电信学	1

Spectrum Transformer: An Attention-Based Wideband Spectrum Detector

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

Journal Info