Scholarlink

<p>Unmanned aerial vehicles (UAVs) play a vital role in various civilian and commercial applications, necessitating accurate classification of their radio frequency (RF) signals. Current deep learning-based approaches struggle with high computational complexity, susceptibility to noise, and limited accuracy. This paper introduces a novel UAV signal classification framework that combines wavelet-based feature extraction with a hierarchical U-Net architecture, enhanced by split-time cross attention (STCA) and residual connectivity. The WUSTCA model effectively classifies UAV and controller signals, achieving an average classification accuracy of 96.6% for UAVs and 95.83% for UAV controllers on the CardRF dataset. By addressing challenges such as noise interference and signal diversity, this work provides a reliable and efficient solution for UAV signal classification, paving the way for real-time applications in complex environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

WUSTCA: enhanced UAV RF signal classification with wavelet transform and STCA attention mechanisms

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月2日

查看全文
  • Jiyu Liu,
  • Zaolin Xia,
  • Yuhui Chen,
  • Hanning Sun,
  • Shu Huang

摘要

Unmanned aerial vehicles (UAVs) play a vital role in various civilian and commercial applications, necessitating accurate classification of their radio frequency (RF) signals. Current deep learning-based approaches struggle with high computational complexity, susceptibility to noise, and limited accuracy. This paper introduces a novel UAV signal classification framework that combines wavelet-based feature extraction with a hierarchical U-Net architecture, enhanced by split-time cross attention (STCA) and residual connectivity. The WUSTCA model effectively classifies UAV and controller signals, achieving an average classification accuracy of 96.6% for UAVs and 95.83% for UAV controllers on the CardRF dataset. By addressing challenges such as noise interference and signal diversity, this work provides a reliable and efficient solution for UAV signal classification, paving the way for real-time applications in complex environments.