Scholarlink

<p>Signal jamming is a significant challenge that can critically impair&#xa0;radar performance and detection accuracy. Identifying and classifying these disruptive signals are critical first steps toward mitigating their effects. Additional information about the jamming signal can significantly improve the classification process. Various techniques have been used for signal classification, but recent advances in machine learning-based methods have proven to be more effective at identifying and classifying these signals. This study presents a novel approach for identifying multiple jamming signals from six different types at the same time using region-based machine learning techniques. This differs from previous methods, which could only classify a single signal jammer in a Range Doppler Map. Our method significantly improves radar system performance, achieving an average accuracy of 94%. Moreover, it extracts valuable information from jamming&#xa0;signals, allowing for more effective and precise countermeasures.</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

Detection of Multiple Jamming Signals Using Range Doppler Map Images

  • 期刊论文

  • 发表日期：

    2025年7月1日

查看全文
  • S. Mohsen Datli Beki,
  • Hossein Soleimani

摘要

Signal jamming is a significant challenge that can critically impair radar performance and detection accuracy. Identifying and classifying these disruptive signals are critical first steps toward mitigating their effects. Additional information about the jamming signal can significantly improve the classification process. Various techniques have been used for signal classification, but recent advances in machine learning-based methods have proven to be more effective at identifying and classifying these signals. This study presents a novel approach for identifying multiple jamming signals from six different types at the same time using region-based machine learning techniques. This differs from previous methods, which could only classify a single signal jammer in a Range Doppler Map. Our method significantly improves radar system performance, achieving an average accuracy of 94%. Moreover, it extracts valuable information from jamming signals, allowing for more effective and precise countermeasures.