Scholarlink

<p>Spectrum sensing is essential for cognitive radio networks, especially under secondary user (SU) mobility, which can degrade sensing performance. To address this, we propose a novel classifier that integrates a pilot-assisted autoregressive moving average (ARMA) Kalman filter to accurately track channel gain variations between mobile SUs and primary users (PUs). The estimated channel gain is used to adaptively update cluster centroids in a K-means clustering framework, where SU energy serves as the feature vector for classifying PU activity. The proposed method enhances the reliability of cooperative spectrum sensing under mobility conditions. Simulation results validate its superior performance over existing techniques.</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

Enhanced cooperative spectrum sensing analysis with autoregressive moving average-based Kalman filter channel estimation and machine learning

  • 期刊论文

  • 发表日期：

    2025年8月29日

查看全文
  • Srinivas Samala,
  • Ch. Rajendra Prasad,
  • Subhashree Mishra,
  • Sudhansu Sekhar Singh

摘要

Spectrum sensing is essential for cognitive radio networks, especially under secondary user (SU) mobility, which can degrade sensing performance. To address this, we propose a novel classifier that integrates a pilot-assisted autoregressive moving average (ARMA) Kalman filter to accurately track channel gain variations between mobile SUs and primary users (PUs). The estimated channel gain is used to adaptively update cluster centroids in a K-means clustering framework, where SU energy serves as the feature vector for classifying PU activity. The proposed method enhances the reliability of cooperative spectrum sensing under mobility conditions. Simulation results validate its superior performance over existing techniques.