Scholarlink

<p>The rapid expansion of 5G networks and Internet-connected wireless devices (such as IoT) has led to intensified spectrum congestion in the Fifth Generation New Radio Frequency Range 1 (5G NR FR1). Efficient spectrum utilization through effective spectrum-sharing solutions is crucial for seamless 5G and Next-Generation (Next-Gen) wireless networks. The statistical/signal processing based sensing methods that allow new wireless devices for spectrum sharing are facing challenges such as uncertain thresholds and degraded performance under high noise levels relative to the signal. Alternatively, machine and deep learning-based spectrum sensing models demonstrate better performance which is independent of detection threshold, but requires large datasets for model training. This paper investigates the applications of frequency-domain auto-correlation coefficients to develop novel sensing methods, namely Auto-Correlation Integral-based Sensing (ACIS) and Logistic Regression Model-based Sensing (LRMS). The work also compares their detection performance and computational complexity against other prominent techniques in the literature. Results and analysis show that ACIS achieves the recommended detector performance <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="42452_2025_7787_Article_IEq1.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="46" /> </InlineMediaObject> <EquationSource Format="TEX">\((P_d \ge\)</EquationSource> </InlineEquation> 90% and <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="42452_2025_7787_Article_IEq2.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="41" /> </InlineMediaObject> <EquationSource Format="TEX">\(P_f \le\)</EquationSource> </InlineEquation> 10%) at a very low signal-to-noise ratio (SNR) value of − 18 dB, using a correlation vector size (<i>N</i>) of 512 with a model complexity of <i>O</i>(<i>NlogN</i>). Whereas LRMS shows superior performance and can detect − 30 dB signals using a correlation vector size of 512 and a model complexity of <i>O</i>(<i>N</i>). The proposed methods outperform most existing signal processing and machine learning-based detectors in the literature.</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

Development of signal processing and machine learning methods for spectrum sensing using autocorrelation features

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月17日

查看全文
  • Srinu Sesham,
  • Nalina Suresh,
  • Dickson Kanungwe Chembe

摘要

The rapid expansion of 5G networks and Internet-connected wireless devices (such as IoT) has led to intensified spectrum congestion in the Fifth Generation New Radio Frequency Range 1 (5G NR FR1). Efficient spectrum utilization through effective spectrum-sharing solutions is crucial for seamless 5G and Next-Generation (Next-Gen) wireless networks. The statistical/signal processing based sensing methods that allow new wireless devices for spectrum sharing are facing challenges such as uncertain thresholds and degraded performance under high noise levels relative to the signal. Alternatively, machine and deep learning-based spectrum sensing models demonstrate better performance which is independent of detection threshold, but requires large datasets for model training. This paper investigates the applications of frequency-domain auto-correlation coefficients to develop novel sensing methods, namely Auto-Correlation Integral-based Sensing (ACIS) and Logistic Regression Model-based Sensing (LRMS). The work also compares their detection performance and computational complexity against other prominent techniques in the literature. Results and analysis show that ACIS achieves the recommended detector performance \((P_d \ge\) 90% and \(P_f \le\) 10%) at a very low signal-to-noise ratio (SNR) value of − 18 dB, using a correlation vector size (N) of 512 with a model complexity of O(NlogN). Whereas LRMS shows superior performance and can detect − 30 dB signals using a correlation vector size of 512 and a model complexity of O(N). The proposed methods outperform most existing signal processing and machine learning-based detectors in the literature.