Imagen de Portada

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

Guardado en:
Publicado en:SN Applied Sciences vol. 7, no. 11 (Nov 2025), p. 1237
Autor principal: Sesham, Srinu
Otros Autores: Suresh, Nalina, Chembe, Dickson Kanungwe
Publicado:
Springer Nature B.V.
Materias:
Wireless networks
Accuracy
Deep learning
Internet of Things
Hypothesis testing
Regression analysis
Communication
5G mobile communication
Regression models
Signal processing
Frequency ranges
Noise levels
Machine learning
Energy
Spectrum allocation
Autocorrelation
Statistical analysis
Correlation coefficients
Correlation coefficient
Learning algorithms
Fourier transforms
Sensors
Support vector machines
Methods
Eigenvalues
Performance degradation
Complexity
Signal to noise ratio
Environmental
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen: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 <inline-graphic specific-use="web" mime-subtype="GIF" xlink:href="42452_2025_7787_Article_IEq1.gif" /> 90% and <inline-graphic specific-use="web" mime-subtype="GIF" xlink:href="42452_2025_7787_Article_IEq2.gif" /> 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.Article highlights<list list-type="bullet"><list-item></list-item>New methods (ACIS & LRMS) help detect weak wireless signals even in very noisy environments.<list-item>LRMS reliably detects signals as low as − 30 dB, using simpler computations than many existing tools.</list-item><list-item>These advances support better sharing of crowded 5G frequencies, helping future&#xa0;wireless networks.</list-item>
ISSN:2523-3963
2523-3971
DOI:10.1007/s42452-025-07787-4
Fuente:Science Database