Spectrum Sensing for Noncircular Signals Using Augmented Covariance-Matrix-Aware Deep Convolutional Neural Network

This work investigates spectrum sensing in cognitive radio networks, where multi-antenna secondary users aim to detect the spectral occupancy of noncircular signals transmitted by primary users. Specifically, we propose a deep-learning-based spectrum sensing approach using an augmented covariance-ma...

Full description

Saved in:
Bibliographic Details
Main Authors: Songlin Chen, Zhenqing He, Wenze Song, Guohao Sun
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4791
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239743456346112
author Songlin Chen
Zhenqing He
Wenze Song
Guohao Sun
author_facet Songlin Chen
Zhenqing He
Wenze Song
Guohao Sun
author_sort Songlin Chen
collection DOAJ
description This work investigates spectrum sensing in cognitive radio networks, where multi-antenna secondary users aim to detect the spectral occupancy of noncircular signals transmitted by primary users. Specifically, we propose a deep-learning-based spectrum sensing approach using an augmented covariance-matrix-aware convolutional neural network (CNN). The core innovation of our approach lies in employing an augmented sample covariance matrix, which integrates both a standard covariance matrix and complementary covariance matrix, thereby fully exploiting the statistical properties of noncircular signals. By feeding augmented sample covariance matrices into the designed CNN architecture, the proposed approach effectively learns discriminative patterns from the underlying data structure, without stringent model constraints. Meanwhile, our approach eliminates the need for restrictive model assumptions and significantly enhances the detection performance by fully exploiting noncircular signal characteristics. Various experimental results demonstrate the significant performance improvement and generalization capability of the proposed approach compared to existing benchmark methods.
format Article
id doaj-art-a842b8f9909d4798bcaddc90f4dedba3
institution Kabale University
issn 1424-8220
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-a842b8f9909d4798bcaddc90f4dedba32025-08-20T04:00:51ZengMDPI AGSensors1424-82202025-08-012515479110.3390/s25154791Spectrum Sensing for Noncircular Signals Using Augmented Covariance-Matrix-Aware Deep Convolutional Neural NetworkSonglin Chen0Zhenqing He1Wenze Song2Guohao Sun3Southwest China Institute of Electronic Technology, Chengdu 610036, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, ChinaThis work investigates spectrum sensing in cognitive radio networks, where multi-antenna secondary users aim to detect the spectral occupancy of noncircular signals transmitted by primary users. Specifically, we propose a deep-learning-based spectrum sensing approach using an augmented covariance-matrix-aware convolutional neural network (CNN). The core innovation of our approach lies in employing an augmented sample covariance matrix, which integrates both a standard covariance matrix and complementary covariance matrix, thereby fully exploiting the statistical properties of noncircular signals. By feeding augmented sample covariance matrices into the designed CNN architecture, the proposed approach effectively learns discriminative patterns from the underlying data structure, without stringent model constraints. Meanwhile, our approach eliminates the need for restrictive model assumptions and significantly enhances the detection performance by fully exploiting noncircular signal characteristics. Various experimental results demonstrate the significant performance improvement and generalization capability of the proposed approach compared to existing benchmark methods.https://www.mdpi.com/1424-8220/25/15/4791cognitive radioconvolutional neural networkdeep learningnoncircular signalspectrum sensing
spellingShingle Songlin Chen
Zhenqing He
Wenze Song
Guohao Sun
Spectrum Sensing for Noncircular Signals Using Augmented Covariance-Matrix-Aware Deep Convolutional Neural Network
Sensors
cognitive radio
convolutional neural network
deep learning
noncircular signal
spectrum sensing
title Spectrum Sensing for Noncircular Signals Using Augmented Covariance-Matrix-Aware Deep Convolutional Neural Network
title_full Spectrum Sensing for Noncircular Signals Using Augmented Covariance-Matrix-Aware Deep Convolutional Neural Network
title_fullStr Spectrum Sensing for Noncircular Signals Using Augmented Covariance-Matrix-Aware Deep Convolutional Neural Network
title_full_unstemmed Spectrum Sensing for Noncircular Signals Using Augmented Covariance-Matrix-Aware Deep Convolutional Neural Network
title_short Spectrum Sensing for Noncircular Signals Using Augmented Covariance-Matrix-Aware Deep Convolutional Neural Network
title_sort spectrum sensing for noncircular signals using augmented covariance matrix aware deep convolutional neural network
topic cognitive radio
convolutional neural network
deep learning
noncircular signal
spectrum sensing
url https://www.mdpi.com/1424-8220/25/15/4791
work_keys_str_mv AT songlinchen spectrumsensingfornoncircularsignalsusingaugmentedcovariancematrixawaredeepconvolutionalneuralnetwork
AT zhenqinghe spectrumsensingfornoncircularsignalsusingaugmentedcovariancematrixawaredeepconvolutionalneuralnetwork
AT wenzesong spectrumsensingfornoncircularsignalsusingaugmentedcovariancematrixawaredeepconvolutionalneuralnetwork
AT guohaosun spectrumsensingfornoncircularsignalsusingaugmentedcovariancematrixawaredeepconvolutionalneuralnetwork