Cargando…

CM-LSTM Based Spectrum Sensing

This paper presents spectrum sensing as a classification problem, and uses a spectrum-sensing algorithm based on a signal covariance matrix and long short-term memory network (CM-LSTM). We jointly exploited the spatial cross-correlation of multiple signals received by the antenna array and the tempo...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Wantong, Wu, Hailong, Ren, Shiyu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8953494/
https://www.ncbi.nlm.nih.gov/pubmed/35336457
http://dx.doi.org/10.3390/s22062286
_version_ 1784675864838930432
author Chen, Wantong
Wu, Hailong
Ren, Shiyu
author_facet Chen, Wantong
Wu, Hailong
Ren, Shiyu
author_sort Chen, Wantong
collection PubMed
description This paper presents spectrum sensing as a classification problem, and uses a spectrum-sensing algorithm based on a signal covariance matrix and long short-term memory network (CM-LSTM). We jointly exploited the spatial cross-correlation of multiple signals received by the antenna array and the temporal autocorrelation of single signals; we used the long short-term memory network (LSTM), which is good at extracting temporal correlation features, as the classification model; we then input the covariance matrix of the signals received by the array into the LSTM classification model to achieve the fusion learning of spatial correlation features and temporal correlation features of the signals, thus significantly improving the performance of spectrum sensing. Simulation analysis shows that the CM-LSTM-based spectrum-sensing algorithm shows better performance compared with support vector machine (SVM), gradient boosting machine (GBM), random forest (RF), and energy detection (ED) algorithm-based spectrum-sensing algorithms for different signal-to-noise ratios (SNRs) and different numbers of secondary users (SUs). Among them, SVM is a classical machine-learning algorithm, GBM and RF are two integrated learning methods with better generalization capability, and ED is a classical, traditional, and spectrum-sensing algorithm.
format Online
Article
Text
id pubmed-8953494
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89534942022-03-26 CM-LSTM Based Spectrum Sensing Chen, Wantong Wu, Hailong Ren, Shiyu Sensors (Basel) Article This paper presents spectrum sensing as a classification problem, and uses a spectrum-sensing algorithm based on a signal covariance matrix and long short-term memory network (CM-LSTM). We jointly exploited the spatial cross-correlation of multiple signals received by the antenna array and the temporal autocorrelation of single signals; we used the long short-term memory network (LSTM), which is good at extracting temporal correlation features, as the classification model; we then input the covariance matrix of the signals received by the array into the LSTM classification model to achieve the fusion learning of spatial correlation features and temporal correlation features of the signals, thus significantly improving the performance of spectrum sensing. Simulation analysis shows that the CM-LSTM-based spectrum-sensing algorithm shows better performance compared with support vector machine (SVM), gradient boosting machine (GBM), random forest (RF), and energy detection (ED) algorithm-based spectrum-sensing algorithms for different signal-to-noise ratios (SNRs) and different numbers of secondary users (SUs). Among them, SVM is a classical machine-learning algorithm, GBM and RF are two integrated learning methods with better generalization capability, and ED is a classical, traditional, and spectrum-sensing algorithm. MDPI 2022-03-16 /pmc/articles/PMC8953494/ /pubmed/35336457 http://dx.doi.org/10.3390/s22062286 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chen, Wantong
Wu, Hailong
Ren, Shiyu
CM-LSTM Based Spectrum Sensing
title CM-LSTM Based Spectrum Sensing
title_full CM-LSTM Based Spectrum Sensing
title_fullStr CM-LSTM Based Spectrum Sensing
title_full_unstemmed CM-LSTM Based Spectrum Sensing
title_short CM-LSTM Based Spectrum Sensing
title_sort cm-lstm based spectrum sensing
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8953494/
https://www.ncbi.nlm.nih.gov/pubmed/35336457
http://dx.doi.org/10.3390/s22062286
work_keys_str_mv AT chenwantong cmlstmbasedspectrumsensing
AT wuhailong cmlstmbasedspectrumsensing
AT renshiyu cmlstmbasedspectrumsensing