Deep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier

Some bands in the frequency spectrum have become overloaded and others underutilized due to the considerable increase in demand and user allocation policy. Cognitive radio applies detection techniques to dynamically allocate unlicensed users. Cooperative spectrum sensing is currently showing promisi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Myke D. M. Valadão, Diego Amoedo, André Costa, Celso Carvalho, Waldir Sabino
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	cooperative spectrum sensing residual neural network cognitive radio Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/209a0f45c06a460b915530ec60dd4e6b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:209a0f45c06a460b915530ec60dd4e6b
record_format	dspace
spelling	oai:doaj.org-article:209a0f45c06a460b915530ec60dd4e6b2021-11-11T19:08:32ZDeep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier10.3390/s212171461424-8220https://doaj.org/article/209a0f45c06a460b915530ec60dd4e6b2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7146https://doaj.org/toc/1424-8220Some bands in the frequency spectrum have become overloaded and others underutilized due to the considerable increase in demand and user allocation policy. Cognitive radio applies detection techniques to dynamically allocate unlicensed users. Cooperative spectrum sensing is currently showing promising results. Therefore, in this work, we propose a cooperative spectrum detection system based on a residual neural network architecture combined with feature extractor and random forest classifier. The objective of this paper is to propose a cooperative spectrum sensing approach that can achieve high accuracy in higher levels of noise power density with less unlicensed users cooperating in the system. Therefore, we propose to extract features of the sensing information of each unlicensed user, then we use a random forest to classify if there is a presence of a licensed user in each band analyzed by the unlicensed user. Then, information from several unlicensed users are shared to a fusion center, where the decision about the presence or absence of a licensed user is accomplished by a model trained by a residual neural network. In our work, we achieved a high level of accuracy even when the noise power density is high, which means that our proposed approach is able to recognize the presence of a licensed user in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>98</mn><mo>%</mo></mrow></semantics></math></inline-formula> of the cases when the evaluated channel suffers a high level of noise power density (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>−</mo><mn>134</mn></mrow></semantics></math></inline-formula> dBm/Hz). This result was achieved with the cooperation of 10 unlicensed users.Myke D. M. ValadãoDiego AmoedoAndré CostaCelso CarvalhoWaldir SabinoMDPI AGarticlecooperative spectrum sensingresidual neural networkcognitive radioChemical technologyTP1-1185ENSensors, Vol 21, Iss 7146, p 7146 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	cooperative spectrum sensing residual neural network cognitive radio Chemical technology TP1-1185
spellingShingle	cooperative spectrum sensing residual neural network cognitive radio Chemical technology TP1-1185 Myke D. M. Valadão Diego Amoedo André Costa Celso Carvalho Waldir Sabino Deep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier
description	Some bands in the frequency spectrum have become overloaded and others underutilized due to the considerable increase in demand and user allocation policy. Cognitive radio applies detection techniques to dynamically allocate unlicensed users. Cooperative spectrum sensing is currently showing promising results. Therefore, in this work, we propose a cooperative spectrum detection system based on a residual neural network architecture combined with feature extractor and random forest classifier. The objective of this paper is to propose a cooperative spectrum sensing approach that can achieve high accuracy in higher levels of noise power density with less unlicensed users cooperating in the system. Therefore, we propose to extract features of the sensing information of each unlicensed user, then we use a random forest to classify if there is a presence of a licensed user in each band analyzed by the unlicensed user. Then, information from several unlicensed users are shared to a fusion center, where the decision about the presence or absence of a licensed user is accomplished by a model trained by a residual neural network. In our work, we achieved a high level of accuracy even when the noise power density is high, which means that our proposed approach is able to recognize the presence of a licensed user in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>98</mn><mo>%</mo></mrow></semantics></math></inline-formula> of the cases when the evaluated channel suffers a high level of noise power density (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>−</mo><mn>134</mn></mrow></semantics></math></inline-formula> dBm/Hz). This result was achieved with the cooperation of 10 unlicensed users.
format	article
author	Myke D. M. Valadão Diego Amoedo André Costa Celso Carvalho Waldir Sabino
author_facet	Myke D. M. Valadão Diego Amoedo André Costa Celso Carvalho Waldir Sabino
author_sort	Myke D. M. Valadão
title	Deep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier
title_short	Deep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier
title_full	Deep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier
title_fullStr	Deep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier
title_full_unstemmed	Deep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier
title_sort	deep cooperative spectrum sensing based on residual neural network using feature extraction and random forest classifier
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/209a0f45c06a460b915530ec60dd4e6b
work_keys_str_mv	AT mykedmvaladao deepcooperativespectrumsensingbasedonresidualneuralnetworkusingfeatureextractionandrandomforestclassifier AT diegoamoedo deepcooperativespectrumsensingbasedonresidualneuralnetworkusingfeatureextractionandrandomforestclassifier AT andrecosta deepcooperativespectrumsensingbasedonresidualneuralnetworkusingfeatureextractionandrandomforestclassifier AT celsocarvalho deepcooperativespectrumsensingbasedonresidualneuralnetworkusingfeatureextractionandrandomforestclassifier AT waldirsabino deepcooperativespectrumsensingbasedonresidualneuralnetworkusingfeatureextractionandrandomforestclassifier
_version_	1718431572327137280

Deep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier

Ejemplares similares