Cargando…

Centroid Optimization of DNN Classification in DOA Estimation for UAV

Classifications based on deep learning have been widely applied in the estimation of the direction of arrival (DOA) of signal. Due to the limited number of classes, the classification of DOA cannot satisfy the required prediction accuracy of signals from random azimuth in real applications. This pap...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Long, Zhang, Zidan, Yang, Xu, Xu, Lu, Chen, Shuyu, Zhang, Yong, Zhang, Jianlong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007322/
https://www.ncbi.nlm.nih.gov/pubmed/36904717
http://dx.doi.org/10.3390/s23052513
_version_ 1784905491992805376
author Wu, Long
Zhang, Zidan
Yang, Xu
Xu, Lu
Chen, Shuyu
Zhang, Yong
Zhang, Jianlong
author_facet Wu, Long
Zhang, Zidan
Yang, Xu
Xu, Lu
Chen, Shuyu
Zhang, Yong
Zhang, Jianlong
author_sort Wu, Long
collection PubMed
description Classifications based on deep learning have been widely applied in the estimation of the direction of arrival (DOA) of signal. Due to the limited number of classes, the classification of DOA cannot satisfy the required prediction accuracy of signals from random azimuth in real applications. This paper presents a Centroid Optimization of deep neural network classification (CO-DNNC) to improve the estimation accuracy of DOA. CO-DNNC includes signal preprocessing, classification network, and Centroid Optimization. The DNN classification network adopts a convolutional neural network, including convolutional layers and fully connected layers. The Centroid Optimization takes the classified labels as the coordinates and calculates the azimuth of received signal according to the probabilities of the Softmax output. The experimental results show that CO-DNNC is capable of acquiring precise and accurate estimation of DOA, especially in the cases of low SNRs. In addition, CO-DNNC requires lower numbers of classes under the same condition of prediction accuracy and SNR, which reduces the complexity of the DNN network and saves training and processing time.
format Online
Article
Text
id pubmed-10007322
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100073222023-03-12 Centroid Optimization of DNN Classification in DOA Estimation for UAV Wu, Long Zhang, Zidan Yang, Xu Xu, Lu Chen, Shuyu Zhang, Yong Zhang, Jianlong Sensors (Basel) Article Classifications based on deep learning have been widely applied in the estimation of the direction of arrival (DOA) of signal. Due to the limited number of classes, the classification of DOA cannot satisfy the required prediction accuracy of signals from random azimuth in real applications. This paper presents a Centroid Optimization of deep neural network classification (CO-DNNC) to improve the estimation accuracy of DOA. CO-DNNC includes signal preprocessing, classification network, and Centroid Optimization. The DNN classification network adopts a convolutional neural network, including convolutional layers and fully connected layers. The Centroid Optimization takes the classified labels as the coordinates and calculates the azimuth of received signal according to the probabilities of the Softmax output. The experimental results show that CO-DNNC is capable of acquiring precise and accurate estimation of DOA, especially in the cases of low SNRs. In addition, CO-DNNC requires lower numbers of classes under the same condition of prediction accuracy and SNR, which reduces the complexity of the DNN network and saves training and processing time. MDPI 2023-02-24 /pmc/articles/PMC10007322/ /pubmed/36904717 http://dx.doi.org/10.3390/s23052513 Text en © 2023 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
Wu, Long
Zhang, Zidan
Yang, Xu
Xu, Lu
Chen, Shuyu
Zhang, Yong
Zhang, Jianlong
Centroid Optimization of DNN Classification in DOA Estimation for UAV
title Centroid Optimization of DNN Classification in DOA Estimation for UAV
title_full Centroid Optimization of DNN Classification in DOA Estimation for UAV
title_fullStr Centroid Optimization of DNN Classification in DOA Estimation for UAV
title_full_unstemmed Centroid Optimization of DNN Classification in DOA Estimation for UAV
title_short Centroid Optimization of DNN Classification in DOA Estimation for UAV
title_sort centroid optimization of dnn classification in doa estimation for uav
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007322/
https://www.ncbi.nlm.nih.gov/pubmed/36904717
http://dx.doi.org/10.3390/s23052513
work_keys_str_mv AT wulong centroidoptimizationofdnnclassificationindoaestimationforuav
AT zhangzidan centroidoptimizationofdnnclassificationindoaestimationforuav
AT yangxu centroidoptimizationofdnnclassificationindoaestimationforuav
AT xulu centroidoptimizationofdnnclassificationindoaestimationforuav
AT chenshuyu centroidoptimizationofdnnclassificationindoaestimationforuav
AT zhangyong centroidoptimizationofdnnclassificationindoaestimationforuav
AT zhangjianlong centroidoptimizationofdnnclassificationindoaestimationforuav