Multi-DOA estimation based on the KR image tensor and improved estimation network

Abstract Deep neural networks have shown great performance for direction-of-arrival (DOA) estimation problem, but it is necessary to design some suitable networks to solve the multi-DOA estimation problem. In this paper, we use Khatri–Rao product to increase the degree of freedom of antenna array an...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ye Yuan, Shuang Wu, Yong Yang, Naichang Yuan
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/22a0d235819f4c338100f1a38217c65f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:22a0d235819f4c338100f1a38217c65f
record_format	dspace
spelling	oai:doaj.org-article:22a0d235819f4c338100f1a38217c65f2021-12-02T11:39:48ZMulti-DOA estimation based on the KR image tensor and improved estimation network10.1038/s41598-021-85864-52045-2322https://doaj.org/article/22a0d235819f4c338100f1a38217c65f2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85864-5https://doaj.org/toc/2045-2322Abstract Deep neural networks have shown great performance for direction-of-arrival (DOA) estimation problem, but it is necessary to design some suitable networks to solve the multi-DOA estimation problem. In this paper, we use Khatri–Rao product to increase the degree of freedom of antenna array and obtain the image tensor of covariance matrix, then we propose an improved estimation network to process the tensor. We use the curriculum learning scheme and partial label strategy to develop a CurriculumNet training scheme. The training/validation results shows that the proposed training scheme can increase the generalization of the estimation network and improve the accuracy of network around $$10\%$$ 10 % . The estimation performance of the proposed network shows high-resolution results, which can distinguish two adjacent signals with angle difference of $$3^\circ $$ 3 ∘ . Moreover, the proposed estimation network has root mean square estimation error lower than $$1^\circ $$ 1 ∘ when signal noise ratio equals $$-\,10\,{\mathrm {dB}}$$ - 10 dB and can estimate DOAs precisely by only 8 snapshots, which performs much better than prior deep neural network based estimation methods and can estimate multi-DOA results under hostile estimation environments.Ye YuanShuang WuYong YangNaichang YuanNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ye Yuan Shuang Wu Yong Yang Naichang Yuan Multi-DOA estimation based on the KR image tensor and improved estimation network
description	Abstract Deep neural networks have shown great performance for direction-of-arrival (DOA) estimation problem, but it is necessary to design some suitable networks to solve the multi-DOA estimation problem. In this paper, we use Khatri–Rao product to increase the degree of freedom of antenna array and obtain the image tensor of covariance matrix, then we propose an improved estimation network to process the tensor. We use the curriculum learning scheme and partial label strategy to develop a CurriculumNet training scheme. The training/validation results shows that the proposed training scheme can increase the generalization of the estimation network and improve the accuracy of network around $$10\%$$ 10 % . The estimation performance of the proposed network shows high-resolution results, which can distinguish two adjacent signals with angle difference of $$3^\circ $$ 3 ∘ . Moreover, the proposed estimation network has root mean square estimation error lower than $$1^\circ $$ 1 ∘ when signal noise ratio equals $$-\,10\,{\mathrm {dB}}$$ - 10 dB and can estimate DOAs precisely by only 8 snapshots, which performs much better than prior deep neural network based estimation methods and can estimate multi-DOA results under hostile estimation environments.
format	article
author	Ye Yuan Shuang Wu Yong Yang Naichang Yuan
author_facet	Ye Yuan Shuang Wu Yong Yang Naichang Yuan
author_sort	Ye Yuan
title	Multi-DOA estimation based on the KR image tensor and improved estimation network
title_short	Multi-DOA estimation based on the KR image tensor and improved estimation network
title_full	Multi-DOA estimation based on the KR image tensor and improved estimation network
title_fullStr	Multi-DOA estimation based on the KR image tensor and improved estimation network
title_full_unstemmed	Multi-DOA estimation based on the KR image tensor and improved estimation network
title_sort	multi-doa estimation based on the kr image tensor and improved estimation network
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/22a0d235819f4c338100f1a38217c65f
work_keys_str_mv	AT yeyuan multidoaestimationbasedonthekrimagetensorandimprovedestimationnetwork AT shuangwu multidoaestimationbasedonthekrimagetensorandimprovedestimationnetwork AT yongyang multidoaestimationbasedonthekrimagetensorandimprovedestimationnetwork AT naichangyuan multidoaestimationbasedonthekrimagetensorandimprovedestimationnetwork
_version_	1718395690459070464

Multi-DOA estimation based on the KR image tensor and improved estimation network

Ejemplares similares