Convolution Neural Networks for Localization of Near-Field Sources via Symmetric Double-Nested Array

Convolution Neural Networks for Localization of Near-Field Sources via Symmetric Double-Nested Array

We present the convolution neural networks (CNNs) to achieve the localization of near-field sources via the symmetric double-nested array (SDNA). Considering that the incoherent near-field sources can be separated in the frequency spectrum, we first calculate the phase difference matrices and consid...

Full description

Bibliographic Details
Main Authors: Xiaolong Su, Panhe Hu, Zhenghui Gong, Zhen Liu, Junpeng Shi, Xiang Li
Format: Article
Language:English
Published: Hindawi-Wiley 2021-01-01
Series:Wireless Communications and Mobile Computing
Online Access:http://dx.doi.org/10.1155/2021/9996780
id doaj-c9545a77f776440eb8194dd4c5118fe8
record_format Article
spelling doaj-c9545a77f776440eb8194dd4c5118fe82021-06-21T02:24:34ZengHindawi-WileyWireless Communications and Mobile Computing1530-86772021-01-01202110.1155/2021/9996780Convolution Neural Networks for Localization of Near-Field Sources via Symmetric Double-Nested ArrayXiaolong Su0Panhe Hu1Zhenghui Gong2Zhen Liu3Junpeng Shi4Xiang Li5College of Electronic Science and TechnologyCollege of Electronic Science and TechnologyCollege of Electronic Science and TechnologyCollege of Electronic Science and TechnologyCollege of Electronic Science and TechnologyCollege of Electronic Science and TechnologyWe present the convolution neural networks (CNNs) to achieve the localization of near-field sources via the symmetric double-nested array (SDNA). Considering that the incoherent near-field sources can be separated in the frequency spectrum, we first calculate the phase difference matrices and consider the typical elements as the inputs of the networks. In order to guarantee the precision of the angle-of-arrival (AOA) estimation, we implement the autoencoders to divide the AOA subregions and construct the corresponding classification CNNs to obtain the AOAs of near-field sources. Then, we construct a particular range vector without the estimated AOAs and utilize the regression CNN to obtain the range parameters of near-field sources. The proposed algorithm is robust to the off-grid parameters and suitable for the scenarios with the different number of near-field sources. Moreover, the proposed method outperforms the existing method for near-field source localization.http://dx.doi.org/10.1155/2021/9996780
collection DOAJ
language English
format Article
sources DOAJ
author Xiaolong Su
Panhe Hu
Zhenghui Gong
Zhen Liu
Junpeng Shi
Xiang Li
spellingShingle Xiaolong Su
Panhe Hu
Zhenghui Gong
Zhen Liu
Junpeng Shi
Xiang Li
Convolution Neural Networks for Localization of Near-Field Sources via Symmetric Double-Nested Array
Wireless Communications and Mobile Computing
author_facet Xiaolong Su
Panhe Hu
Zhenghui Gong
Zhen Liu
Junpeng Shi
Xiang Li
author_sort Xiaolong Su
title Convolution Neural Networks for Localization of Near-Field Sources via Symmetric Double-Nested Array
title_short Convolution Neural Networks for Localization of Near-Field Sources via Symmetric Double-Nested Array
title_full Convolution Neural Networks for Localization of Near-Field Sources via Symmetric Double-Nested Array
title_fullStr Convolution Neural Networks for Localization of Near-Field Sources via Symmetric Double-Nested Array
title_full_unstemmed Convolution Neural Networks for Localization of Near-Field Sources via Symmetric Double-Nested Array
title_sort convolution neural networks for localization of near-field sources via symmetric double-nested array
publisher Hindawi-Wiley
series Wireless Communications and Mobile Computing
issn 1530-8677
publishDate 2021-01-01
description We present the convolution neural networks (CNNs) to achieve the localization of near-field sources via the symmetric double-nested array (SDNA). Considering that the incoherent near-field sources can be separated in the frequency spectrum, we first calculate the phase difference matrices and consider the typical elements as the inputs of the networks. In order to guarantee the precision of the angle-of-arrival (AOA) estimation, we implement the autoencoders to divide the AOA subregions and construct the corresponding classification CNNs to obtain the AOAs of near-field sources. Then, we construct a particular range vector without the estimated AOAs and utilize the regression CNN to obtain the range parameters of near-field sources. The proposed algorithm is robust to the off-grid parameters and suitable for the scenarios with the different number of near-field sources. Moreover, the proposed method outperforms the existing method for near-field source localization.
url http://dx.doi.org/10.1155/2021/9996780
work_keys_str_mv AT xiaolongsu convolutionneuralnetworksforlocalizationofnearfieldsourcesviasymmetricdoublenestedarray
AT panhehu convolutionneuralnetworksforlocalizationofnearfieldsourcesviasymmetricdoublenestedarray
AT zhenghuigong convolutionneuralnetworksforlocalizationofnearfieldsourcesviasymmetricdoublenestedarray
AT zhenliu convolutionneuralnetworksforlocalizationofnearfieldsourcesviasymmetricdoublenestedarray
AT junpengshi convolutionneuralnetworksforlocalizationofnearfieldsourcesviasymmetricdoublenestedarray
AT xiangli convolutionneuralnetworksforlocalizationofnearfieldsourcesviasymmetricdoublenestedarray
_version_ 1721369281937014784

Similar Items