High-Resolution Multiple-Source 2D DOA Estimation Using Convolutional Neural Network With Robustness to Array Imperfections
In this paper, we present an efficient convolutional neural network (CNN)-based model to estimate both elevation and azimuth arrival angles of multiple sources with high resolution (small source angular separation). The sources are considered closely spaced in both elevation and azimuth up to 0.5&am...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10713319/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850175125230452736 |
|---|---|
| author | Tarek Sallam Qun Wang Ahmed M. Attiya |
| author_facet | Tarek Sallam Qun Wang Ahmed M. Attiya |
| author_sort | Tarek Sallam |
| collection | DOAJ |
| description | In this paper, we present an efficient convolutional neural network (CNN)-based model to estimate both elevation and azimuth arrival angles of multiple sources with high resolution (small source angular separation). The sources are considered closely spaced in both elevation and azimuth up to 0.5° resolution in both directions. Ten sources are supposed to be received by an <inline-formula> <tex-math notation="LaTeX">$8\times 8$ </tex-math></inline-formula> antenna array. Compared to multiple signal classification (MUSIC) algorithm and radial basis function neural network (RBFNN), numerical results indicate that the CNN model exhibits notable precision in two-dimensional (2D) direction of arrival (DOA) estimation of multiple-source with high resolution, along with less than one-tenth second execution time. Finally, it maintains its superior performance even in the presence of array imperfections and significantly reduced SNR. |
| format | Article |
| id | doaj-art-1d890e3c1ae8434aa8a1b2e7ccd8f3d4 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-1d890e3c1ae8434aa8a1b2e7ccd8f3d42025-08-20T02:19:31ZengIEEEIEEE Access2169-35362025-01-0113931159312310.1109/ACCESS.2024.347792010713319High-Resolution Multiple-Source 2D DOA Estimation Using Convolutional Neural Network With Robustness to Array ImperfectionsTarek Sallam0https://orcid.org/0000-0003-3485-7988Qun Wang1Ahmed M. Attiya2https://orcid.org/0000-0002-2227-9976School of Computer Science and Technology, Shandong Xiehe University, Jinan, Shandong, ChinaSchool of Computer Science and Technology, Shandong Xiehe University, Jinan, Shandong, ChinaMicrowave Engineering Department, Electronics Research Institute (ERI), Cairo, EgyptIn this paper, we present an efficient convolutional neural network (CNN)-based model to estimate both elevation and azimuth arrival angles of multiple sources with high resolution (small source angular separation). The sources are considered closely spaced in both elevation and azimuth up to 0.5° resolution in both directions. Ten sources are supposed to be received by an <inline-formula> <tex-math notation="LaTeX">$8\times 8$ </tex-math></inline-formula> antenna array. Compared to multiple signal classification (MUSIC) algorithm and radial basis function neural network (RBFNN), numerical results indicate that the CNN model exhibits notable precision in two-dimensional (2D) direction of arrival (DOA) estimation of multiple-source with high resolution, along with less than one-tenth second execution time. Finally, it maintains its superior performance even in the presence of array imperfections and significantly reduced SNR.https://ieeexplore.ieee.org/document/10713319/2D DOA estimationarray imperfectionsconvolutional neural networkdeep learningMUSIC algorithm |
| spellingShingle | Tarek Sallam Qun Wang Ahmed M. Attiya High-Resolution Multiple-Source 2D DOA Estimation Using Convolutional Neural Network With Robustness to Array Imperfections IEEE Access 2D DOA estimation array imperfections convolutional neural network deep learning MUSIC algorithm |
| title | High-Resolution Multiple-Source 2D DOA Estimation Using Convolutional Neural Network With Robustness to Array Imperfections |
| title_full | High-Resolution Multiple-Source 2D DOA Estimation Using Convolutional Neural Network With Robustness to Array Imperfections |
| title_fullStr | High-Resolution Multiple-Source 2D DOA Estimation Using Convolutional Neural Network With Robustness to Array Imperfections |
| title_full_unstemmed | High-Resolution Multiple-Source 2D DOA Estimation Using Convolutional Neural Network With Robustness to Array Imperfections |
| title_short | High-Resolution Multiple-Source 2D DOA Estimation Using Convolutional Neural Network With Robustness to Array Imperfections |
| title_sort | high resolution multiple source 2d doa estimation using convolutional neural network with robustness to array imperfections |
| topic | 2D DOA estimation array imperfections convolutional neural network deep learning MUSIC algorithm |
| url | https://ieeexplore.ieee.org/document/10713319/ |
| work_keys_str_mv | AT tareksallam highresolutionmultiplesource2ddoaestimationusingconvolutionalneuralnetworkwithrobustnesstoarrayimperfections AT qunwang highresolutionmultiplesource2ddoaestimationusingconvolutionalneuralnetworkwithrobustnesstoarrayimperfections AT ahmedmattiya highresolutionmultiplesource2ddoaestimationusingconvolutionalneuralnetworkwithrobustnesstoarrayimperfections |