Design of sparse arrays via deep learning for enhanced DOA estimation
Abstract This paper introduces an enhanced deep learning-based (DL) antenna selection approach for optimum sparse linear array selection for direction-of-arrival (DOA) estimation applications. Generally, the antenna selection problem yields a combination of subarrays as a solution. Previous DL-based...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2021-04-01
|
Series: | EURASIP Journal on Advances in Signal Processing |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13634-021-00727-5 |
id |
doaj-ee22f1e93de647268b46f235b4c96bcc |
---|---|
record_format |
Article |
spelling |
doaj-ee22f1e93de647268b46f235b4c96bcc2021-05-02T11:23:36ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802021-04-012021111310.1186/s13634-021-00727-5Design of sparse arrays via deep learning for enhanced DOA estimationSteven Wandale0Koichi Ichige1Department of Electrical and Computer Engineering, Yokohama National UniversityDepartment of Electrical and Computer Engineering, Yokohama National UniversityAbstract This paper introduces an enhanced deep learning-based (DL) antenna selection approach for optimum sparse linear array selection for direction-of-arrival (DOA) estimation applications. Generally, the antenna selection problem yields a combination of subarrays as a solution. Previous DL-based methods designated these subarrays as classes to fit the problem into a classification problem to which a convolutional neural network (CNN) is employed to solve it. However, these methods sample the combination set randomly to reduce computational cost related to the generation of training data, and it often leads to sub-optimal solutions due to ill-sampling issues. Hence, in this paper, we propose an improved DL-based method by constraining the combination set to retain the hole-free subarrays to enhance the method’s performance and sparse subarrays rendered. Numerical examples show that the proposed method yields sparser subarrays with better beampattern properties and improved DOA estimation performance than conventional DL techniques.https://doi.org/10.1186/s13634-021-00727-5Antenna selectionDirection-of-arrival estimationDeep learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Steven Wandale Koichi Ichige |
spellingShingle |
Steven Wandale Koichi Ichige Design of sparse arrays via deep learning for enhanced DOA estimation EURASIP Journal on Advances in Signal Processing Antenna selection Direction-of-arrival estimation Deep learning |
author_facet |
Steven Wandale Koichi Ichige |
author_sort |
Steven Wandale |
title |
Design of sparse arrays via deep learning for enhanced DOA estimation |
title_short |
Design of sparse arrays via deep learning for enhanced DOA estimation |
title_full |
Design of sparse arrays via deep learning for enhanced DOA estimation |
title_fullStr |
Design of sparse arrays via deep learning for enhanced DOA estimation |
title_full_unstemmed |
Design of sparse arrays via deep learning for enhanced DOA estimation |
title_sort |
design of sparse arrays via deep learning for enhanced doa estimation |
publisher |
SpringerOpen |
series |
EURASIP Journal on Advances in Signal Processing |
issn |
1687-6180 |
publishDate |
2021-04-01 |
description |
Abstract This paper introduces an enhanced deep learning-based (DL) antenna selection approach for optimum sparse linear array selection for direction-of-arrival (DOA) estimation applications. Generally, the antenna selection problem yields a combination of subarrays as a solution. Previous DL-based methods designated these subarrays as classes to fit the problem into a classification problem to which a convolutional neural network (CNN) is employed to solve it. However, these methods sample the combination set randomly to reduce computational cost related to the generation of training data, and it often leads to sub-optimal solutions due to ill-sampling issues. Hence, in this paper, we propose an improved DL-based method by constraining the combination set to retain the hole-free subarrays to enhance the method’s performance and sparse subarrays rendered. Numerical examples show that the proposed method yields sparser subarrays with better beampattern properties and improved DOA estimation performance than conventional DL techniques. |
topic |
Antenna selection Direction-of-arrival estimation Deep learning |
url |
https://doi.org/10.1186/s13634-021-00727-5 |
work_keys_str_mv |
AT stevenwandale designofsparsearraysviadeeplearningforenhanceddoaestimation AT koichiichige designofsparsearraysviadeeplearningforenhanceddoaestimation |
_version_ |
1721492351235391488 |