Simulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning

This paper proposes simulated annealing (SA) assisted deep learning (DL) based sparse array selection approach. Conventional DL-based antenna selectors are primarily data-driven techniques. As a result, the required dataset is generated by listing all possible combinations of selecting <inline-fo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Steven Wandale, Koichi Ichige
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Antenna selection direction-of-arrival estimation deep learning simulated annealing sparse arrays Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/6641cfa0fa3f4c9eb3403a62097c2617
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6641cfa0fa3f4c9eb3403a62097c2617
record_format	dspace
spelling	oai:doaj.org-article:6641cfa0fa3f4c9eb3403a62097c26172021-12-02T00:00:30ZSimulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning2169-353610.1109/ACCESS.2021.3129856https://doaj.org/article/6641cfa0fa3f4c9eb3403a62097c26172021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9623448/https://doaj.org/toc/2169-3536This paper proposes simulated annealing (SA) assisted deep learning (DL) based sparse array selection approach. Conventional DL-based antenna selectors are primarily data-driven techniques. As a result, the required dataset is generated by listing all possible combinations of selecting <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math></inline-formula> sensors given <inline-formula> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> uniform array, which is computationally expensive. A simulated annealing algorithm is proposed to assist dataset generation as an initializer to circumvent the above limitation. The SA algorithm sequentially samples and optimizes the subarrays that constitute the training data samples while retaining specific array characteristics. Hence, it simplifies the dataset annotation as most array configurations generated contain desired properties, thereby reducing the computation complexity of the overall data annotation processes. Therefore, the initializer reduces computation costs related to data generation considerably. Simulation examples show that using the dataset generated by the proposed method improves the DL-based array selector’s accuracy compared to the one generated by the conventional random sampler. Moreover, the realized sparse arrays show better sparse array configuration characteristics and enhanced DOA estimation performance.Steven WandaleKoichi IchigeIEEEarticleAntenna selectiondirection-of-arrival estimationdeep learningsimulated annealingsparse arraysElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 156907-156914 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Antenna selection direction-of-arrival estimation deep learning simulated annealing sparse arrays Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Antenna selection direction-of-arrival estimation deep learning simulated annealing sparse arrays Electrical engineering. Electronics. Nuclear engineering TK1-9971 Steven Wandale Koichi Ichige Simulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning
description	This paper proposes simulated annealing (SA) assisted deep learning (DL) based sparse array selection approach. Conventional DL-based antenna selectors are primarily data-driven techniques. As a result, the required dataset is generated by listing all possible combinations of selecting <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math></inline-formula> sensors given <inline-formula> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> uniform array, which is computationally expensive. A simulated annealing algorithm is proposed to assist dataset generation as an initializer to circumvent the above limitation. The SA algorithm sequentially samples and optimizes the subarrays that constitute the training data samples while retaining specific array characteristics. Hence, it simplifies the dataset annotation as most array configurations generated contain desired properties, thereby reducing the computation complexity of the overall data annotation processes. Therefore, the initializer reduces computation costs related to data generation considerably. Simulation examples show that using the dataset generated by the proposed method improves the DL-based array selector’s accuracy compared to the one generated by the conventional random sampler. Moreover, the realized sparse arrays show better sparse array configuration characteristics and enhanced DOA estimation performance.
format	article
author	Steven Wandale Koichi Ichige
author_facet	Steven Wandale Koichi Ichige
author_sort	Steven Wandale
title	Simulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning
title_short	Simulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning
title_full	Simulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning
title_fullStr	Simulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning
title_full_unstemmed	Simulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning
title_sort	simulated annealing assisted sparse array selection utilizing deep learning
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/6641cfa0fa3f4c9eb3403a62097c2617
work_keys_str_mv	AT stevenwandale simulatedannealingassistedsparsearrayselectionutilizingdeeplearning AT koichiichige simulatedannealingassistedsparsearrayselectionutilizingdeeplearning
_version_	1718403988290797568

Simulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning

Ejemplares similares