A Suboptimal Approach to Antenna Design Problems with Kernel Regression

Sangwoo Lee, Jun Hur, Moon Beom Heo, Sunwoo Kim, Hosung Choo, Gangil Byun

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)

Abstract

This paper proposes a novel iterative algorithm based on a Kernel regression as a suboptimal approach to reliable and efficient antenna optimization. In our approach, the complex and non-linear cost surface calculated from antenna characteristics is fitted into a simple linear model using Kernels, and an argument that minimizes this Kernel regression model is used as a new input to calculate its cost using numerical simulations. This process is repeated by updating coefficients of the Kernel regression model with new entries until meeting the stopping criteria. At every iteration, existing inputs are partitioned into a limited number of clusters to reduce the computational time and resources and to prevent unexpected over-weighted situations. The proposed approach is validated for the Rastrigins function as well as a real engineering problem using an antipodal Vivaldi antenna in comparison with a genetic algorithm. Furthermore, we explore the most appropriate Kernel that minimizes the least-square error when fitting the antenna cost surface. The results demonstrate that the proposed process is suitable to be used in antenna design problems as a reliable approach with a fast convergence time.

Original languageEnglish
Article number8630937
Pages (from-to)17461-17468
Number of pages8
JournalIEEE Access
Volume7
DOIs
StatePublished - 2019 Jan 1

Fingerprint

Antennas
Costs
Genetic algorithms
Computer simulation

Keywords

  • Antennas
  • Kernel regression
  • cost surface
  • optimization

Cite this

Lee, S., Hur, J., Heo, M. B., Kim, S., Choo, H., & Byun, G. (2019). A Suboptimal Approach to Antenna Design Problems with Kernel Regression. IEEE Access, 7, 17461-17468. [8630937]. https://doi.org/10.1109/ACCESS.2019.2896658
Lee, Sangwoo ; Hur, Jun ; Heo, Moon Beom ; Kim, Sunwoo ; Choo, Hosung ; Byun, Gangil. / A Suboptimal Approach to Antenna Design Problems with Kernel Regression. In: IEEE Access. 2019 ; Vol. 7. pp. 17461-17468.
@article{f257adddec4a43578b5084cf2c57d101,
title = "A Suboptimal Approach to Antenna Design Problems with Kernel Regression",
abstract = "This paper proposes a novel iterative algorithm based on a Kernel regression as a suboptimal approach to reliable and efficient antenna optimization. In our approach, the complex and non-linear cost surface calculated from antenna characteristics is fitted into a simple linear model using Kernels, and an argument that minimizes this Kernel regression model is used as a new input to calculate its cost using numerical simulations. This process is repeated by updating coefficients of the Kernel regression model with new entries until meeting the stopping criteria. At every iteration, existing inputs are partitioned into a limited number of clusters to reduce the computational time and resources and to prevent unexpected over-weighted situations. The proposed approach is validated for the Rastrigins function as well as a real engineering problem using an antipodal Vivaldi antenna in comparison with a genetic algorithm. Furthermore, we explore the most appropriate Kernel that minimizes the least-square error when fitting the antenna cost surface. The results demonstrate that the proposed process is suitable to be used in antenna design problems as a reliable approach with a fast convergence time.",
keywords = "Antennas, Kernel regression, cost surface, optimization",
author = "Sangwoo Lee and Jun Hur and Heo, {Moon Beom} and Sunwoo Kim and Hosung Choo and Gangil Byun",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2019.2896658",
language = "English",
volume = "7",
pages = "17461--17468",
journal = "IEEE Access",
issn = "2169-3536",

}

Lee, S, Hur, J, Heo, MB, Kim, S, Choo, H & Byun, G 2019, 'A Suboptimal Approach to Antenna Design Problems with Kernel Regression', IEEE Access, vol. 7, 8630937, pp. 17461-17468. https://doi.org/10.1109/ACCESS.2019.2896658

A Suboptimal Approach to Antenna Design Problems with Kernel Regression. / Lee, Sangwoo; Hur, Jun; Heo, Moon Beom; Kim, Sunwoo; Choo, Hosung; Byun, Gangil.

In: IEEE Access, Vol. 7, 8630937, 01.01.2019, p. 17461-17468.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A Suboptimal Approach to Antenna Design Problems with Kernel Regression

AU - Lee, Sangwoo

AU - Hur, Jun

AU - Heo, Moon Beom

AU - Kim, Sunwoo

AU - Choo, Hosung

AU - Byun, Gangil

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This paper proposes a novel iterative algorithm based on a Kernel regression as a suboptimal approach to reliable and efficient antenna optimization. In our approach, the complex and non-linear cost surface calculated from antenna characteristics is fitted into a simple linear model using Kernels, and an argument that minimizes this Kernel regression model is used as a new input to calculate its cost using numerical simulations. This process is repeated by updating coefficients of the Kernel regression model with new entries until meeting the stopping criteria. At every iteration, existing inputs are partitioned into a limited number of clusters to reduce the computational time and resources and to prevent unexpected over-weighted situations. The proposed approach is validated for the Rastrigins function as well as a real engineering problem using an antipodal Vivaldi antenna in comparison with a genetic algorithm. Furthermore, we explore the most appropriate Kernel that minimizes the least-square error when fitting the antenna cost surface. The results demonstrate that the proposed process is suitable to be used in antenna design problems as a reliable approach with a fast convergence time.

AB - This paper proposes a novel iterative algorithm based on a Kernel regression as a suboptimal approach to reliable and efficient antenna optimization. In our approach, the complex and non-linear cost surface calculated from antenna characteristics is fitted into a simple linear model using Kernels, and an argument that minimizes this Kernel regression model is used as a new input to calculate its cost using numerical simulations. This process is repeated by updating coefficients of the Kernel regression model with new entries until meeting the stopping criteria. At every iteration, existing inputs are partitioned into a limited number of clusters to reduce the computational time and resources and to prevent unexpected over-weighted situations. The proposed approach is validated for the Rastrigins function as well as a real engineering problem using an antipodal Vivaldi antenna in comparison with a genetic algorithm. Furthermore, we explore the most appropriate Kernel that minimizes the least-square error when fitting the antenna cost surface. The results demonstrate that the proposed process is suitable to be used in antenna design problems as a reliable approach with a fast convergence time.

KW - Antennas

KW - Kernel regression

KW - cost surface

KW - optimization

UR - http://www.scopus.com/inward/record.url?scp=85061752724&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2896658

DO - 10.1109/ACCESS.2019.2896658

M3 - Article

VL - 7

SP - 17461

EP - 17468

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8630937

ER -