A Machine Learning Enhanced Evolutionary Algorithm for Antenna Design

Kai Fu; Kwok Wa Leung

doi:10.1109/CAMA57522.2023.10352720

A Machine Learning Enhanced Evolutionary Algorithm for Antenna Design

Kai Fu
, Kwok Wa Leung^*

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

Abstract

Antenna optimization based on traditional algorithms is always computationally expensive, because it is inevitable to conduct many full-wave simulations during the iterative process. Machine learning (ML) can reduce the computation budget during the optimization, but it requires a large dataset for training. This paper proposes a novel algorithm that combines ML with evolutionary algorithm to achieve efficient antenna synthesis. A synthesis experiment on a wide-band dielectric resonator antenna is conducted, and results show that the proposed algorithm can greatly improve the optimization efficiency compared with traditional optimization methods. The proposed algorithm can also be applied to other types of antenna synthesis problems. This work demonstrates the potential of the ML-enhanced evolutionary algorithm for efficient antenna designs and optimizations. © 2023 IEEE.

Original language	English
Title of host publication	2023 IEEE Conference on Antenna Measurements and Applications (CAMA)
Publisher	IEEE
Pages	50-53
ISBN (Electronic)	9798350323047
ISBN (Print)	9798350323054
DOIs	https://doi.org/10.1109/CAMA57522.2023.10352720
Publication status	Published - 2023
Event	9th IEEE International Conference on Antenna Measurements and Applications (CAMA 2023) - NH Collection Genova Marina Hotel, Genoa, Italy Duration: 15 Nov 2023 → 17 Nov 2023 https://2023ieeecama.org/

Publication series

Name	IEEE Conference on Antenna Measurements and Applications, CAMA
ISSN (Print)	2474-1760
ISSN (Electronic)	2643-6795

Conference

Conference	9th IEEE International Conference on Antenna Measurements and Applications (CAMA 2023)
Abbreviated title	2023 IEEE CAMA
Place	Italy
City	Genoa
Period	15/11/23 → 17/11/23
Internet address	https://2023ieeecama.org/

Funding

This work was supported in part by the Seed Grant of the College of Engineering, City University of Hong Kong (Project no. 9229132), in part by the International Cooperative Research Program of Guangzhou City GDD District under Grant 2020GH06, in part by the Shenzhen-Hong Kong-Macau Science and Technology Project (Category C) (Project no. SGDX20210823104002018), and in part by 2022 Guangdong-Hong Kong-Macao Joint Innovation Funding Scheme under Grant 2022A0505030021.

Research Keywords

Antenna optimization
dielectric resonator antennas
particle swarm optimization
radial basis function network
surrogate assisted evolutionary algorithm

Access Output

10.1109/CAMA57522.2023.10352720

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{8c815aa402a54cdebc4c549c05476b71,

title = "A Machine Learning Enhanced Evolutionary Algorithm for Antenna Design",

abstract = "Antenna optimization based on traditional algorithms is always computationally expensive, because it is inevitable to conduct many full-wave simulations during the iterative process. Machine learning (ML) can reduce the computation budget during the optimization, but it requires a large dataset for training. This paper proposes a novel algorithm that combines ML with evolutionary algorithm to achieve efficient antenna synthesis. A synthesis experiment on a wide-band dielectric resonator antenna is conducted, and results show that the proposed algorithm can greatly improve the optimization efficiency compared with traditional optimization methods. The proposed algorithm can also be applied to other types of antenna synthesis problems. This work demonstrates the potential of the ML-enhanced evolutionary algorithm for efficient antenna designs and optimizations. {\textcopyright} 2023 IEEE.",

keywords = "Antenna optimization, dielectric resonator antennas, particle swarm optimization, radial basis function network, surrogate assisted evolutionary algorithm",

author = "Kai Fu and Leung, \{Kwok Wa\}",

year = "2023",

doi = "10.1109/CAMA57522.2023.10352720",

language = "English",

isbn = "9798350323054",

series = "IEEE Conference on Antenna Measurements and Applications, CAMA",

publisher = "IEEE",

pages = "50--53",

booktitle = "2023 IEEE Conference on Antenna Measurements and Applications (CAMA)",

address = "United States",

note = "9th IEEE International Conference on Antenna Measurements and Applications (CAMA 2023), 2023 IEEE CAMA ; Conference date: 15-11-2023 Through 17-11-2023",

url = "https://2023ieeecama.org/",

}

Fu, K & Leung, KW 2023, A Machine Learning Enhanced Evolutionary Algorithm for Antenna Design. in 2023 IEEE Conference on Antenna Measurements and Applications (CAMA). IEEE Conference on Antenna Measurements and Applications, CAMA, IEEE, pp. 50-53, 9th IEEE International Conference on Antenna Measurements and Applications (CAMA 2023), Genoa, Italy, 15/11/23. https://doi.org/10.1109/CAMA57522.2023.10352720

A Machine Learning Enhanced Evolutionary Algorithm for Antenna Design. / Fu, Kai ; Leung, Kwok Wa.
2023 IEEE Conference on Antenna Measurements and Applications (CAMA). IEEE, 2023. p. 50-53 (IEEE Conference on Antenna Measurements and Applications, CAMA).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A Machine Learning Enhanced Evolutionary Algorithm for Antenna Design

AU - Fu, Kai

AU - Leung, Kwok Wa

PY - 2023

Y1 - 2023

N2 - Antenna optimization based on traditional algorithms is always computationally expensive, because it is inevitable to conduct many full-wave simulations during the iterative process. Machine learning (ML) can reduce the computation budget during the optimization, but it requires a large dataset for training. This paper proposes a novel algorithm that combines ML with evolutionary algorithm to achieve efficient antenna synthesis. A synthesis experiment on a wide-band dielectric resonator antenna is conducted, and results show that the proposed algorithm can greatly improve the optimization efficiency compared with traditional optimization methods. The proposed algorithm can also be applied to other types of antenna synthesis problems. This work demonstrates the potential of the ML-enhanced evolutionary algorithm for efficient antenna designs and optimizations. © 2023 IEEE.

AB - Antenna optimization based on traditional algorithms is always computationally expensive, because it is inevitable to conduct many full-wave simulations during the iterative process. Machine learning (ML) can reduce the computation budget during the optimization, but it requires a large dataset for training. This paper proposes a novel algorithm that combines ML with evolutionary algorithm to achieve efficient antenna synthesis. A synthesis experiment on a wide-band dielectric resonator antenna is conducted, and results show that the proposed algorithm can greatly improve the optimization efficiency compared with traditional optimization methods. The proposed algorithm can also be applied to other types of antenna synthesis problems. This work demonstrates the potential of the ML-enhanced evolutionary algorithm for efficient antenna designs and optimizations. © 2023 IEEE.

KW - Antenna optimization

KW - dielectric resonator antennas

KW - particle swarm optimization

KW - radial basis function network

KW - surrogate assisted evolutionary algorithm

UR - https://www.scopus.com/pages/publications/85182274811

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85182274811&origin=recordpage

U2 - 10.1109/CAMA57522.2023.10352720

DO - 10.1109/CAMA57522.2023.10352720

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9798350323054

T3 - IEEE Conference on Antenna Measurements and Applications, CAMA

SP - 50

EP - 53

BT - 2023 IEEE Conference on Antenna Measurements and Applications (CAMA)

PB - IEEE

T2 - 9th IEEE International Conference on Antenna Measurements and Applications (CAMA 2023)

Y2 - 15 November 2023 through 17 November 2023

ER -

A Machine Learning Enhanced Evolutionary Algorithm for Antenna Design

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

DON_RMG: A Machine Learning-Assisted Mixed-Integer Algorithm for Antenna Design Optimization - RMGS

Cite this

A Machine Learning Enhanced Evolutionary Algorithm for Antenna Design

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

DON_RMG: A Machine Learning-Assisted Mixed-Integer Algorithm for Antenna Design Optimization - RMGS

Cite this