Ensemble-Learning-Based Multiobjective Optimization for Antenna Design

Xinchen Wang; Gang Wang; Dong Wang; Qingfu Zhang

doi:10.1109/TAP.2022.3222076

Ensemble-Learning-Based Multiobjective Optimization for Antenna Design

Xinchen Wang, Gang Wang^*, Dong Wang, Qingfu Zhang

^*Corresponding author for this work

Department of Computer Science

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

12 Citations (Scopus)

Abstract

An ensemble-learning-based multiobjective optimization is proposed for antenna design. By integrating the local search into multiobjective evolutionary algorithm based on decomposition (MOEA/D) and selecting appropriate solutions of the local search acquired with different offspring reproduction (OR) operators, the MOEA/D combined with ensemble OR (MOEA/D-EOR) is presented. Parallel local OR operators based on samples are also merged, for the first time, by exhaustively mining the evolution data of the optimization searching. The diversity and convergence of MOEA/D-EOR are verified by several widely used benchmark problems. The efficiency of MOEA/D-EOR is demonstrated by designing a high-performance bow-tie multiple-input and multiple-output (MIMO) antenna, which saves at least 25% of the optimization time. The overall performance of MOEA/D-EOR is further demonstrated by designing a 2 × 2 MIMO patch antenna in a compact size of 0.667λ₀× 0.667λ₀, which achieves a high isolation of 24 dB in an operation band of 4.95 to 5.07 GHz.

Original language	English
Pages (from-to)	1295-1303
Journal	IEEE Transactions on Antennas and Propagation
Volume	71
Issue number	2
Online published	18 Nov 2022
DOIs	https://doi.org/10.1109/TAP.2022.3222076
Publication status	Published - Feb 2023

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 62171423 and in part by the Hong Kong General Research Fund under Grant 11208121.

Research Keywords

Antennas
data mining
ensemble learning
local search
multiobjective optimization
multiple-input and multiple-output (MIMO) antenna

Access Output

10.1109/TAP.2022.3222076

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{b19b9e2fb6f94675bdce7a4592248863,

title = "Ensemble-Learning-Based Multiobjective Optimization for Antenna Design",

abstract = "An ensemble-learning-based multiobjective optimization is proposed for antenna design. By integrating the local search into multiobjective evolutionary algorithm based on decomposition (MOEA/D) and selecting appropriate solutions of the local search acquired with different offspring reproduction (OR) operators, the MOEA/D combined with ensemble OR (MOEA/D-EOR) is presented. Parallel local OR operators based on samples are also merged, for the first time, by exhaustively mining the evolution data of the optimization searching. The diversity and convergence of MOEA/D-EOR are verified by several widely used benchmark problems. The efficiency of MOEA/D-EOR is demonstrated by designing a high-performance bow-tie multiple-input and multiple-output (MIMO) antenna, which saves at least 25% of the optimization time. The overall performance of MOEA/D-EOR is further demonstrated by designing a 2 × 2 MIMO patch antenna in a compact size of 0.667λ0 × 0.667λ0, which achieves a high isolation of 24 dB in an operation band of 4.95 to 5.07 GHz.",

keywords = "Antennas, data mining, ensemble learning, local search, multiobjective optimization, multiple-input and multiple-output (MIMO) antenna",

author = "Xinchen Wang and Gang Wang and Dong Wang and Qingfu Zhang",

year = "2023",

month = feb,

doi = "10.1109/TAP.2022.3222076",

language = "English",

volume = "71",

pages = "1295--1303",

journal = "IEEE Transactions on Antennas and Propagation",

issn = "0018-926X",

publisher = "IEEE",

number = "2",

}

TY - JOUR

T1 - Ensemble-Learning-Based Multiobjective Optimization for Antenna Design

AU - Wang, Xinchen

AU - Wang, Gang

AU - Wang, Dong

AU - Zhang, Qingfu

PY - 2023/2

Y1 - 2023/2

N2 - An ensemble-learning-based multiobjective optimization is proposed for antenna design. By integrating the local search into multiobjective evolutionary algorithm based on decomposition (MOEA/D) and selecting appropriate solutions of the local search acquired with different offspring reproduction (OR) operators, the MOEA/D combined with ensemble OR (MOEA/D-EOR) is presented. Parallel local OR operators based on samples are also merged, for the first time, by exhaustively mining the evolution data of the optimization searching. The diversity and convergence of MOEA/D-EOR are verified by several widely used benchmark problems. The efficiency of MOEA/D-EOR is demonstrated by designing a high-performance bow-tie multiple-input and multiple-output (MIMO) antenna, which saves at least 25% of the optimization time. The overall performance of MOEA/D-EOR is further demonstrated by designing a 2 × 2 MIMO patch antenna in a compact size of 0.667λ0 × 0.667λ0, which achieves a high isolation of 24 dB in an operation band of 4.95 to 5.07 GHz.

AB - An ensemble-learning-based multiobjective optimization is proposed for antenna design. By integrating the local search into multiobjective evolutionary algorithm based on decomposition (MOEA/D) and selecting appropriate solutions of the local search acquired with different offspring reproduction (OR) operators, the MOEA/D combined with ensemble OR (MOEA/D-EOR) is presented. Parallel local OR operators based on samples are also merged, for the first time, by exhaustively mining the evolution data of the optimization searching. The diversity and convergence of MOEA/D-EOR are verified by several widely used benchmark problems. The efficiency of MOEA/D-EOR is demonstrated by designing a high-performance bow-tie multiple-input and multiple-output (MIMO) antenna, which saves at least 25% of the optimization time. The overall performance of MOEA/D-EOR is further demonstrated by designing a 2 × 2 MIMO patch antenna in a compact size of 0.667λ0 × 0.667λ0, which achieves a high isolation of 24 dB in an operation band of 4.95 to 5.07 GHz.

KW - Antennas

KW - data mining

KW - ensemble learning

KW - local search

KW - multiobjective optimization

KW - multiple-input and multiple-output (MIMO) antenna

UR - http://www.scopus.com/inward/record.url?scp=85142820992&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85142820992&origin=recordpage

U2 - 10.1109/TAP.2022.3222076

DO - 10.1109/TAP.2022.3222076

M3 - RGC 21 - Publication in refereed journal

SN - 0018-926X

VL - 71

SP - 1295

EP - 1303

JO - IEEE Transactions on Antennas and Propagation

JF - IEEE Transactions on Antennas and Propagation

IS - 2

ER -

Ensemble-Learning-Based Multiobjective Optimization for Antenna Design

Abstract

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Investigation on Approximation of Pareto Set and Structure Constraints

Cite this

Ensemble-Learning-Based Multiobjective Optimization for Antenna Design

Abstract

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Investigation on Approximation of Pareto Set and Structure Constraints

Cite this