Machine learning‐driven design of dual‐band antennas using PGGAN and enhanced feature mapping

Abstract This paper presents a systematic antenna design methodology that integrates machine learning, leveraging the progressive growth technique of Progressive Growing of GANs (PGGAN) to generate images of various dual‐band PIFA‐like antenna structures. The process involves using data augmentation...

Full description

Saved in:
Bibliographic Details
Main Authors: Lung‐Fai Tuen, Ching‐Lieh Li, Yu‐Jen Chi, Chien‐Ching Chiu, Po Hsiang Chen
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Microwaves, Antennas & Propagation
Subjects:
Online Access:https://doi.org/10.1049/mia2.12534
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850132473099321344
author Lung‐Fai Tuen
Ching‐Lieh Li
Yu‐Jen Chi
Chien‐Ching Chiu
Po Hsiang Chen
author_facet Lung‐Fai Tuen
Ching‐Lieh Li
Yu‐Jen Chi
Chien‐Ching Chiu
Po Hsiang Chen
author_sort Lung‐Fai Tuen
collection DOAJ
description Abstract This paper presents a systematic antenna design methodology that integrates machine learning, leveraging the progressive growth technique of Progressive Growing of GANs (PGGAN) to generate images of various dual‐band PIFA‐like antenna structures. The process involves using data augmentation methods to generate 4180 antenna samples. In the latent space, the authors employ Latin Hypercube Sampling to maintain diversity and combine it with the Hough Transform to enhance the edge features of the antennas while providing labelling functionality. This labelling method strengthens the relationship between antenna frequency and wavelength characteristics. The paper clearly outlines the design process, starting from the simulation of two types of single‐frequency PIFA‐like antennas (2.45 and 5.2 GHz, respectively) to the completion of PGGAN's generation task, resulting in a novel dual‐band Wi‐Fi PIFA‐like antenna structure. The measurement results of the dual‐band antennas exhibit excellent consistency with the simulation results.
format Article
id doaj-art-de5c9c6dff6c43a69bf208f790f80dd6
institution OA Journals
issn 1751-8725
1751-8733
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Microwaves, Antennas & Propagation
spelling doaj-art-de5c9c6dff6c43a69bf208f790f80dd62025-08-20T02:32:12ZengWileyIET Microwaves, Antennas & Propagation1751-87251751-87332024-12-0118121113113810.1049/mia2.12534Machine learning‐driven design of dual‐band antennas using PGGAN and enhanced feature mappingLung‐Fai Tuen0Ching‐Lieh Li1Yu‐Jen Chi2Chien‐Ching Chiu3Po Hsiang Chen4Department of Electrical and Computer Engineering Tamkang University New Taipei City TaiwanDepartment of Electrical and Computer Engineering Tamkang University New Taipei City TaiwanDepartment of Electrical and Computer Engineering Tamkang University New Taipei City TaiwanDepartment of Electrical and Computer Engineering Tamkang University New Taipei City TaiwanDepartment of Electrical and Computer Engineering Tamkang University New Taipei City TaiwanAbstract This paper presents a systematic antenna design methodology that integrates machine learning, leveraging the progressive growth technique of Progressive Growing of GANs (PGGAN) to generate images of various dual‐band PIFA‐like antenna structures. The process involves using data augmentation methods to generate 4180 antenna samples. In the latent space, the authors employ Latin Hypercube Sampling to maintain diversity and combine it with the Hough Transform to enhance the edge features of the antennas while providing labelling functionality. This labelling method strengthens the relationship between antenna frequency and wavelength characteristics. The paper clearly outlines the design process, starting from the simulation of two types of single‐frequency PIFA‐like antennas (2.45 and 5.2 GHz, respectively) to the completion of PGGAN's generation task, resulting in a novel dual‐band Wi‐Fi PIFA‐like antenna structure. The measurement results of the dual‐band antennas exhibit excellent consistency with the simulation results.https://doi.org/10.1049/mia2.12534dual‐band antennahough transformLatin hypercube samplingPGGANWGAN‐GP
spellingShingle Lung‐Fai Tuen
Ching‐Lieh Li
Yu‐Jen Chi
Chien‐Ching Chiu
Po Hsiang Chen
Machine learning‐driven design of dual‐band antennas using PGGAN and enhanced feature mapping
IET Microwaves, Antennas & Propagation
dual‐band antenna
hough transform
Latin hypercube sampling
PGGAN
WGAN‐GP
title Machine learning‐driven design of dual‐band antennas using PGGAN and enhanced feature mapping
title_full Machine learning‐driven design of dual‐band antennas using PGGAN and enhanced feature mapping
title_fullStr Machine learning‐driven design of dual‐band antennas using PGGAN and enhanced feature mapping
title_full_unstemmed Machine learning‐driven design of dual‐band antennas using PGGAN and enhanced feature mapping
title_short Machine learning‐driven design of dual‐band antennas using PGGAN and enhanced feature mapping
title_sort machine learning driven design of dual band antennas using pggan and enhanced feature mapping
topic dual‐band antenna
hough transform
Latin hypercube sampling
PGGAN
WGAN‐GP
url https://doi.org/10.1049/mia2.12534
work_keys_str_mv AT lungfaituen machinelearningdrivendesignofdualbandantennasusingpgganandenhancedfeaturemapping
AT chingliehli machinelearningdrivendesignofdualbandantennasusingpgganandenhancedfeaturemapping
AT yujenchi machinelearningdrivendesignofdualbandantennasusingpgganandenhancedfeaturemapping
AT chienchingchiu machinelearningdrivendesignofdualbandantennasusingpgganandenhancedfeaturemapping
AT pohsiangchen machinelearningdrivendesignofdualbandantennasusingpgganandenhancedfeaturemapping