Mode Recognition of Rectangular Dielectric Resonator Antenna Using Artificial Neural Network

Yuqi Xiao; Kwok Wa Leung; Kai Lu; Chi-Sing Leung

doi:10.1109/TAP.2022.3146860

Mode Recognition of Rectangular Dielectric Resonator Antenna Using Artificial Neural Network

Yuqi Xiao, Kwok Wa Leung, Kai Lu^*, Chi-Sing Leung

^*Corresponding author for this work

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

12 Citations (Scopus)

Abstract

A new method powered by an artificial neural network (ANN) is studied for resonant-mode recognitions of a rectangular dielectric resonator antenna (DRA). Different rectangular DRAs were simulated with ANSYS HFSS to generate a large dataset for training the model. Their resonance frequencies, dimensions, and 3-D electric fields are input to the ANN. The output end is a 12-element array representing the corresponding probabilities of 12 different resonant modes. Using this trained ANN model, the mode recognition accuracy can reach 96.74%. Apart from identifying the resonant modes, our proposed approach can suggest how to modify a rectangular DRA to improve the purity of a resonant mode for better antenna performance.

Original language	English
Pages (from-to)	5209-5216
Journal	IEEE Transactions on Antennas and Propagation
Volume	70
Issue number	7
Online published	2 Feb 2022
DOIs	https://doi.org/10.1109/TAP.2022.3146860
Publication status	Published - Jul 2022

Funding

This work was supported by the General Research Fund (GRF) research grant from the Research Grants Council of Hong Kong SAR, China, under Project CityU 11218020

Research Keywords

Antenna measurements
artificial intelligence
artificial neural network
Artificial neural networks
Dielectric resonator antenna
Dielectric resonator antennas
mode recognition
Neurons
Optical resonators
particle swarm optimization
Resonant frequency
resonant mode
Training

Access Output

10.1109/TAP.2022.3146860

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{3fa6099e5c794705b16870006f512c56,

title = "Mode Recognition of Rectangular Dielectric Resonator Antenna Using Artificial Neural Network",

abstract = "A new method powered by an artificial neural network (ANN) is studied for resonant-mode recognitions of a rectangular dielectric resonator antenna (DRA). Different rectangular DRAs were simulated with ANSYS HFSS to generate a large dataset for training the model. Their resonance frequencies, dimensions, and 3-D electric fields are input to the ANN. The output end is a 12-element array representing the corresponding probabilities of 12 different resonant modes. Using this trained ANN model, the mode recognition accuracy can reach 96.74%. Apart from identifying the resonant modes, our proposed approach can suggest how to modify a rectangular DRA to improve the purity of a resonant mode for better antenna performance.",

keywords = "Antenna measurements, artificial intelligence, artificial neural network, Artificial neural networks, Dielectric resonator antenna, Dielectric resonator antennas, mode recognition, Neurons, Optical resonators, particle swarm optimization, Resonant frequency, resonant mode, Training",

author = "Yuqi Xiao and Leung, {Kwok Wa} and Kai Lu and Chi-Sing Leung",

year = "2022",

month = jul,

doi = "10.1109/TAP.2022.3146860",

language = "English",

volume = "70",

pages = "5209--5216",

journal = "IEEE Transactions on Antennas and Propagation",

issn = "0018-926X",

publisher = "IEEE",

number = "7",

}

TY - JOUR

T1 - Mode Recognition of Rectangular Dielectric Resonator Antenna Using Artificial Neural Network

AU - Xiao, Yuqi

AU - Leung, Kwok Wa

AU - Lu, Kai

AU - Leung, Chi-Sing

PY - 2022/7

Y1 - 2022/7

N2 - A new method powered by an artificial neural network (ANN) is studied for resonant-mode recognitions of a rectangular dielectric resonator antenna (DRA). Different rectangular DRAs were simulated with ANSYS HFSS to generate a large dataset for training the model. Their resonance frequencies, dimensions, and 3-D electric fields are input to the ANN. The output end is a 12-element array representing the corresponding probabilities of 12 different resonant modes. Using this trained ANN model, the mode recognition accuracy can reach 96.74%. Apart from identifying the resonant modes, our proposed approach can suggest how to modify a rectangular DRA to improve the purity of a resonant mode for better antenna performance.

AB - A new method powered by an artificial neural network (ANN) is studied for resonant-mode recognitions of a rectangular dielectric resonator antenna (DRA). Different rectangular DRAs were simulated with ANSYS HFSS to generate a large dataset for training the model. Their resonance frequencies, dimensions, and 3-D electric fields are input to the ANN. The output end is a 12-element array representing the corresponding probabilities of 12 different resonant modes. Using this trained ANN model, the mode recognition accuracy can reach 96.74%. Apart from identifying the resonant modes, our proposed approach can suggest how to modify a rectangular DRA to improve the purity of a resonant mode for better antenna performance.

KW - Antenna measurements

KW - artificial intelligence

KW - artificial neural network

KW - Artificial neural networks

KW - Dielectric resonator antenna

KW - Dielectric resonator antennas

KW - mode recognition

KW - Neurons

KW - Optical resonators

KW - particle swarm optimization

KW - Resonant frequency

KW - resonant mode

KW - Training

UR - http://www.scopus.com/inward/record.url?scp=85124200802&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85124200802&origin=recordpage

U2 - 10.1109/TAP.2022.3146860

DO - 10.1109/TAP.2022.3146860

M3 - RGC 21 - Publication in refereed journal

SN - 0018-926X

VL - 70

SP - 5209

EP - 5216

JO - IEEE Transactions on Antennas and Propagation

JF - IEEE Transactions on Antennas and Propagation

IS - 7

ER -

Mode Recognition of Rectangular Dielectric Resonator Antenna Using Artificial Neural Network

Abstract

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Investigation of Dielectric Resonator Antenna Arrays for Wireless Communications

Cite this

Mode Recognition of Rectangular Dielectric Resonator Antenna Using Artificial Neural Network

Abstract

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Investigation of Dielectric Resonator Antenna Arrays for Wireless Communications

Cite this