A Comparative Analysis of Machine Learning Algorithms for Predicting the Dimensions of Rectangular Microstrip Antennas

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Antenna design process is time-consuming often involves a trial-and-error approach, which is not efficient. Machine learning algorithms can save significant time and effort in the design process and result in better antenna performance. This paper provides an analysis of suitable machine learning algorithms for predicting microstrip antenna dimensions by comparing six machine learning models based on four commonly used metrics in multi-output regression problems. The result shows that Random Forest algorithm is the most suitable algorithm since it gives the highest R2 score, namely 0.757, and lowest error value among the other algorithms, i.e. 0.674 for MAE, 4.097 for MSE, and 2.024 for RMSE.

Original languageEnglish
Title of host publication2023 IEEE International Symposium on Antennas and Propagation, ISAP 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350341140
DOIs
Publication statusPublished - 2023
Event2023 IEEE International Symposium on Antennas and Propagation, ISAP 2023 - Kuala Lumpur, Malaysia
Duration: 30 Oct 20232 Nov 2023

Publication series

Name2023 IEEE International Symposium on Antennas and Propagation, ISAP 2023

Conference

Conference2023 IEEE International Symposium on Antennas and Propagation, ISAP 2023
Country/TerritoryMalaysia
CityKuala Lumpur
Period30/10/232/11/23

Keywords

  • antenna design
  • machine learning
  • microstrip antenna
  • regression

Fingerprint

Dive into the research topics of 'A Comparative Analysis of Machine Learning Algorithms for Predicting the Dimensions of Rectangular Microstrip Antennas'. Together they form a unique fingerprint.

Cite this