Ultra-Wideband (UWB) characteristic estimation of elliptic patch antenna based on machine learning techniques

Çolak Ş., Gençoğlan D. N., Yildirim E., ARSLAN M. T.

Frequenz, vol.74, no.910, pp.351-358, 2020 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 74 Issue: 910
  • Publication Date: 2020
  • Doi Number: 10.1515/freq-2019-0210
  • Journal Name: Frequenz
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Applied Science & Technology Source, Compendex, INSPEC, RILM Abstracts of Music Literature
  • Page Numbers: pp.351-358
  • Keywords: Antenna design, Consistency based feature selection (CbFS), K-Nearest neighborhood algorithm (kNN), Microstrip patch antenna, Substrate materials, UWB antenna
  • Hatay Mustafa Kemal University Affiliated: Yes

Abstract

In this study, estimation of Ultra-Wideband (UWB) characteristics of microstrip elliptic patch antenna is investigated by means of k-nearest neighborhood algorithm. A total of 16,940 antennas are simulated by changing antenna dimensions and substrate material. Antennas are examined by observing Return Loss and Voltage Standing Wave Ratio (VSWR) characteristics. In the study, classification of antennas in terms of having UWB characteristics results in accuracies higher than 97%. Additionally, Consistency based Feature Selection method is applied to eliminate redundant and irrelevant features. This method yields that substrate material does not affect the UWB characteristics of the antenna. Classification process is repeated for the reduced feature set, reaching to 97.44% accuracy rate. This result is validated by 854 antennas, which are not included in the original antenna set. Antennas are designed for seven different substrate materials keeping all other parameters constant. Computer Simulation Technology Microwave Studio (CST MWS) is used for the design and simulation of the antennas.