Grey Wolf Optimizer Aided ANN Based Behavioral Modelling Scheme for Fully Printed VO2 Switches

Saddam Husain, Damir Kanymkulov, Miras Akhmetov, Miras Akhmetov, Galymzhan Nauryzbayev, Mohammad Hashmi

2023

Closed access Metadata (CSL-JSON)
DOI 10.1109/icecs58634.2023.10382818
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Radio Frequency (RF) switches are one of the key drivers in the modern design of Frequency-Reconfigurable Circuits (FRCs). Recently, fully printed Vanadium Dioxide (VO2) based RF switches have been proposed for the state-of-the-art FRCs. However, VO2switch is still an evolving technology and needs behavioral models for the possible inclusion in computer aided design tools. This paper explores and develops Artificial Neural Network (ANN) and Grey Wolf Optimizer (GWO) aided ANN based behavioral models for the VO2switch. Then, the models are thoroughly evaluated on common metrics namely mean squared error, mean absolute error, coefficient of determination, prediction ability on unseen data, training and simulation time, parameters’ tuning time and complexity of the models.