Regrouping of acoustics microwaves in piezoelectric material (ZnO) by SVM classifier

Abstract

In this paper, we propose a new numerical method for acoustics microwaves detection of an acoustics microwaves signal during the propagation of acoustics microwaves in a piezoelectric substrate zinc oxide (ZnO). We have used support vector machines (SVMs), the originality of this method is the accurate values that provides this technique help to identify undetectable waves that we can not identify with the classical methods. We classify all the values of the real part and the imaginary part of the coefficient attenuation with the acoustic velocity in order to build a model from which we note the types of microwaves acoustics (bulk waves or surface waves or leaky waves). We obtain accurate values for each of the coefficient attenuation and acoustic velocity. This study will be very interesting in modelling and realisation of acoustics microwaves devices (ultrasound, radiating structures, filter SAW) based on the propagation of acoustics microwaves.