Evaluation of the Impact of the Angle of Incidence Discretization in Surrogate Models of Periodic Cells in Reflectarray Antenna Analysis
Subject:
Machine learning
Support vector regression (SVR)
Surrogate model
Angle of incidence
Reflectarray analysis
Publication date:
Editorial:
IEEE
Abstract:
Different strategies for the discretization of the angles of incidence and its influence on reflectarray analysis based on surrogate models with support vector regression (SVR) are studied. One SVR per pair of angles of incidence is considered, and it is shown that while the copolar pattern is robust against the discretization of the angle of incidence, the crosspolar pattern presents a higher sensitivity with regard to the baseline scenario.
Description:
IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting (2020. Montreal)
Patrocinado por:
This work was supported in part by the Ministerio de Ciencia, Innovación y Universidades under project TEC2017-86619-R (ARTEINE); by the Ministerio de Economía, Industria y Competitividad under project TEC2016-75103-C2-1-R (MYRADA); by the Gobierno del Principado de Asturias/FEDER under Project GRUPIN-IDI/2018/000191.
Collections
Files in this item
Compartir
