Machine-Learning Classification of Closed and Open Radiating Wires from Near Magnetic or Electric Field Scan Images

TL;DR

This paper presents a machine learning approach to automatically classify radiating wire configurations as magnetic or electric types using near-field scan data, with models trained on diverse datasets.

Contribution

It introduces a software package that employs support vector machines, k-nearest neighbors, and Gaussian processes for automatic classification of radiating wires from near-field data.

Findings

High classification accuracy demonstrated through cross-validation

Versatile software adaptable to various near-field datasets

Effective differentiation between magnetic and electric radiating sources

Abstract

Sets of intelligent classifiers are applied to the near-field scan-data in order to automatically classify the shape of radiating wirings. The support vector machine, k-nearest neighbors algorithm, and Gaussian process classifications are trained using the near-field radiation pattern of diverse radiating wire configurations. Leave-one-out cross-validation is used for estimating the performance of the predictive models. The output of this research is a software package well-suited to be retrained based on any measured near-field databank to automate the identification of magnetic-type or electric-type of the radiating coupling sources.