Machine-Learning-Based Approach for Diffraction Loss Variation Prediction by the Human Body

Abstract

This letter presents a machine learning (ML)-based model to predict the diffraction loss around the human body. Practically, it is not reasonable to measure the diffraction loss changes for all possible body rotation angles, builds, and line-of-sight elevation angles. A diffraction loss variation prediction model based on a non-parametric learning technique called Gaussian process is introduced. Analyzed results state that 86% correlation and normalized mean square error of 0.3 on the test data is achieved using only 40% of measured data. This allows a 60% reduction in required measurements in order to achieve a well-fitted ML loss prediction model. It also confirms the model generalizability for nonmeasured rotation angles.