University of Surrey

Test tubes in the lab Research in the ATI Dance Research

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

Khalily, Mohsen, Brown, Tim W. C. and Tafazolli, Rahim (2019) Machine Learning Based Approach for Diffraction Loss Variation Prediction by the Human Body IEEE Antennas and Wireless Propagation Letters.

[img]
Preview
Text
Machine Learning Based Approach for Diffraction Loss Variation Prediction by the Human Body.pdf - Accepted version Manuscript

Download (1MB) | Preview

Abstract

This paper 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 (LoS) elevation angles. A diffraction loss variation prediction model based on a non-parametric learning technique called Gaussian process (GP) is introduced. Analysed results state that 86% correlation and normalised mean square error (NMSE) 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 non-measured rotation angles.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Khalily, Mohsenm.khalily@surrey.ac.uk
Brown, Tim W. C.T.Brown@surrey.ac.uk
Tafazolli, RahimR.Tafazolli@surrey.ac.uk
Date : 2019
Copyright Disclaimer : © 2019 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
Uncontrolled Keywords : Diffraction loss; Guassian process (GP); Machine learning (ML); Network planning tool
Related URLs :
Depositing User : Clive Harris
Date Deposited : 05 Jul 2019 07:34
Last Modified : 05 Jul 2019 07:34
URI: http://epubs.surrey.ac.uk/id/eprint/852207

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800