A Surrogate Model Based on Artificial Neural Network for RF Radiation Modelling with High-Dimensional Data

Xi Cheng; Clément Henry; Francesco P P Andriulli; Christian Person; Joe Wiart

doi:10.3390/ijerph17072586

A Surrogate Model Based on Artificial Neural Network for RF Radiation Modelling with High-Dimensional Data

Int J Environ Res Public Health. 2020 Apr 9;17(7):2586. doi: 10.3390/ijerph17072586.

Authors

Xi Cheng¹, Clément Henry², Francesco P P Andriulli², Christian Person³, Joe Wiart¹

Affiliations

¹ Chaire C2M, LTCI, Télécom Paris, 19 Place Marguerite Perey, 91120 Palaiseau, France.
² Department of Electronics and Telecommunications, Politecnico di Torino, IT-10129 Turin, Italy.
³ IMT Atlantique/lab-STICC UMR CNRS 6285, Technopole Brest Iroise-CS83818-29238, Brest Cedex 03, France.

Abstract

This paper focuses on quantifying the uncertainty in the specific absorption rate valuesof the brain induced by the uncertain positions of the electroencephalography electrodes placed onthe patient's scalp. To avoid running a large number of simulations, an artificial neural networkarchitecture for uncertainty quantification involving high-dimensional data is proposed in this paper.The proposed method is demonstrated to be an attractive alternative to conventional uncertaintyquantification methods because of its considerable advantage in the computational expense andspeed.

Keywords: artificial neural networks; specific absorption rate; uncertainty quantification.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Brain
Data Analysis
Electrodes
Electroencephalography* / methods
Humans
Neural Networks, Computer*
Uncertainty