Machine learning based classification and prediction of electromagnetic absorption in electrical reverberation chambers

Stiemer, Marcus

doi:10.23919/ursigass57860.2023.10265605

Machine learning based classification and prediction of electromagnetic absorption in electrical reverberation chambers

Publication date

2023-10-03

Document type

Konferenzbeitrag

Author

Stiemer, Marcus

Organisational unit

Theoretische Elektrotechnik

DOI

10.23919/ursigass57860.2023.10265605

URI

https://openhsu.ub.hsu-hh.de/handle/10.24405/22657

Conference

35th General Assembly and Scientific Symposium of the International Union of Radio Science (URSI GASS 2023) ; Sapporo, Japan ; August 19–26, 2023

Book title

2023 XXXVth General Assembly and Scientific Symposium of the International Union of Radio Science (URSI GASS)

ISBN

978-9-4639-6809-6

Part of the university bibliography

✅

Language

English

Abstract

A method is proposed to quickly classify devices with regard to their susceptibility to absorb power from an ambient electromagnetic field with the help of an electrical reverberation chamber. Different absorption classes are implemented via a set of labeled training devices. Frequency depending S-parameters are considered as data. The machine learning environment consists of an auto-encoder to reduce the dimension of the input data and several machine learning approaches for classification.

Version

Published version

Access right on openHSU

Metadata only access