Comparison of Predictions between Artificial Neural Networks and Gaussian Processes in EMC Investigations

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

  • Felix Burghardt
  • Heyno Garbe
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des Sammelwerks2019 International Symposium on Electromagnetic Compatibility - EMC Europe 2019
UntertitelProceedings
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten921-926
Seitenumfang6
ISBN (elektronisch)978-1-7281-0594-9
ISBN (Print)978-1-7281-0595-6
PublikationsstatusVeröffentlicht - Sept. 2019
Veranstaltung2019 International Symposium on Electromagnetic Compatibility: EMC Europe 2019 - Barcelona, Spanien
Dauer: 2 Sept. 20196 Sept. 2019

Publikationsreihe

NameProceedings of the International Symposium on Electromagnetic Compatibility (EMC Europe)
ISSN (Print)2325-0356
ISSN (elektronisch)2325-0364

Abstract

Due to the increasing size and complexity of investigations in the field of electromagnetic compatibility, it is a desirable objective to reduce the calculation effort of such studies. In some of them, a large number of similarly constructed DUTs are investigated. For these cases, similar results are expected under equal conditions. Studies have shown, that artificial neural networks (ANNs) can reduce the effort of such investigations. This paper presents a further reduction method, the Gaussian processes. In addition, ANNs and Gaussian processes are compared and the results predictability regarding to EMC are evaluated.

ASJC Scopus Sachgebiete

Zitieren

Comparison of Predictions between Artificial Neural Networks and Gaussian Processes in EMC Investigations. / Burghardt, Felix; Garbe, Heyno.
2019 International Symposium on Electromagnetic Compatibility - EMC Europe 2019: Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. S. 921-926 8871865 (Proceedings of the International Symposium on Electromagnetic Compatibility (EMC Europe)).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Burghardt, F & Garbe, H 2019, Comparison of Predictions between Artificial Neural Networks and Gaussian Processes in EMC Investigations. in 2019 International Symposium on Electromagnetic Compatibility - EMC Europe 2019: Proceedings., 8871865, Proceedings of the International Symposium on Electromagnetic Compatibility (EMC Europe), Institute of Electrical and Electronics Engineers Inc., S. 921-926, 2019 International Symposium on Electromagnetic Compatibility, Barcelona, Spanien, 2 Sept. 2019. https://doi.org/10.1109/EMCEurope.2019.8871865
Burghardt, F., & Garbe, H. (2019). Comparison of Predictions between Artificial Neural Networks and Gaussian Processes in EMC Investigations. In 2019 International Symposium on Electromagnetic Compatibility - EMC Europe 2019: Proceedings (S. 921-926). Artikel 8871865 (Proceedings of the International Symposium on Electromagnetic Compatibility (EMC Europe)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMCEurope.2019.8871865
Burghardt F, Garbe H. Comparison of Predictions between Artificial Neural Networks and Gaussian Processes in EMC Investigations. in 2019 International Symposium on Electromagnetic Compatibility - EMC Europe 2019: Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. S. 921-926. 8871865. (Proceedings of the International Symposium on Electromagnetic Compatibility (EMC Europe)). doi: 10.1109/EMCEurope.2019.8871865
Burghardt, Felix ; Garbe, Heyno. / Comparison of Predictions between Artificial Neural Networks and Gaussian Processes in EMC Investigations. 2019 International Symposium on Electromagnetic Compatibility - EMC Europe 2019: Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. S. 921-926 (Proceedings of the International Symposium on Electromagnetic Compatibility (EMC Europe)).
Download
@inproceedings{bda0be3e7a4a4c5f9fcc9dfc770d2cc6,
title = "Comparison of Predictions between Artificial Neural Networks and Gaussian Processes in EMC Investigations",
abstract = "Due to the increasing size and complexity of investigations in the field of electromagnetic compatibility, it is a desirable objective to reduce the calculation effort of such studies. In some of them, a large number of similarly constructed DUTs are investigated. For these cases, similar results are expected under equal conditions. Studies have shown, that artificial neural networks (ANNs) can reduce the effort of such investigations. This paper presents a further reduction method, the Gaussian processes. In addition, ANNs and Gaussian processes are compared and the results predictability regarding to EMC are evaluated.",
keywords = "artificial neural network, EMC investigations, Gaussian process, prediction",
author = "Felix Burghardt and Heyno Garbe",
note = "Funding Information: The results shown in this paper were partly produced with the support of the Bundeswehr Research Institute for Protective Technologies – NBC-Protection in Munster, Germany. Contract Number E/E590/GZ004/CF011.; 2019 International Symposium on Electromagnetic Compatibility : EMC Europe 2019 ; Conference date: 02-09-2019 Through 06-09-2019",
year = "2019",
month = sep,
doi = "10.1109/EMCEurope.2019.8871865",
language = "English",
isbn = "978-1-7281-0595-6",
series = "Proceedings of the International Symposium on Electromagnetic Compatibility (EMC Europe)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "921--926",
booktitle = "2019 International Symposium on Electromagnetic Compatibility - EMC Europe 2019",
address = "United States",

}

Download

TY - GEN

T1 - Comparison of Predictions between Artificial Neural Networks and Gaussian Processes in EMC Investigations

AU - Burghardt, Felix

AU - Garbe, Heyno

N1 - Funding Information: The results shown in this paper were partly produced with the support of the Bundeswehr Research Institute for Protective Technologies – NBC-Protection in Munster, Germany. Contract Number E/E590/GZ004/CF011.

PY - 2019/9

Y1 - 2019/9

N2 - Due to the increasing size and complexity of investigations in the field of electromagnetic compatibility, it is a desirable objective to reduce the calculation effort of such studies. In some of them, a large number of similarly constructed DUTs are investigated. For these cases, similar results are expected under equal conditions. Studies have shown, that artificial neural networks (ANNs) can reduce the effort of such investigations. This paper presents a further reduction method, the Gaussian processes. In addition, ANNs and Gaussian processes are compared and the results predictability regarding to EMC are evaluated.

AB - Due to the increasing size and complexity of investigations in the field of electromagnetic compatibility, it is a desirable objective to reduce the calculation effort of such studies. In some of them, a large number of similarly constructed DUTs are investigated. For these cases, similar results are expected under equal conditions. Studies have shown, that artificial neural networks (ANNs) can reduce the effort of such investigations. This paper presents a further reduction method, the Gaussian processes. In addition, ANNs and Gaussian processes are compared and the results predictability regarding to EMC are evaluated.

KW - artificial neural network

KW - EMC investigations

KW - Gaussian process

KW - prediction

UR - http://www.scopus.com/inward/record.url?scp=85074325319&partnerID=8YFLogxK

U2 - 10.1109/EMCEurope.2019.8871865

DO - 10.1109/EMCEurope.2019.8871865

M3 - Conference contribution

AN - SCOPUS:85074325319

SN - 978-1-7281-0595-6

T3 - Proceedings of the International Symposium on Electromagnetic Compatibility (EMC Europe)

SP - 921

EP - 926

BT - 2019 International Symposium on Electromagnetic Compatibility - EMC Europe 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Symposium on Electromagnetic Compatibility

Y2 - 2 September 2019 through 6 September 2019

ER -