Deep Learning Method for Prediction of Planar Radiating Sources from Near-Field Intensity Data

Hanzhi Ma; Er Ping Li; Jose Schutt-Aine; Andreas C. Cangellaris

doi:10.1109/ISEMC.2019.8825271

Deep Learning Method for Prediction of Planar Radiating Sources from Near-Field Intensity Data

Hanzhi Ma, Er Ping Li, Jose Schutt-Aine, Andreas C. Cangellaris

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A deep learning method, cascaded convolutional neural networks, is investigated as a means for the prediction of frequency-dependent intensity distribution of planar radiating sources from frequency-dependent, near-field intensity data. More specifically, two convolutional neural networks are utilized as follows. The first one uses as input the available near-field amplitude data to predict the amplitude and phase of radiated fields on a plane in closer proximity to the radiating sources. Using the obtained distribution as input, the second one estimates the intensity of the planar radiating sources. The proposed method exhibits very good accuracy in the prediction of the radiating source distribution over the frequency range used for the training of the convolutional neural networks.

Original language	English (US)
Title of host publication	2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	610-615
Number of pages	6
ISBN (Electronic)	9781538691991
DOIs	https://doi.org/10.1109/ISEMC.2019.8825271
State	Published - Jul 2019
Event	2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019 - New Orleans, United States Duration: Jul 22 2019 → Jul 26 2019

Publication series

Name	2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019

Conference

Conference	2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019
Country	United States
City	New Orleans
Period	7/22/19 → 7/26/19

Fingerprint

Keywords

convolutional neural network
deep learning method
frequency-dependent radiated emissions analysis
near-field scanning

ASJC Scopus subject areas

Signal Processing
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Safety, Risk, Reliability and Quality

Cite this

Ma, H., Li, E. P., Schutt-Aine, J., & Cangellaris, A. C. (2019). Deep Learning Method for Prediction of Planar Radiating Sources from Near-Field Intensity Data. In 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019 (pp. 610-615). [8825271] (2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISEMC.2019.8825271

Deep Learning Method for Prediction of Planar Radiating Sources from Near-Field Intensity Data. / Ma, Hanzhi; Li, Er Ping; Schutt-Aine, Jose ; Cangellaris, Andreas C.

2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 610-615 8825271 (2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ma, H, Li, EP, Schutt-Aine, J & Cangellaris, AC 2019, Deep Learning Method for Prediction of Planar Radiating Sources from Near-Field Intensity Data. in 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019., 8825271, 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019, Institute of Electrical and Electronics Engineers Inc., pp. 610-615, 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019, New Orleans, United States, 7/22/19. https://doi.org/10.1109/ISEMC.2019.8825271

Ma H, Li EP, Schutt-Aine J , Cangellaris AC. Deep Learning Method for Prediction of Planar Radiating Sources from Near-Field Intensity Data. In 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 610-615. 8825271. (2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019). https://doi.org/10.1109/ISEMC.2019.8825271

Ma, Hanzhi ; Li, Er Ping ; Schutt-Aine, Jose ; Cangellaris, Andreas C. / Deep Learning Method for Prediction of Planar Radiating Sources from Near-Field Intensity Data. 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 610-615 (2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019).

@inproceedings{d8714befd9a94c9caa8263220fcc6ff6,

title = "Deep Learning Method for Prediction of Planar Radiating Sources from Near-Field Intensity Data",

abstract = "A deep learning method, cascaded convolutional neural networks, is investigated as a means for the prediction of frequency-dependent intensity distribution of planar radiating sources from frequency-dependent, near-field intensity data. More specifically, two convolutional neural networks are utilized as follows. The first one uses as input the available near-field amplitude data to predict the amplitude and phase of radiated fields on a plane in closer proximity to the radiating sources. Using the obtained distribution as input, the second one estimates the intensity of the planar radiating sources. The proposed method exhibits very good accuracy in the prediction of the radiating source distribution over the frequency range used for the training of the convolutional neural networks.",

keywords = "convolutional neural network, deep learning method, frequency-dependent radiated emissions analysis, near-field scanning",

author = "Hanzhi Ma and Li, {Er Ping} and Jose Schutt-Aine and Cangellaris, {Andreas C.}",

year = "2019",

month = jul,

doi = "10.1109/ISEMC.2019.8825271",

language = "English (US)",

series = "2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "610--615",

booktitle = "2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019",

address = "United States",

note = "2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019 ; Conference date: 22-07-2019 Through 26-07-2019",

}

TY - GEN

T1 - Deep Learning Method for Prediction of Planar Radiating Sources from Near-Field Intensity Data

AU - Ma, Hanzhi

AU - Li, Er Ping

AU - Schutt-Aine, Jose

AU - Cangellaris, Andreas C.

PY - 2019/7

Y1 - 2019/7

N2 - A deep learning method, cascaded convolutional neural networks, is investigated as a means for the prediction of frequency-dependent intensity distribution of planar radiating sources from frequency-dependent, near-field intensity data. More specifically, two convolutional neural networks are utilized as follows. The first one uses as input the available near-field amplitude data to predict the amplitude and phase of radiated fields on a plane in closer proximity to the radiating sources. Using the obtained distribution as input, the second one estimates the intensity of the planar radiating sources. The proposed method exhibits very good accuracy in the prediction of the radiating source distribution over the frequency range used for the training of the convolutional neural networks.

AB - A deep learning method, cascaded convolutional neural networks, is investigated as a means for the prediction of frequency-dependent intensity distribution of planar radiating sources from frequency-dependent, near-field intensity data. More specifically, two convolutional neural networks are utilized as follows. The first one uses as input the available near-field amplitude data to predict the amplitude and phase of radiated fields on a plane in closer proximity to the radiating sources. Using the obtained distribution as input, the second one estimates the intensity of the planar radiating sources. The proposed method exhibits very good accuracy in the prediction of the radiating source distribution over the frequency range used for the training of the convolutional neural networks.

KW - convolutional neural network

KW - deep learning method

KW - frequency-dependent radiated emissions analysis

KW - near-field scanning

UR - http://www.scopus.com/inward/record.url?scp=85073049871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073049871&partnerID=8YFLogxK

U2 - 10.1109/ISEMC.2019.8825271

DO - 10.1109/ISEMC.2019.8825271

M3 - Conference contribution

AN - SCOPUS:85073049871

T3 - 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019

SP - 610

EP - 615

BT - 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019

Y2 - 22 July 2019 through 26 July 2019

ER -

Access to Document

10.1109/ISEMC.2019.8825271