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 | |
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
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
}
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.
ER -