Deep learning based source reconstruction method using asymmetric encoder–decoder​ structure and physics-induced loss

This paper proposes a novel deep learning (DL) based source reconstruction method (SRM). The proposed DL-based SRM employs the deep convolutional asymmetric encoder–decoder structure (DCAEDS), which only demands one-time single-frequency far-field measurement on EM scattered field as its input and f...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of computational and applied mathematics Ročník 438; s. 115503
Hlavní autori: Ng, Michael, Yao, He Ming
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.03.2024
Predmet:
ISSN:0377-0427
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract This paper proposes a novel deep learning (DL) based source reconstruction method (SRM). The proposed DL-based SRM employs the deep convolutional asymmetric encoder–decoder structure (DCAEDS), which only demands one-time single-frequency far-field measurement on EM scattered field as its input and further predicts the equivalent source on target scatterers. During the offline training, an EM scattering simulator is designed to compute EM scattered field originated from the predicted equivalent source on target scatterers. The DCAEDS is combined with the EM scattering simulator to optimize the loss function, including two parts: (1) Data-induced loss, which directly evaluates the difference between the prediction of the proposed DCAEDS and the true-labelled equivalent source of target scatterers; (2) Physics-induced loss, which evaluates the difference between received EM scattered field and the computed EM scattered field originated from the prediction of DCAEDS. Moreover, the proposed DL-based SRM can overcome the limitation of conventional methods, involving high computation cost and strong ill-conditions. Consequently, the proposed DL-based SRM can realize the reconstruction of the equivalent current source with higher accuracy and lower computation complexity. Numerical examples illustrate the feasibility of the proposed DL-based SRM, which opens the new path for DL-based EM computation approaches.
AbstractList This paper proposes a novel deep learning (DL) based source reconstruction method (SRM). The proposed DL-based SRM employs the deep convolutional asymmetric encoder–decoder structure (DCAEDS), which only demands one-time single-frequency far-field measurement on EM scattered field as its input and further predicts the equivalent source on target scatterers. During the offline training, an EM scattering simulator is designed to compute EM scattered field originated from the predicted equivalent source on target scatterers. The DCAEDS is combined with the EM scattering simulator to optimize the loss function, including two parts: (1) Data-induced loss, which directly evaluates the difference between the prediction of the proposed DCAEDS and the true-labelled equivalent source of target scatterers; (2) Physics-induced loss, which evaluates the difference between received EM scattered field and the computed EM scattered field originated from the prediction of DCAEDS. Moreover, the proposed DL-based SRM can overcome the limitation of conventional methods, involving high computation cost and strong ill-conditions. Consequently, the proposed DL-based SRM can realize the reconstruction of the equivalent current source with higher accuracy and lower computation complexity. Numerical examples illustrate the feasibility of the proposed DL-based SRM, which opens the new path for DL-based EM computation approaches.
ArticleNumber 115503
Author Yao, He Ming
Ng, Michael
Author_xml – sequence: 1
  givenname: Michael
  surname: Ng
  fullname: Ng, Michael
– sequence: 2
  givenname: He Ming
  surname: Yao
  fullname: Yao, He Ming
  email: yaohm@hku.hk
BookMark eNp9kL9OwzAQhz0UiRZ4ADa_QIodJ3EiJlT-SpVYYLYc-0JdJXZlJ0jZ2Bl5Q54ER-nE0OlOp_vu9PtWaGGdBYSuKVlTQoub_VrJbp2SlK0pzXPCFmhJGOcJyVJ-jlYh7AkhRUWzJRrvAQ64BemtsR-4lgE0Dm7wCrAH5Wzo_aB64yzuoN85jYcwLcowdnHgjcJgldPgf79-NBy7bzxjgwcsrcaH3RiMComxelDxQetCuERnjWwDXB3rBXp_fHjbPCfb16eXzd02UWnF-ySXsijLmqUaZMMkNDWvGkVLzeo6z8tS5XkGtSSEFVJrDloCTxUvGt5UTGcVu0B8vqt8_OqhEcr0ckrUe2laQYmYrIm9iNbEZE3M1iJJ_5EHbzrpx5PM7cxAjPRpwIugTDQE2kSdvdDOnKD_ADv8j7E
CitedBy_id crossref_primary_10_1016_j_enganabound_2024_105813
Cites_doi 10.1029/93RS03445
10.1007/978-3-319-11179-7_36
10.1109/TAP.2013.2274032
10.1109/TAP.2022.3196496
10.1109/MAP.2021.3127514
10.2528/PIERM18082907
10.1109/TGRS.2021.3101119
10.1109/APS/URSI47566.2021.9704363
10.1109/TGRS.2007.894932
10.1109/TEMC.2018.2797132
10.1109/TIP.2017.2713099
10.1109/TAP.2020.2985172
10.1109/MAP.2017.2731203
10.1088/0266-5611/29/2/025015
10.1109/LAWP.2020.2995455
10.1038/s41598-021-00326-2
10.1109/15.974631
10.1109/TEMC.2016.2642955
10.1109/LAWP.2019.2916369
10.23919/ACES48530.2019.9060439
10.1109/TPAMI.2016.2644615
10.1111/j.1365-2478.2009.00824.x
10.1109/LAWP.2021.3056460
10.1109/TEMC.2012.2235837
10.1109/TGRS.2020.2986000
10.23919/EMCTokyo.2019.8893747
10.1109/TAP.2016.2560901
10.1109/NEMO49486.2020.9343382
10.1109/TAP.2022.3177556
10.1109/TMTT.2021.3098769
10.1109/LAWP.2019.2925578
ContentType Journal Article
Copyright 2023 Elsevier B.V.
Copyright_xml – notice: 2023 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.cam.2023.115503
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Mathematics
ExternalDocumentID 10_1016_j_cam_2023_115503
S0377042723004478
GroupedDBID --K
--M
-~X
.~1
0R~
0SF
1B1
1RT
1~.
1~5
4.4
457
4G.
5GY
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAFTH
AAIKJ
AAKOC
AAOAW
AAQFI
AAXKI
AAXUO
ABAOU
ABJNI
ABMAC
ABVKL
ACDAQ
ACGFS
ACRLP
ADBBV
ADEZE
AEBSH
AEKER
AENEX
AFJKZ
AFKWA
AFTJW
AGUBO
AGYEJ
AHHHB
AIEXJ
AIGVJ
AIKHN
AITUG
AJOXV
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ARUGR
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FIRID
FNPLU
FYGXN
G-Q
GBLVA
HVGLF
IHE
IXB
J1W
KOM
LG9
M26
M41
MHUIS
MO0
N9A
O-L
O9-
OAUVE
OK1
OZT
P-8
P-9
P2P
PC.
Q38
RNS
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSW
T5K
TN5
UPT
XPP
YQT
ZMT
~02
~G-
29K
5VS
9DU
AAFWJ
AALRI
AAQXK
AATTM
AAYWO
AAYXX
ABDPE
ABEFU
ABFNM
ABWVN
ABXDB
ACLOT
ACRPL
ACVFH
ADCNI
ADMUD
ADNMO
ADVLN
AEIPS
AEUPX
AEXQZ
AFPUW
AGHFR
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
D-I
EFKBS
EFLBG
EJD
FGOYB
G-2
HZ~
NHB
R2-
SSZ
WUQ
ZY4
~HD
ID FETCH-LOGICAL-c297t-5aa688b32deaf3aefb79fc18d3bb5588c554eba0036add7edae72c76f7f93d493
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001097639300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0377-0427
IngestDate Sat Nov 29 07:19:26 EST 2025
Tue Nov 18 20:47:30 EST 2025
Tue Dec 03 03:44:46 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Source reconstruction method
Real time
Convolutional neural network
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c297t-5aa688b32deaf3aefb79fc18d3bb5588c554eba0036add7edae72c76f7f93d493
ParticipantIDs crossref_citationtrail_10_1016_j_cam_2023_115503
crossref_primary_10_1016_j_cam_2023_115503
elsevier_sciencedirect_doi_10_1016_j_cam_2023_115503
PublicationCentury 2000
PublicationDate 2024-03-01
2024-03-00
PublicationDateYYYYMMDD 2024-03-01
PublicationDate_xml – month: 03
  year: 2024
  text: 2024-03-01
  day: 01
PublicationDecade 2020
PublicationTitle Journal of computational and applied mathematics
PublicationYear 2024
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Guo, Lin, Shan, Li, Yang, Xu, Abubakar (b19) 2021; 20
Shan, Tang, Dang, Li, Yang, Xu, Wu (b20) 2020; 68
X. Song, M. Li, A. Abubakar, A Regularization Scheme Based on Gaussian Mixture Model for EM Data Inversion, in: 2020 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization, NEMO, China, 2020, pp. 1–4.
Chew (b1) 2001
H.M. Yao, L. Jiang, W.E.I. Sha, Source Reconstruction Method based on Machine Learning Algorithms, in: 2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC, Sapporo, Japan, 2019, pp. 774–777.
Huang, Fan (b30) 2018; 60
Li, Li, Jiang, Hu (b12) 2013; 61
Lin, Guo, Li, Abubakar, Zhao, Yang, Xu (b27) 2021; 69
Li, Jiang (b10) 2013; 55
Wuttke (b33) 2021; 11
Li (b5) 2017; 59
J. Cong, B. Xiao, Minimizing computation in convolutional neural networks, in: Proc. Int. Conf. Artif. Neural Netw., 2014, pp. 281–290.
Hu (b16) 2020; 58
Massa, Marcantonio, Chen, Li, Salucci (b14) 2019; 18
L. Guo, M. Li, S. Xu, F. Yang, L. Liu, Electromagnetic Modeling Using an FDTD-Equivalent Recurrent Convolution Neural Network: Accurate Computing on a Deep Learning Framework, IEEE Antennas Propag. Mag.
M. Salucci, M. Arrebola, T. Shan, M. Li, Artificial Intelligence: New Frontiers in Real–Time Inverse Scattering and Electromagnetic Imaging, IEEE Trans. Antennas and Propagation
Zhang, Jiang, Yao (b24) 2016; 64
D.P. Kingma, J.L. Ba, Adam: A method for stochastic optimization, in: Proc. Int. Conf. Learn. Represent., 2015, pp. 1–41.
Yao, Jiang, Sha (b17) 2020; 19
Jin (b34) 2017; 26
Yao, Sha, Jiang (b4) 2018; 76
Shan, Song, Guo, Li, Yang, Xu (b31) 2021
Li, Semerci, Abubakar (b3) 2013; 29
T. Shan, R. Guo, M. Li, F. Yang, S. Xu, L. Liang, Application of Multitask Learning for 2-D Modeling of Magnetotelluric Surveys: TE Case, IEEE Trans. Geosci. Remote Sens.
Zhang (b25) 2017; 59
Badrinarayanan, Kendall, Cipolla (b32) 2017; 39
Regue (b6) 2001; 43
Pastorino (b2) 2010
Catedra (b36) 1995
Kim (b37) 2017
Z. Lin, R. Guo, M. Li, F. Yang, S. Xu, A. Abubakar, Study on the Degrees of Freedom of Scattered Fields in Nonlinear Inverse Scattering Problems, in: 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, APS/URSI, 2021, pp. 1845–1846.
.
Yu, Carin (b7) 2007; 45
Li, Abubakar, Habashy, Zhang (b11) 2010; 58
H.M. Yao, L. Jiang, H.H. Zhang, W.E.I. Sha, Machine Learning Methodology Review for Computational Electromagnetics, in: 2019 ACES, Nanjing, China, 2019, pp. 1–4.
Yao (b26) 2019; 18
Yao, Jiang, Ng (b22) 2022
Yao, Guo, Li, Jiang, Ng (b28) 2022; 70
Kleinman, van den Berg (b9) 1994; 29
Hu (10.1016/j.cam.2023.115503_b16) 2020; 58
Zhang (10.1016/j.cam.2023.115503_b24) 2016; 64
Lin (10.1016/j.cam.2023.115503_b27) 2021; 69
Guo (10.1016/j.cam.2023.115503_b19) 2021; 20
Regue (10.1016/j.cam.2023.115503_b6) 2001; 43
Huang (10.1016/j.cam.2023.115503_b30) 2018; 60
Yao (10.1016/j.cam.2023.115503_b26) 2019; 18
10.1016/j.cam.2023.115503_b29
Li (10.1016/j.cam.2023.115503_b10) 2013; 55
10.1016/j.cam.2023.115503_b23
Yao (10.1016/j.cam.2023.115503_b28) 2022; 70
Jin (10.1016/j.cam.2023.115503_b34) 2017; 26
10.1016/j.cam.2023.115503_b21
Yu (10.1016/j.cam.2023.115503_b7) 2007; 45
Zhang (10.1016/j.cam.2023.115503_b25) 2017; 59
Li (10.1016/j.cam.2023.115503_b3) 2013; 29
Yao (10.1016/j.cam.2023.115503_b4) 2018; 76
10.1016/j.cam.2023.115503_b15
10.1016/j.cam.2023.115503_b38
10.1016/j.cam.2023.115503_b13
10.1016/j.cam.2023.115503_b35
Kleinman (10.1016/j.cam.2023.115503_b9) 1994; 29
Li (10.1016/j.cam.2023.115503_b12) 2013; 61
Massa (10.1016/j.cam.2023.115503_b14) 2019; 18
Kim (10.1016/j.cam.2023.115503_b37) 2017
10.1016/j.cam.2023.115503_b8
10.1016/j.cam.2023.115503_b18
Yao (10.1016/j.cam.2023.115503_b22) 2022
Catedra (10.1016/j.cam.2023.115503_b36) 1995
Shan (10.1016/j.cam.2023.115503_b31) 2021
Wuttke (10.1016/j.cam.2023.115503_b33) 2021; 11
Pastorino (10.1016/j.cam.2023.115503_b2) 2010
Li (10.1016/j.cam.2023.115503_b5) 2017; 59
Li (10.1016/j.cam.2023.115503_b11) 2010; 58
Yao (10.1016/j.cam.2023.115503_b17) 2020; 19
Badrinarayanan (10.1016/j.cam.2023.115503_b32) 2017; 39
Shan (10.1016/j.cam.2023.115503_b20) 2020; 68
Chew (10.1016/j.cam.2023.115503_b1) 2001
References_xml – reference: J. Cong, B. Xiao, Minimizing computation in convolutional neural networks, in: Proc. Int. Conf. Artif. Neural Netw., 2014, pp. 281–290.
– volume: 20
  start-page: 538
  year: 2021
  end-page: 542
  ident: b19
  article-title: Solving combined field integral equation with deep neural network for 2-D conducting object
  publication-title: IEEE Antennas Wirel. Propag. Lett.
– volume: 18
  year: 2019
  ident: b26
  article-title: Two-step enhanced deep learning approach for electromagnetic inverse scattering problems
  publication-title: IEEE Antennas Wirel. Propag. Lett.
– year: 2010
  ident: b2
  article-title: Microwave Imaging
– year: 2021
  ident: b31
  article-title: Physics-informed supervised residual learning for 2D electromagnetic forward modeling
– volume: 76
  start-page: 91
  year: 2018
  end-page: 99
  ident: b4
  article-title: Applying convolutional neural networks for the source reconstruction
  publication-title: Prog. Electromagn. Res. M
– volume: 45
  start-page: 1258
  year: 2007
  end-page: 1270
  ident: b7
  article-title: Three-dimensional Bayesian inversion with application to subsurface sensing
  publication-title: IEEE Trans. Geosci. Remote Sens.
– reference: Z. Lin, R. Guo, M. Li, F. Yang, S. Xu, A. Abubakar, Study on the Degrees of Freedom of Scattered Fields in Nonlinear Inverse Scattering Problems, in: 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, APS/URSI, 2021, pp. 1845–1846.
– volume: 43
  start-page: 520
  year: 2001
  end-page: 530
  ident: b6
  article-title: A genetic algorithm based method for source identification and far-field radiated emissions prediction from near-field measurements for PCB characterization
  publication-title: IEEE Trans. Electromagn. Compat.
– year: 2017
  ident: b37
  article-title: MATLAB Deep Learning
– volume: 68
  start-page: 6725
  year: 2020
  end-page: 6733
  ident: b20
  article-title: Study on a fast solver for Poisson’s equation based on deep learning technique
  publication-title: IEEE Trans. Antennas Propag.
– volume: 55
  start-page: 933
  year: 2013
  end-page: 940
  ident: b10
  article-title: Source reconstruction method-based radiated emission characterization for PCBs
  publication-title: IEEE Trans. Electromagn. Compat.
– volume: 11
  start-page: 1
  year: 2021
  end-page: 15
  ident: b33
  article-title: Wave based damage detection in solid structures using spatially asymmetric encoder–decoder network
  publication-title: Sci. Rep.
– year: 1995
  ident: b36
  article-title: The CG-FFT Method: Application of Signal Processing Techniques to Electromagnetics
– reference: X. Song, M. Li, A. Abubakar, A Regularization Scheme Based on Gaussian Mixture Model for EM Data Inversion, in: 2020 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization, NEMO, China, 2020, pp. 1–4.
– volume: 69
  start-page: 4366
  year: 2021
  ident: b27
  article-title: Low-frequency data prediction with iterative learning for highly nonlinear inverse scattering problems
  publication-title: IEEE Trans. Microw. Theory Tech.
– volume: 70
  start-page: 6195
  year: 2022
  end-page: 6206
  ident: b28
  article-title: Enhanced supervised descent learning technique for electromagnetic inverse scattering problems by the deep convolutional neural networks
  publication-title: IEEE Trans. Antennas Propag.
– reference: H.M. Yao, L. Jiang, H.H. Zhang, W.E.I. Sha, Machine Learning Methodology Review for Computational Electromagnetics, in: 2019 ACES, Nanjing, China, 2019, pp. 1–4.
– volume: 58
  start-page: 8013
  year: 2020
  end-page: 8025
  ident: b16
  article-title: A supervised descent learning technique for solving directional electromagnetic logging-while-drilling inverse problems
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 60
  start-page: 1640
  year: 2018
  end-page: 1647
  ident: b30
  article-title: Machine learning based source reconstruction for RF desense
  publication-title: IEEE Trans. Electromagn. Compat.
– volume: 39
  start-page: 2481
  year: 2017
  end-page: 2495
  ident: b32
  article-title: SegNet: A deep convolutional encoder-decoder architecture for image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 59
  start-page: 1152
  year: 2017
  end-page: 1160
  ident: b25
  article-title: Transient heterogeneous electromagnetic simulation with DGTD and behavioral macromodel
  publication-title: IEEE Trans. Electromagn. Compat.
– volume: 58
  start-page: 455
  year: 2010
  end-page: 467
  ident: b11
  article-title: Inversion of controlled-source electromagnetic data using a model-based approach
  publication-title: Geophys. Prospect.
– reference: M. Salucci, M. Arrebola, T. Shan, M. Li, Artificial Intelligence: New Frontiers in Real–Time Inverse Scattering and Electromagnetic Imaging, IEEE Trans. Antennas and Propagation
– volume: 19
  start-page: 1211
  year: 2020
  end-page: 1215
  ident: b17
  article-title: Enhanced deep learning approach based on the deep convolutional encoder-decoder architecture for electromagnetic inverse scattering problems
  publication-title: IEEE Antennas Wirel. Propag. Lett.
– volume: 61
  start-page: 5338
  year: 2013
  end-page: 5343
  ident: b12
  article-title: A wide-band equivalent source reconstruction method exploiting the stoer-bulirsch algorithm with the adaptive frequency sampling
  publication-title: IEEE Trans. Antennas and Propagation
– reference: .
– reference: D.P. Kingma, J.L. Ba, Adam: A method for stochastic optimization, in: Proc. Int. Conf. Learn. Represent., 2015, pp. 1–41.
– reference: L. Guo, M. Li, S. Xu, F. Yang, L. Liu, Electromagnetic Modeling Using an FDTD-Equivalent Recurrent Convolution Neural Network: Accurate Computing on a Deep Learning Framework, IEEE Antennas Propag. Mag.
– year: 2001
  ident: b1
  article-title: Fast and Efficient Algorithms in Computational Electromagnetics
– volume: 29
  start-page: 1157
  year: 1994
  end-page: 1169
  ident: b9
  article-title: Two-dimensional location and shape reconstruction
  publication-title: Radio Sci.
– reference: H.M. Yao, L. Jiang, W.E.I. Sha, Source Reconstruction Method based on Machine Learning Algorithms, in: 2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC, Sapporo, Japan, 2019, pp. 774–777.
– volume: 18
  start-page: 2225
  year: 2019
  end-page: 2229
  ident: b14
  article-title: DNNs as applied to electromagnetics, antennas, and propagation—A review
  publication-title: IEEE Antennas Wirel. Propag. Lett.
– year: 2022
  ident: b22
  article-title: Implementing the fast full wave electromagnetic forward solver using the deep convolutional encoder-decoder architecture
  publication-title: IEEE Trans. Antennas and Propagation
– volume: 26
  start-page: 4509
  year: 2017
  ident: b34
  article-title: Deep convolutional neural network for inverse problems in imaging
  publication-title: IEEE Trans. Image Process.
– reference: T. Shan, R. Guo, M. Li, F. Yang, S. Xu, L. Liang, Application of Multitask Learning for 2-D Modeling of Magnetotelluric Surveys: TE Case, IEEE Trans. Geosci. Remote Sens.
– volume: 29
  year: 2013
  ident: b3
  article-title: A contrast source inversion method in the wavelet domain
  publication-title: Inverse Probl.
– volume: 59
  start-page: 9
  year: 2017
  end-page: 115
  ident: b5
  article-title: Electromagnetic inverse problems
  publication-title: IEEE Antennas Propag. Mag.
– volume: 64
  start-page: 3233
  year: 2016
  end-page: 3238
  ident: b24
  article-title: Embedding the behavior macromodel into TDIE for transient field-circuit simulations
  publication-title: IEEE Trans. Antennas Propag.
– volume: 29
  start-page: 1157
  year: 1994
  ident: 10.1016/j.cam.2023.115503_b9
  article-title: Two-dimensional location and shape reconstruction
  publication-title: Radio Sci.
  doi: 10.1029/93RS03445
– ident: 10.1016/j.cam.2023.115503_b35
  doi: 10.1007/978-3-319-11179-7_36
– volume: 61
  start-page: 5338
  issue: 10
  year: 2013
  ident: 10.1016/j.cam.2023.115503_b12
  article-title: A wide-band equivalent source reconstruction method exploiting the stoer-bulirsch algorithm with the adaptive frequency sampling
  publication-title: IEEE Trans. Antennas and Propagation
  doi: 10.1109/TAP.2013.2274032
– volume: 70
  start-page: 6195
  issue: 8
  year: 2022
  ident: 10.1016/j.cam.2023.115503_b28
  article-title: Enhanced supervised descent learning technique for electromagnetic inverse scattering problems by the deep convolutional neural networks
  publication-title: IEEE Trans. Antennas Propag.
  doi: 10.1109/TAP.2022.3196496
– ident: 10.1016/j.cam.2023.115503_b21
  doi: 10.1109/MAP.2021.3127514
– volume: 76
  start-page: 91
  year: 2018
  ident: 10.1016/j.cam.2023.115503_b4
  article-title: Applying convolutional neural networks for the source reconstruction
  publication-title: Prog. Electromagn. Res. M
  doi: 10.2528/PIERM18082907
– ident: 10.1016/j.cam.2023.115503_b23
  doi: 10.1109/TGRS.2021.3101119
– ident: 10.1016/j.cam.2023.115503_b15
  doi: 10.1109/APS/URSI47566.2021.9704363
– volume: 45
  start-page: 1258
  issue: 5
  year: 2007
  ident: 10.1016/j.cam.2023.115503_b7
  article-title: Three-dimensional Bayesian inversion with application to subsurface sensing
  publication-title: IEEE Trans. Geosci. Remote Sens.
  doi: 10.1109/TGRS.2007.894932
– volume: 60
  start-page: 1640
  issue: 6
  year: 2018
  ident: 10.1016/j.cam.2023.115503_b30
  article-title: Machine learning based source reconstruction for RF desense
  publication-title: IEEE Trans. Electromagn. Compat.
  doi: 10.1109/TEMC.2018.2797132
– volume: 26
  start-page: 4509
  issue: 9
  year: 2017
  ident: 10.1016/j.cam.2023.115503_b34
  article-title: Deep convolutional neural network for inverse problems in imaging
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2017.2713099
– volume: 68
  start-page: 6725
  issue: 9
  year: 2020
  ident: 10.1016/j.cam.2023.115503_b20
  article-title: Study on a fast solver for Poisson’s equation based on deep learning technique
  publication-title: IEEE Trans. Antennas Propag.
  doi: 10.1109/TAP.2020.2985172
– volume: 59
  start-page: 9
  issue: 5
  year: 2017
  ident: 10.1016/j.cam.2023.115503_b5
  article-title: Electromagnetic inverse problems
  publication-title: IEEE Antennas Propag. Mag.
  doi: 10.1109/MAP.2017.2731203
– volume: 29
  issue: 2
  year: 2013
  ident: 10.1016/j.cam.2023.115503_b3
  article-title: A contrast source inversion method in the wavelet domain
  publication-title: Inverse Probl.
  doi: 10.1088/0266-5611/29/2/025015
– year: 2021
  ident: 10.1016/j.cam.2023.115503_b31
– volume: 19
  start-page: 1211
  issue: 7
  year: 2020
  ident: 10.1016/j.cam.2023.115503_b17
  article-title: Enhanced deep learning approach based on the deep convolutional encoder-decoder architecture for electromagnetic inverse scattering problems
  publication-title: IEEE Antennas Wirel. Propag. Lett.
  doi: 10.1109/LAWP.2020.2995455
– year: 2010
  ident: 10.1016/j.cam.2023.115503_b2
– volume: 11
  start-page: 1
  issue: 1
  year: 2021
  ident: 10.1016/j.cam.2023.115503_b33
  article-title: Wave based damage detection in solid structures using spatially asymmetric encoder–decoder network
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-021-00326-2
– volume: 43
  start-page: 520
  issue: 4
  year: 2001
  ident: 10.1016/j.cam.2023.115503_b6
  article-title: A genetic algorithm based method for source identification and far-field radiated emissions prediction from near-field measurements for PCB characterization
  publication-title: IEEE Trans. Electromagn. Compat.
  doi: 10.1109/15.974631
– volume: 59
  start-page: 1152
  issue: 4
  year: 2017
  ident: 10.1016/j.cam.2023.115503_b25
  article-title: Transient heterogeneous electromagnetic simulation with DGTD and behavioral macromodel
  publication-title: IEEE Trans. Electromagn. Compat.
  doi: 10.1109/TEMC.2016.2642955
– volume: 18
  start-page: 2225
  issue: 11
  year: 2019
  ident: 10.1016/j.cam.2023.115503_b14
  article-title: DNNs as applied to electromagnetics, antennas, and propagation—A review
  publication-title: IEEE Antennas Wirel. Propag. Lett.
  doi: 10.1109/LAWP.2019.2916369
– ident: 10.1016/j.cam.2023.115503_b13
  doi: 10.23919/ACES48530.2019.9060439
– volume: 39
  start-page: 2481
  issue: 12
  year: 2017
  ident: 10.1016/j.cam.2023.115503_b32
  article-title: SegNet: A deep convolutional encoder-decoder architecture for image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2016.2644615
– year: 1995
  ident: 10.1016/j.cam.2023.115503_b36
– year: 2017
  ident: 10.1016/j.cam.2023.115503_b37
– volume: 58
  start-page: 455
  issue: 3
  year: 2010
  ident: 10.1016/j.cam.2023.115503_b11
  article-title: Inversion of controlled-source electromagnetic data using a model-based approach
  publication-title: Geophys. Prospect.
  doi: 10.1111/j.1365-2478.2009.00824.x
– volume: 20
  start-page: 538
  issue: 4
  year: 2021
  ident: 10.1016/j.cam.2023.115503_b19
  article-title: Solving combined field integral equation with deep neural network for 2-D conducting object
  publication-title: IEEE Antennas Wirel. Propag. Lett.
  doi: 10.1109/LAWP.2021.3056460
– year: 2022
  ident: 10.1016/j.cam.2023.115503_b22
  article-title: Implementing the fast full wave electromagnetic forward solver using the deep convolutional encoder-decoder architecture
  publication-title: IEEE Trans. Antennas and Propagation
– volume: 55
  start-page: 933
  issue: 5
  year: 2013
  ident: 10.1016/j.cam.2023.115503_b10
  article-title: Source reconstruction method-based radiated emission characterization for PCBs
  publication-title: IEEE Trans. Electromagn. Compat.
  doi: 10.1109/TEMC.2012.2235837
– volume: 58
  start-page: 8013
  issue: 11
  year: 2020
  ident: 10.1016/j.cam.2023.115503_b16
  article-title: A supervised descent learning technique for solving directional electromagnetic logging-while-drilling inverse problems
  publication-title: IEEE Trans. Geosci. Remote Sens.
  doi: 10.1109/TGRS.2020.2986000
– ident: 10.1016/j.cam.2023.115503_b29
  doi: 10.23919/EMCTokyo.2019.8893747
– volume: 64
  start-page: 3233
  issue: 7
  year: 2016
  ident: 10.1016/j.cam.2023.115503_b24
  article-title: Embedding the behavior macromodel into TDIE for transient field-circuit simulations
  publication-title: IEEE Trans. Antennas Propag.
  doi: 10.1109/TAP.2016.2560901
– ident: 10.1016/j.cam.2023.115503_b8
  doi: 10.1109/NEMO49486.2020.9343382
– ident: 10.1016/j.cam.2023.115503_b18
  doi: 10.1109/TAP.2022.3177556
– volume: 69
  start-page: 4366
  issue: 10
  year: 2021
  ident: 10.1016/j.cam.2023.115503_b27
  article-title: Low-frequency data prediction with iterative learning for highly nonlinear inverse scattering problems
  publication-title: IEEE Trans. Microw. Theory Tech.
  doi: 10.1109/TMTT.2021.3098769
– volume: 18
  issue: 11
  year: 2019
  ident: 10.1016/j.cam.2023.115503_b26
  article-title: Two-step enhanced deep learning approach for electromagnetic inverse scattering problems
  publication-title: IEEE Antennas Wirel. Propag. Lett.
  doi: 10.1109/LAWP.2019.2925578
– year: 2001
  ident: 10.1016/j.cam.2023.115503_b1
– ident: 10.1016/j.cam.2023.115503_b38
SSID ssj0006914
Score 2.4173632
Snippet This paper proposes a novel deep learning (DL) based source reconstruction method (SRM). The proposed DL-based SRM employs the deep convolutional asymmetric...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 115503
SubjectTerms Convolutional neural network
Deep learning
Real time
Source reconstruction method
Title Deep learning based source reconstruction method using asymmetric encoder–decoder​ structure and physics-induced loss
URI https://dx.doi.org/10.1016/j.cam.2023.115503
Volume 438
WOSCitedRecordID wos001097639300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0377-0427
  databaseCode: AIEXJ
  dateStart: 20211207
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0006914
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLdg2wEOaDDQPtjkw05EkbrYiZ3jBkXbJCqkDam3yHGciWlNK7pN2213jvyH_Ut4zx9JaQEBEpfITRuneu9nv-fn598jZN9UNTciq2NVMhZDs4xlCgPPMJOlYP9r1dO22IQYDORwmH_0O_hTW05ANI28u8sn_1XVcA-UjUdn_0LdbadwA9qgdLiC2uH6R4p_Z8wkFIO4iNBKYWQcQ_SRXf22jLG-enR0Y8MFano_GmF5LR0htyXyivg8CFaZ-c_yKHJdhK0HFxyZxrC6v8FsgquxT-pY9nm1rSER4o-WJ9Z7waOWPrZ18gcXi3n9ODupsbOW8IU3uj5mkfAuacsF0pYO07gDXELEWPpjfnLmjvtlaaJ3MYdLWMQjnUDCYOqHtRbrrFqba3iG_WK3CZKLcSEfk9VEpDlMgauHJ_3haWu4s9xRwYf_ETbBbTrgwot-7sbMuSbn6-SZly89dFh4Th6Z5gV5-qGT6Aa5R1TQgApqUUEdKuiPqKAOFdSignaooB4Vs4dvHg-zh6-0RQIFZdIFJFBEwkvy6X3__O1x7KtuxDrJxXWcKpVJWbKkMqpmytSlyGt9ICtWlmkqpQYH1JQKiYzANgpTKSMSDcNd1ABInrNXZKUZN2aT0IzxTMN458jQlPJaKWgeZCWrZC_nurdFekGIhfaU9FgZ5aoIuYeXBci9QLkXTu5b5E37yMTxsfzuxzxopvAOpXMUC4DRrx_b_rfHdsiTDuuvyQoowOySNX17_Xn6Zc-D7TtvgaBW
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+learning+based+source+reconstruction+method+using+asymmetric+encoder%E2%80%93decoder%E2%80%8B+structure+and+physics-induced+loss&rft.jtitle=Journal+of+computational+and+applied+mathematics&rft.au=Ng%2C+Michael&rft.au=Yao%2C+He+Ming&rft.date=2024-03-01&rft.pub=Elsevier+B.V&rft.issn=0377-0427&rft.volume=438&rft_id=info:doi/10.1016%2Fj.cam.2023.115503&rft.externalDocID=S0377042723004478
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0377-0427&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0377-0427&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0377-0427&client=summon