Fast Full Wave Electromagnetic Forward Solver Based on Deep Conditional Convolutional Autoencoders

This paper proposes a novel deep learning (DL) based fast solver for the electromagnetic forward (EMF) process. This proposed fast full-wave solver for EMF process is designed based on the deep conditional convolutional autoencoder (DCCAE), consisting of a complex-valued deep convolutional encoder n...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE antennas and wireless propagation letters Ročník 22; číslo 4; s. 1 - 5
Hlavní autori: Zhang, Huan Huan, Yao, He Ming, Jiang, Lijun, Ng, Michael
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.04.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:1536-1225, 1548-5757
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 fast solver for the electromagnetic forward (EMF) process. This proposed fast full-wave solver for EMF process is designed based on the deep conditional convolutional autoencoder (DCCAE), consisting of a complex-valued deep convolutional encoder network and its corresponding complex-valued deep convolutional decoder network. The encoder network makes use of the input consisting of the incident EM wave and the contrast (permittivities) distribution of the target domain, while the corresponding decoder network predicts the total EM field illuminated by the input incident EM wave. The training of the proposed DCCAE solver for EMF is merely based on the simple synthetic dataset. Thanks to its strong approximation capability, the proposed DCCAE can realize the prediction of the EM field of target domain by using the incident EM field and the distribution of contrasts (permittivities). Therefore, compared with conventional methods, the EMF problem could be solved with higher accuracy and the significant reduced computation time. Numerical examples have illustrated the feasibility of the newly proposed DL based EMF solver. The newly proposed DL-based EMF solver presents its excellent performance for the real-time online application.
AbstractList This paper proposes a novel deep learning (DL) based fast solver for the electromagnetic forward (EMF) process. This proposed fast full-wave solver for EMF process is designed based on the deep conditional convolutional autoencoder (DCCAE), consisting of a complex-valued deep convolutional encoder network and its corresponding complex-valued deep convolutional decoder network. The encoder network makes use of the input consisting of the incident EM wave and the contrast (permittivities) distribution of the target domain, while the corresponding decoder network predicts the total EM field illuminated by the input incident EM wave. The training of the proposed DCCAE solver for EMF is merely based on the simple synthetic dataset. Thanks to its strong approximation capability, the proposed DCCAE can realize the prediction of the EM field of target domain by using the incident EM field and the distribution of contrasts (permittivities). Therefore, compared with conventional methods, the EMF problem could be solved with higher accuracy and the significant reduced computation time. Numerical examples have illustrated the feasibility of the newly proposed DL based EMF solver. The newly proposed DL-based EMF solver presents its excellent performance for the real-time online application.
This letter proposes a novel deep learning (DL) based fast solver for the electromagnetic forward (EMF) process. This proposed fast full-wave solver for EMF process is designed based on the deep conditional convolutional autoencoder (DCCAE), consisting of a complex-valued deep convolutional encoder network and its corresponding complex-valued deep convolutional decoder network. The encoder network makes use of the input consisting of the incident electromagnetic (EM) wave and the contrast (permittivities) distribution of the target domain, while the corresponding decoder network predicts the total EM field illuminated by the input incident EM wave. The training of the proposed DCCAE solver for EMF is merely based on the simple synthetic dataset. Thanks to its strong approximation capability, the proposed DCCAE can realize the prediction of the EM field of target domain by using the incident EM field and the distribution of contrasts (permittivities). Therefore, compared with conventional methods, the EMF problem could be solved with higher accuracy and the significant reduced computation time. Numerical examples have illustrated the feasibility of the newly proposed DL-based EMF solver. The newly proposed DL-based EMF solver presents its excellent performance for the real-time online application.
Author Yao, He Ming
Jiang, Lijun
Ng, Michael
Zhang, Huan Huan
Author_xml – sequence: 1
  givenname: Huan Huan
  orcidid: 0000-0003-4579-832X
  surname: Zhang
  fullname: Zhang, Huan Huan
  organization: Xidian University, Xi'an, China
– sequence: 2
  givenname: He Ming
  orcidid: 0000-0003-2814-9539
  surname: Yao
  fullname: Yao, He Ming
  organization: Department of Mathematics, The University of Hong Kong, Pokfulam Road, Hong Kong, China
– sequence: 3
  givenname: Lijun
  orcidid: 0000-0002-7391-6322
  surname: Jiang
  fullname: Jiang, Lijun
  organization: Department of Electrical and Electronic Engineering, The University of Hong Kong, Pokfulam Road, Hong Kong, China
– sequence: 4
  givenname: Michael
  orcidid: 0000-0001-6833-5227
  surname: Ng
  fullname: Ng, Michael
  organization: Department of Mathematics, The University of Hong Kong, Pokfulam Road, Hong Kong, China
BookMark eNp9UMtKA0EQHCSCMfoB4mXA88Z57GuOMSYqBBRUchzm0SsbNjtxZjbi37tLggcPnrq6qeruqnM0al0LCF1RMqWUiNvVbP0yZYSxKWcsFSU_QWOapWWSFVkxGjDPE8pYdobOQ9gQQos842OklypEvOyaBq_VHvCiARO926qPFmJt8NL5L-UtfnXNHjy-UwEsdi2-B9jhuWttHWvXqmbAe9d0x27WRQetcRZ8uECnlWoCXB7rBL0vF2_zx2T1_PA0n60SwwSPSUVSbbWu8oIJkqoyMwzyLC-NpTQ1YLlQJTGGZLkVvWXbz3SRGqp1qQ3hFZ-gm8PenXefHYQoN67z_TdBskIUrMyZYD2LHljGuxA8VHLn663y35ISOUQphyjlEKU8Rtlrij8aU0c1WI1e1c2_yuuDsgaA30tC5GlP4D9x6YRg
CODEN IAWPA7
CitedBy_id crossref_primary_10_1007_s00366_024_02056_1
crossref_primary_10_1109_TAP_2024_3369683
crossref_primary_10_1109_JSTARS_2023_3343526
crossref_primary_10_1109_LAWP_2024_3372437
crossref_primary_10_3390_app131810521
crossref_primary_10_1109_LAWP_2024_3424940
Cites_doi 10.1109/MAP.2017.2731203
10.1007/978-1-4615-7566-5
10.1109/TAP.2020.2985172
10.1109/TAP.2022.3216920
10.1109/MAP.2020.3021433
10.1109/TEMC.2016.2642955
10.1002/9781119311997.app4
10.1038/nature14539
10.1109/TAP.2022.3177556
10.1109/TIE.2020.3013492
10.1002/9780470602492
10.1007/978-1-4842-2845-6
10.1109/TAP.2022.3196496
10.1145/2835776.2835837
10.1007/978-3-642-21735-7_7
10.1109/LAWP.2019.2916369
10.1109/TII.2020.3011441
10.1007/978-3-319-11179-7_36
10.1109/APUSNCURSINRSM.2017.8072529
10.1016/j.neucom.2013.09.055
10.2528/PIERM18082907
10.1109/TGRS.2018.2869221
10.1109/ACCESS.2020.2969569
10.1109/TAP.2010.2103027
10.1109/9780470544631
10.1109/TIP.2017.2713099
10.1109/TAP.2016.2560901
10.1109/TGRS.2020.3032743
10.1109/MAP.2004.1388823
10.1109/APUSNCURSINRSM.2018.8608745
10.1109/MSP.2017.2739299
10.3390/computation8010015
10.1109/LAWP.2020.2995455
10.1109/LAWP.2019.2925578
10.1109/ACCESS.2019.2915263
10.1109/TAP.2021.3139627
10.1109/TAP.1966.1138693
10.1201/b17623
10.1109/LAWP.2018.2885570
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
DOI 10.1109/LAWP.2022.3224983
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1548-5757
EndPage 5
ExternalDocumentID 10_1109_LAWP_2022_3224983
9964224
Genre orig-research
GrantInformation_xml – fundername: Asian Office of Aerospace Research and Development; AOARD
  grantid: FA2386-17-1-0010
  funderid: 10.13039/100018237
– fundername: Research Grants Council of the Hong Kong Special Administrative Region, China
  grantid: HKU PDFS2122-7S05
– fundername: Research Grants Council of Hong Kong
  grantid: GRF 17207114; GRF 17210815
– fundername: Hong Kong Research Grant Council GRF
  grantid: 12300218; 12300519; 17201020; 17209918; 12306616; 12200317
– fundername: Hong Kong UGC
  grantid: AoE/P-04/08
– fundername: National Natural Science Foundation of China; NSFC
  grantid: 61271158
  funderid: 10.13039/501100001809
– fundername: Joint NSFC-RGC
  grantid: N-HKU76921
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AASAJ
AAWTH
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
AAYXX
AETIX
AGSQL
AIBXA
CITATION
EJD
7SP
8FD
AARMG
ABAZT
L7M
ID FETCH-LOGICAL-c293t-f04bdbbf672904a85c2e6568cd114ced39a80cc056d9110d4ceb74c1bb8bc03f3
IEDL.DBID RIE
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000967399800023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1536-1225
IngestDate Mon Jun 30 07:08:45 EDT 2025
Sat Nov 29 02:08:19 EST 2025
Tue Nov 18 20:45:57 EST 2025
Tue Nov 25 14:44:28 EST 2025
IsPeerReviewed false
IsScholarly true
Issue 4
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c293t-f04bdbbf672904a85c2e6568cd114ced39a80cc056d9110d4ceb74c1bb8bc03f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-6833-5227
0000-0003-4579-832X
0000-0003-2814-9539
0000-0002-7391-6322
PQID 2797286292
PQPubID 75732
PageCount 5
ParticipantIDs crossref_primary_10_1109_LAWP_2022_3224983
proquest_journals_2797286292
crossref_citationtrail_10_1109_LAWP_2022_3224983
ieee_primary_9964224
PublicationCentury 2000
PublicationDate 2023-04-01
PublicationDateYYYYMMDD 2023-04-01
PublicationDate_xml – month: 04
  year: 2023
  text: 2023-04-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE antennas and wireless propagation letters
PublicationTitleAbbrev LAWP
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref35
ref12
ref34
Kingma (ref45)
ref15
ref37
ref14
ref36
ref31
ref30
ref11
ref33
ref32
ref2
ref17
ref39
ref16
ref19
ref18
Tschannen (ref38) 2018
Alpaydin (ref10) 2020
Catedra (ref47) 1995
ref24
ref46
ref23
Reitich (ref8) 2004; 5
ref26
ref25
Chew (ref1) 2001
ref20
ref42
ref41
ref22
ref44
ref21
ref43
ref28
ref27
Bondeson (ref4) 2005; 51
ref29
ref7
Zhang (ref40) 2018
ref9
ref3
ref6
ref5
References_xml – volume-title: The CG-FFT Method: Application of Signal Processing Techniques to Electromagnetics
  year: 1995
  ident: ref47
– ident: ref2
  doi: 10.1109/MAP.2017.2731203
– volume: 5
  start-page: 287
  issue: 4
  year: 2004
  ident: ref8
  article-title: State-of-the-art trends and directions in computational electromagnetics
  publication-title: Comput. Model. Eng. Sci.
– ident: ref9
  doi: 10.1007/978-1-4615-7566-5
– ident: ref17
  doi: 10.1109/TAP.2020.2985172
– volume: 51
  volume-title: Computational Electromagnetics
  year: 2005
  ident: ref4
– ident: ref23
  doi: 10.1109/TAP.2022.3216920
– volume-title: Introduction to Machine Learning
  year: 2020
  ident: ref10
– ident: ref29
  doi: 10.1109/MAP.2020.3021433
– ident: ref22
  doi: 10.1109/TEMC.2016.2642955
– ident: ref33
  doi: 10.1002/9781119311997.app4
– ident: ref11
  doi: 10.1038/nature14539
– ident: ref26
  doi: 10.1109/TAP.2022.3177556
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref45
  article-title: Adam: A method for stochastic optimization
– ident: ref35
  doi: 10.1109/TIE.2020.3013492
– ident: ref3
  doi: 10.1002/9780470602492
– ident: ref44
  doi: 10.1007/978-1-4842-2845-6
– ident: ref19
  doi: 10.1109/TAP.2022.3196496
– ident: ref37
  doi: 10.1145/2835776.2835837
– ident: ref39
  doi: 10.1007/978-3-642-21735-7_7
– ident: ref28
  doi: 10.1109/LAWP.2019.2916369
– ident: ref34
  doi: 10.1109/TII.2020.3011441
– ident: ref46
  doi: 10.1007/978-3-319-11179-7_36
– year: 2018
  ident: ref38
  article-title: Recent advances in autoencoder-based representation learning
– volume-title: Fast and Efficient Algorithms in Computational Electromagnetics
  year: 2001
  ident: ref1
– ident: ref16
  doi: 10.1109/APUSNCURSINRSM.2017.8072529
– ident: ref36
  doi: 10.1016/j.neucom.2013.09.055
– ident: ref15
  doi: 10.2528/PIERM18082907
– ident: ref42
  doi: 10.1109/TGRS.2018.2869221
– ident: ref25
  doi: 10.1109/ACCESS.2020.2969569
– ident: ref32
  doi: 10.1109/TAP.2010.2103027
– year: 2018
  ident: ref40
  article-title: A better autoencoder for image: Convolutional autoencoder
– ident: ref5
  doi: 10.1109/9780470544631
– ident: ref43
  doi: 10.1109/TIP.2017.2713099
– ident: ref21
  doi: 10.1109/TAP.2016.2560901
– ident: ref14
  doi: 10.1109/TGRS.2020.3032743
– ident: ref7
  doi: 10.1109/MAP.2004.1388823
– ident: ref18
  doi: 10.1109/APUSNCURSINRSM.2018.8608745
– ident: ref27
  doi: 10.1109/MSP.2017.2739299
– ident: ref13
  doi: 10.3390/computation8010015
– ident: ref20
  doi: 10.1109/LAWP.2020.2995455
– ident: ref41
  doi: 10.1109/LAWP.2019.2925578
– ident: ref12
  doi: 10.1109/ACCESS.2019.2915263
– ident: ref30
  doi: 10.1109/TAP.2021.3139627
– ident: ref6
  doi: 10.1109/TAP.1966.1138693
– ident: ref31
  doi: 10.1201/b17623
– ident: ref24
  doi: 10.1109/LAWP.2018.2885570
SSID ssj0017653
Score 2.405186
Snippet This paper proposes a novel deep learning (DL) based fast solver for the electromagnetic forward (EMF) process. This proposed fast full-wave solver for EMF...
This letter proposes a novel deep learning (DL) based fast solver for the electromagnetic forward (EMF) process. This proposed fast full-wave solver for EMF...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Coders
Convolutional Neural Network
Decoding
Deep Learning
Domains
Electromagnetic Forward Process
Electromagnetics
Feature extraction
Mathematical models
Real Time
Real-time systems
Solvers
Synthetic data
Training
Transmitters
Title Fast Full Wave Electromagnetic Forward Solver Based on Deep Conditional Convolutional Autoencoders
URI https://ieeexplore.ieee.org/document/9964224
https://www.proquest.com/docview/2797286292
Volume 22
WOSCitedRecordID wos000967399800023&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1548-5757
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017653
  issn: 1536-1225
  databaseCode: RIE
  dateStart: 20020101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UPOjBt7i-yMGTWM22aZMcfS0eRAQVvZU8RdBWdrv7-82kdVEUwVtoE1ryJZmZzOMDOMgLoXIleeILJhMmqEiE5FniTda3jFplMh_JJvjNjXh6krczcDTNhXHOxeAzd4zN6Mu3tRnjVdlJ0M1ZEDmzMMt50eZqTT0GvIgVJ8MGRl6ZNO88mH0qT65PH2-DJZimx2H1MimybzIokqr8OImjeBks_-_HVmCpUyPJaYv7Ksy4ag0WvxQXXAc9UKOGoIlJHtXEkcuW8OZNPVeYuEgG9RAjZsldjcHR5CyIM0vqilw4907Oa3Rlx2tCbE-6BYqfHDc1Fr_EAOgNeBhc3p9fJR2jQmKCWG8ST5m2WvsiqNSUKZGb1AWFThgbzCLjbCaVoMYEpciGQ5Da8ExzZvpaC21o5rNNmKvqym0B8UopYzUNrxgz0kqRasuc99L6IneiB_RzjkvTlRtH1ovXMpodVJYIS4mwlB0sPTicDnlva2381XkdcZh27CDowe4nkGW3G0dlyiVPg-km0-3fR-3AAtLItxE5uzDXDMduD-bNpHkZDffjQvsAGInSRw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB5RqFQ48CgglqcPPVUEvI6T2EdeK6puV0gFwS3yE1UqCdrN7u_H44QVVatK3KzEViJ_tmfG8_gAvmS5UJmSReJzLhMuqEiELNLEm7RvObXKpD6STRSjkXh4kDcLcDzPhXHOxeAzd4LN6Mu3tZniVdlp0M15EDkfYCnjnNE2W2vuMyjyWHMybGFklmFZ58PsU3k6PLu_CbYgYydh_XIp0j-kUKRV-essjgJmsPa-X1uH1U6RJGct8huw4KrPsPKmvOAm6IGaNASNTHKvZo5ctZQ3T-qxwtRFMqjHGDNLftYYHk3Og0CzpK7IpXPP5KJGZ3a8KMT2rFui-MlpU2P5SwyB3oK7wdXtxXXScSokJgj2JvGUa6u1z4NSTbkSmWEuqHTC2GAYGWdTqQQ1JqhFNhyD1IZnuuCmr7XQhqY-3YbFqq7cDhCvlDJW0_CKcyOtFExb7ryX1ueZEz2gr3Ncmq7gOPJe_C6j4UFlibCUCEvZwdKDr_Mhz221jf913kQc5h07CHqw_wpk2e3HSckKWbBgvEm2--9RR_Dp-vbHsBx-G33fg2UklW_jc_ZhsRlP3QF8NLPm12R8GBfdCy5p1Y4
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=Fast+Full-Wave+Electromagnetic+Forward+Solver+Based+on+Deep+Conditional+Convolutional+Autoencoders&rft.jtitle=IEEE+antennas+and+wireless+propagation+letters&rft.au=Huan+Huan+Zhang&rft.au=Yao%2C+He+Ming&rft.au=Jiang%2C+Lijun&rft.au=Ng%2C+Michael&rft.date=2023-04-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1536-1225&rft.eissn=1548-5757&rft.volume=22&rft.issue=4&rft.spage=779&rft_id=info:doi/10.1109%2FLAWP.2022.3224983&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1536-1225&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1536-1225&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1536-1225&client=summon