Inverse design of reflective metasurface antennas using deep learning from small‐scale statistically random pico‐cells

A small‐scale data‐selection method is proposed for deep‐learning‐based inverse design of reflective metasurface antennas (MAs). The overall design process involves discretization, coding, data selection, simulation, feature representation, training, prediction, and metasurface design. Unlike conven...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Microwave and optical technology letters Ročník 66; číslo 2
Hlavní autoři: You, Xi Chong, Lin, Feng Han
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Wiley Subscription Services, Inc 01.02.2024
Témata:
ISSN:0895-2477, 1098-2760
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract A small‐scale data‐selection method is proposed for deep‐learning‐based inverse design of reflective metasurface antennas (MAs). The overall design process involves discretization, coding, data selection, simulation, feature representation, training, prediction, and metasurface design. Unlike conventional method that selects the training data empirically after simulation from a large quantity of unit cells, the proposed statistically random data filtering (SRDF) method selects the training data set randomly before simulation by leveraging the geometric‐coding statistics of the unit cells. The advantages of the proposed data‐selection method include lower simulation cost (due to fewer simulations needed), improved generality, and higher design accuracy simultaneously. The design process starts from the discretization of a unit cell into a grid array of binaurally‐coded pico‐cells. Afterwards, the proposed SRDF method selects 0.01% of all the possible unit cells for simulation. With the simulated results, a deep‐convolutional‐variational‐autoencoder network is trained, leading to an accurate and bidirectional prediction of both the geometry and reflection phase of a unit cell in seconds. The proposed data‐selection method is validated by designing two reflective MAs with the predicted unit cells, each pointing a pencil beam off the boresight by 30° and 60°, respectively. Experiments are in line with full‐wave simulations.
AbstractList A small‐scale data‐selection method is proposed for deep‐learning‐based inverse design of reflective metasurface antennas (MAs). The overall design process involves discretization, coding, data selection, simulation, feature representation, training, prediction, and metasurface design. Unlike conventional method that selects the training data empirically after simulation from a large quantity of unit cells, the proposed statistically random data filtering (SRDF) method selects the training data set randomly before simulation by leveraging the geometric‐coding statistics of the unit cells. The advantages of the proposed data‐selection method include lower simulation cost (due to fewer simulations needed), improved generality, and higher design accuracy simultaneously. The design process starts from the discretization of a unit cell into a grid array of binaurally‐coded pico‐cells. Afterwards, the proposed SRDF method selects 0.01% of all the possible unit cells for simulation. With the simulated results, a deep‐convolutional‐variational‐autoencoder network is trained, leading to an accurate and bidirectional prediction of both the geometry and reflection phase of a unit cell in seconds. The proposed data‐selection method is validated by designing two reflective MAs with the predicted unit cells, each pointing a pencil beam off the boresight by 30° and 60°, respectively. Experiments are in line with full‐wave simulations.
A small‐scale data‐selection method is proposed for deep‐learning‐based inverse design of reflective metasurface antennas (MAs). The overall design process involves discretization, coding, data selection, simulation, feature representation, training, prediction, and metasurface design. Unlike conventional method that selects the training data empirically after simulation from a large quantity of unit cells, the proposed statistically random data filtering (SRDF) method selects the training data set randomly before simulation by leveraging the geometric‐coding statistics of the unit cells. The advantages of the proposed data‐selection method include lower simulation cost (due to fewer simulations needed), improved generality, and higher design accuracy simultaneously. The design process starts from the discretization of a unit cell into a grid array of binaurally‐coded pico‐cells. Afterwards, the proposed SRDF method selects 0.01% of all the possible unit cells for simulation. With the simulated results, a deep‐convolutional‐variational‐autoencoder network is trained, leading to an accurate and bidirectional prediction of both the geometry and reflection phase of a unit cell in seconds. The proposed data‐selection method is validated by designing two reflective MAs with the predicted unit cells, each pointing a pencil beam off the boresight by 30° and 60°, respectively. Experiments are in line with full‐wave simulations.
A small‐scale data‐selection method is proposed for deep‐learning‐based inverse design of reflective metasurface antennas (MAs). The overall design process involves discretization, coding, data selection, simulation, feature representation, training, prediction, and metasurface design. Unlike conventional method that selects the training data empirically after simulation from a large quantity of unit cells, the proposed statistically random data filtering (SRDF) method selects the training data set randomly before simulation by leveraging the geometric‐coding statistics of the unit cells. The advantages of the proposed data‐selection method include lower simulation cost (due to fewer simulations needed), improved generality, and higher design accuracy simultaneously. The design process starts from the discretization of a unit cell into a grid array of binaurally‐coded pico‐cells. Afterwards, the proposed SRDF method selects 0.01% of all the possible unit cells for simulation. With the simulated results, a deep‐convolutional‐variational‐autoencoder network is trained, leading to an accurate and bidirectional prediction of both the geometry and reflection phase of a unit cell in seconds. The proposed data‐selection method is validated by designing two reflective MAs with the predicted unit cells, each pointing a pencil beam off the boresight by 30° and 60°, respectively. Experiments are in line with full‐wave simulations.
Author Lin, Feng Han
You, Xi Chong
Author_xml – sequence: 1
  givenname: Xi Chong
  orcidid: 0000-0001-8839-841X
  surname: You
  fullname: You, Xi Chong
  organization: ShanghaiTech University
– sequence: 2
  givenname: Feng Han
  orcidid: 0000-0002-4964-0063
  surname: Lin
  fullname: Lin, Feng Han
  email: linfh@shanghaitech.edu.cn
  organization: ShanghaiTech University
BookMark eNp9kM1KxDAURoMoOI4ufIOAKxedSdKmbZYy-AfKuNB1SdMbiaRJTTrKuPIRfEafxIzjStDV5cL5vss9B2jXeQcIHVMyo4Swee-HWV6Qst5BE0pEnbGqJLtoQmrBM1ZU1T46iPGJEJJXFZugt2v3AiEC7iCaR4e9xgG0BTWaF8A9jDKugpYKsHQjOCcjXkXjHhMPA7Ygg9tsOvgex15a-_n-EZW0gOMoRxNHkxa7xkG6LiGDUT4RCqyNh2hPSxvh6GdO0cPF-f3iKrtZXl4vzm4yxURVZ4JpJSkTbZEXmue8k3lJRFe1WjAqdNdqxoEBFy0pqoITLmsCtM1pqYToOM-n6GTbOwT_vII4Nk9-FVw62TCR06LktCSJOt1SKvgYk4NmCKaXYd1Q0mzUNklt8602sfNfrDKbb70bgzT2v8SrsbD-u7q5Xd5tE1_CjJDR
CitedBy_id crossref_primary_10_3390_app15062883
crossref_primary_10_1109_TAP_2024_3511089
crossref_primary_10_1016_j_optlastec_2025_113723
crossref_primary_10_1088_1361_6463_add543
crossref_primary_10_1002_cpe_8276
crossref_primary_10_1109_JIOT_2025_3560682
crossref_primary_10_1016_j_compositesb_2024_111946
Cites_doi 10.1002/mop.33284
10.1109/TAP.2021.3111280
10.1109/TAP.2023.3262969
10.1109/MM.2021.3086541
10.1002/adts.201800132
10.1109/TAP.2016.2590559
10.1109/LAWP.2022.3227881
10.1109/TEMC.2023.3325438
10.1109/TAP.1963.1138112
10.1021/acs.nanolett.8b03171
10.1109/MM.2021.3061394
10.1007/11494669_93
10.1109/LAWP.2013.2270934
10.1109/TAP.2021.3138517
10.1002/jnm.2746
10.1002/mop.32656
10.1109/APS/URSI47566.2021.9704279
10.2528/PIER22062201
10.1109/TAP.2010.2103006
10.1109/TAP.2003.817983
10.1109/TAP.2022.3155204
10.1002/mop.32156
10.1109/TKDE.2009.191
10.1109/ACCESS.2023.3254204
10.1214/aoms/1177729694
10.1002/mop.32649
10.1109/TAP.2017.2671036
10.1109/TAP.2018.2860121
10.1038/s41467-021-23087-y
10.1109/TAP.2018.2854366
10.1109/TAP.2022.3226343
10.1109/TAP.2021.3060142
10.1002/mop.30769
10.1109/APS/URSI47566.2021.9703937
10.1109/TAP.2018.2806401
ContentType Journal Article
Copyright 2024 Wiley Periodicals LLC.
Copyright_xml – notice: 2024 Wiley Periodicals LLC.
DBID AAYXX
CITATION
7SP
8FD
F28
FR3
L7M
DOI 10.1002/mop.34068
DatabaseName CrossRef
Electronics & Communications Abstracts
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Engineering Research Database
Technology Research Database
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
Electronics & Communications Abstracts
DatabaseTitleList CrossRef
Engineering Research Database

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
EISSN 1098-2760
EndPage n/a
ExternalDocumentID 10_1002_mop_34068
MOP34068
Genre researchArticle
GrantInformation_xml – fundername: Lingang Laboratory
  funderid: LG‐QS‐202202‐05
– fundername: National Key Research and Development Program of China
  funderid: 2022YFB2902800
– fundername: National Natural Science Foundation of China
  funderid: 62101330
– fundername: NVIDIA Academic Hardware Grant Program
GroupedDBID .3N
.GA
.Y3
05W
0R~
10A
123
1L6
1OB
1OC
31~
33P
3SF
3WU
4.4
4ZD
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A03
AAESR
AAEVG
AAHQN
AAMMB
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDPE
ABEML
ABIJN
ABJNI
ABPVW
ACAHQ
ACBWZ
ACCZN
ACGFS
ACIWK
ACPOU
ACRPL
ACSCC
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMLS
ADNMO
ADOZA
ADXAS
ADZMN
AEFGJ
AEIGN
AEIMD
AENEX
AEUYR
AEYWJ
AFBPY
AFFNX
AFFPM
AFGKR
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGXDD
AGYGG
AHBTC
AIDQK
AIDYY
AITYG
AIURR
AJXKR
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CMOOK
CS3
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EBS
EJD
F00
F01
F04
F5P
FEDTE
G-S
G.N
GNP
GODZA
H.T
H.X
HBH
HF~
HGLYW
HHY
HVGLF
HZ~
IX1
J0M
JPC
KQQ
LATKE
LAW
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
M59
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
NNB
O66
O9-
OIG
P2P
P2W
P2X
P4D
PALCI
Q.N
Q11
QB0
QRW
R.K
RIWAO
RJQFR
ROL
RX1
RYL
SAMSI
SUPJJ
UB1
V2E
W8V
W99
WBKPD
WH7
WIH
WIK
WLBEL
WOHZO
WQJ
WXSBR
WYISQ
XG1
XPP
XV2
ZZTAW
~IA
~WT
AAYXX
AIQQE
CITATION
O8X
7SP
8FD
F28
FR3
L7M
ID FETCH-LOGICAL-c2978-92fca129b434f535da3609d7bf9219fdbf25e2e59b0474505a80e1b316c99d553
IEDL.DBID DRFUL
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001159063500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0895-2477
IngestDate Fri Jul 25 10:20:51 EDT 2025
Sat Nov 29 06:14:45 EST 2025
Tue Nov 18 22:32:16 EST 2025
Wed Aug 20 07:26:20 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2978-92fca129b434f535da3609d7bf9219fdbf25e2e59b0474505a80e1b316c99d553
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-4964-0063
0000-0001-8839-841X
PQID 2931465160
PQPubID 1006447
PageCount 11
ParticipantIDs proquest_journals_2931465160
crossref_primary_10_1002_mop_34068
crossref_citationtrail_10_1002_mop_34068
wiley_primary_10_1002_mop_34068_MOP34068
PublicationCentury 2000
PublicationDate February 2024
2024-02-00
20240201
PublicationDateYYYYMMDD 2024-02-01
PublicationDate_xml – month: 02
  year: 2024
  text: February 2024
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle Microwave and optical technology letters
PublicationYear 2024
Publisher Wiley Subscription Services, Inc
Publisher_xml – name: Wiley Subscription Services, Inc
References 2021; 69
2022; 175
2023; 11
2022; 70
2020; 63
2020; 62
2017; 65
2008; 19
2008; 9
1951; 22
2006
2005
2022; 64
2011; 59
2020; 33
2018; 66
2003; 51
2010; 22
2018; 18
2018; 2
2023; 22
2021; 12
1963; 11
2017; 59
2023
2021
2013; 12
2016; 64
2021; 41
2023; 71
e_1_2_9_31_1
e_1_2_9_11_1
e_1_2_9_34_1
e_1_2_9_10_1
e_1_2_9_35_1
e_1_2_9_13_1
e_1_2_9_12_1
e_1_2_9_33_1
Studio M (e_1_2_9_32_1) 2008; 19
e_1_2_9_15_1
e_1_2_9_38_1
e_1_2_9_14_1
e_1_2_9_39_1
e_1_2_9_17_1
e_1_2_9_36_1
e_1_2_9_16_1
e_1_2_9_19_1
e_1_2_9_18_1
e_1_2_9_20_1
e_1_2_9_40_1
e_1_2_9_22_1
e_1_2_9_21_1
e_1_2_9_24_1
e_1_2_9_23_1
e_1_2_9_8_1
e_1_2_9_7_1
e_1_2_9_6_1
Maaten LV (e_1_2_9_37_1) 2008; 9
e_1_2_9_5_1
Balanis CA (e_1_2_9_30_1) 2005
e_1_2_9_4_1
e_1_2_9_3_1
e_1_2_9_2_1
e_1_2_9_9_1
e_1_2_9_26_1
e_1_2_9_25_1
e_1_2_9_28_1
e_1_2_9_27_1
e_1_2_9_29_1
References_xml – volume: 59
  start-page: 904
  issue: 3
  year: 2011
  end-page: 913
  article-title: Dispersion characteristics of a metamaterial‐based parallel‐plate ridge gap waveguide realized by bed of nails
  publication-title: IEEE Trans Antennas Propag
– volume: 11
  start-page: 24175
  year: 2023
  end-page: 24184
  article-title: Rapid design of 3D reflectarray antennas by inverse surrogate modeling and regularization
  publication-title: IEEE Access
– volume: 22
  start-page: 1345
  issue: 10
  year: 2010
  end-page: 1359
  article-title: A survey on transfer learning
  publication-title: IEEE Trans Knowl Data Eng
– volume: 69
  start-page: 5725
  issue: 9
  year: 2021
  end-page: 5739
  article-title: A generative machine learning‐based approach for inverse design of multilayer metasurfaces
  publication-title: IEEE Trans Antennas Propag
– year: 2005
– volume: 9
  start-page: 2579
  year: 2008
  end-page: 2605
  article-title: Visualizing data using t‐SNE
  publication-title: J Mach Learn Res
– volume: 11
  start-page: 645
  issue: 6
  year: 1963
  end-page: 651
  article-title: The reflectarray antenna
  publication-title: IEEE Trans Antennas Propag
– volume: 41
  start-page: 78
  issue: 4
  year: 2021
  end-page: 83
  article-title: Rome to Milan, AMD continues its tour of Italy
  publication-title: IEEE Micro
– volume: 59
  start-page: 2575
  issue: 10
  year: 2017
  end-page: 2580
  article-title: A bandwidth‐enhanced metasurface antenna for wireless applications
  publication-title: Microwave Opt Technol Lett
– volume: 66
  start-page: 1894
  issue: 4
  year: 2018
  end-page: 1902
  article-title: A method of suppressing higher‐order modes for improving radiation performance of metasurface multiport antennas using characteristic mode analysis
  publication-title: IEEE Trans Antennas Propag
– volume: 66
  start-page: 5043
  issue: 10
  year: 2018
  end-page: 5051
  article-title: Truncated impedance‐sheet model for low‐profile broadband nonresonant‐cell metasurface antennas using characteristic mode analysis
  publication-title: IEEE Trans Antennas Propag
– volume: 63
  start-page: 1207
  issue: 4
  year: 2020
  end-page: 1212
  article-title: Low‐profile wideband dual‐circularly polarized orbital angular momentum antenna array using metasurface
  publication-title: Microwave Opt Technol Lett
– volume: 71
  start-page: 1578
  issue: 2
  year: 2023
  end-page: 1589
  article-title: Knowledge‐guided active‐base‐element modeling in machine‐learning‐assisted antenna‐array design
  publication-title: IEEE Trans Antennas Propag
– volume: 71
  start-page: 5422
  issue: 6
  year: 2023
  end-page: 5427
  article-title: A novel wideband tightly coupled dual‐polarized reflectarray antenna
  publication-title: IEEE Trans Antennas Propag
– volume: 64
  start-page: 3896
  issue: 9
  year: 2016
  end-page: 3906
  article-title: Flat optics for leaky‐waves on modulated metasurfaces: adiabatic Floquet‐wave analysis
  publication-title: IEEE Trans Antennas Propag
– volume: 22
  start-page: 79
  issue: 1
  year: 1951
  end-page: 86
  article-title: On information and sufficiency
  publication-title: Ann Math Stat
– start-page: 863
  year: 2021
  end-page: 864
– volume: 70
  start-page: 846
  issue: 2
  year: 2022
  end-page: 855
  article-title: Single‐fed triple‐mode wideband circularly polarized microstrip antennas using characteristic mode analysis
  publication-title: IEEE Trans Antennas Propag
– volume: 19
  year: 2008
  article-title: CST‐computer simulation technology
  publication-title: Bad Nuheimer Str
– volume: 12
  start-page: 737
  issue: 5
  year: 2013
  end-page: 740
  article-title: A 0.7–20‐GHz strip‐fed bilateral tapered slot antenna with low cross polarization
  publication-title: IEEE Antennas Wirel Propag Lett
– volume: 65
  start-page: 1706
  issue: 4
  year: 2017
  end-page: 1713
  article-title: Low‐profile wideband metasurface antennas using characteristic mode analysis
  publication-title: IEEE Trans Antennas Propag
– volume: 175
  start-page: 91
  year: 2022
  end-page: 104
  article-title: Low‐profile high‐gain wideband multi‐resonance microstrip‐fed slot antenna with anisotropic metasurface
  publication-title: Progr Electromagn Res
– volume: 66
  start-page: 5620
  issue: 10
  year: 2018
  end-page: 5624
  article-title: A dual‐band metasurface antenna using characteristic mode analysis
  publication-title: IEEE Trans Antennas Propag
– volume: 62
  start-page: 1366
  issue: 3
  year: 2020
  end-page: 1373
  article-title: Broadband graphene‐based metasurface solar absorber
  publication-title: Microwave Opt Technol Lett
– volume: 64
  start-page: 1339
  issue: 8
  year: 2022
  end-page: 1346
  article-title: Design of paper‐based bandpass frequency selective surface using slotlines
  publication-title: Microwave Opt Technol Lett
– volume: 18
  start-page: 6570
  issue: 10
  year: 2018
  end-page: 6576
  article-title: Generative model for the inverse design of metasurfaces
  publication-title: Nano Lett
– volume: 12
  start-page: 2974
  issue: 1
  year: 2021
  article-title: Phase‐to‐pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning
  publication-title: Nat Commun
– volume: 22
  start-page: 898
  issue: 4
  year: 2023
  end-page: 902
  article-title: Low‐profile wideband circular polarization metasurface antenna with characteristic mode analysis and mode suppression
  publication-title: IEEE Antennas Wirel Propag Lett
– year: 2006
– volume: 70
  start-page: 5078
  issue: 7
  year: 2022
  end-page: 5093
  article-title: Towards efficient reflectarray digital twins—an EM‐driven machine learning perspective
  publication-title: IEEE Trans Antennas Propag
– year: 2023
– volume: 70
  start-page: 5024
  issue: 7
  year: 2022
  end-page: 5034
  article-title: Prior‐knowledge‐guided deep‐learning‐enabled synthesis for broadband and large phase shift range metacells in metalens antenna
  publication-title: IEEE Trans Antennas Propag
– volume: 51
  start-page: 2936
  issue: 10
  year: 2003
  end-page: 2946
  article-title: Microstrip antennas integrated with electromagnetic band‐gap (EBG) structures: a low mutual coupling design for array applications
  publication-title: IEEE Trans Antennas Propag
– volume: 41
  start-page: 29
  issue: 2
  year: 2021
  end-page: 35
  article-title: Nvidia A100 tensor core GPU: performance and innovation
  publication-title: IEEE Micro
– start-page: 758
  year: 2005
  end-page: 770
– volume: 62
  start-page: 638
  issue: 2
  year: 2020
  end-page: 646
  article-title: Wideband high‐gain multiresonance antenna based on polarization‐dependent metasurface
  publication-title: Microw Opt Technol Lett
– volume: 2
  issue: 2
  year: 2018
  article-title: Machine‐learning designs of anisotropic digital coding metasurfaces
  publication-title: Adv Theory Simul
– volume: 33
  start-page: 2746
  issue: 6
  year: 2020
  article-title: Artificial neural network application for novel 3D printed nonuniform ceramic reflectarray antenna
  publication-title: Int J Numer Modell Electr Netw Dev Fields
– start-page: 103
  year: 2021
  end-page: 104
– ident: e_1_2_9_16_1
  doi: 10.1002/mop.33284
– ident: e_1_2_9_9_1
  doi: 10.1109/TAP.2021.3111280
– ident: e_1_2_9_31_1
– ident: e_1_2_9_13_1
  doi: 10.1109/TAP.2023.3262969
– ident: e_1_2_9_33_1
  doi: 10.1109/MM.2021.3086541
– ident: e_1_2_9_20_1
  doi: 10.1002/adts.201800132
– ident: e_1_2_9_15_1
  doi: 10.1109/TAP.2016.2590559
– ident: e_1_2_9_3_1
  doi: 10.1109/LAWP.2022.3227881
– ident: e_1_2_9_17_1
  doi: 10.1109/TEMC.2023.3325438
– ident: e_1_2_9_40_1
  doi: 10.1109/TAP.1963.1138112
– ident: e_1_2_9_23_1
  doi: 10.1021/acs.nanolett.8b03171
– ident: e_1_2_9_34_1
  doi: 10.1109/MM.2021.3061394
– ident: e_1_2_9_36_1
  doi: 10.1007/11494669_93
– ident: e_1_2_9_38_1
  doi: 10.1109/LAWP.2013.2270934
– ident: e_1_2_9_29_1
  doi: 10.1109/TAP.2021.3138517
– ident: e_1_2_9_22_1
  doi: 10.1002/jnm.2746
– ident: e_1_2_9_11_1
  doi: 10.1002/mop.32656
– ident: e_1_2_9_39_1
  doi: 10.1109/APS/URSI47566.2021.9704279
– ident: e_1_2_9_8_1
  doi: 10.2528/PIER22062201
– ident: e_1_2_9_14_1
  doi: 10.1109/TAP.2010.2103006
– ident: e_1_2_9_18_1
  doi: 10.1109/TAP.2003.817983
– volume-title: Antenna Theory: Analysis and Design
  year: 2005
  ident: e_1_2_9_30_1
– ident: e_1_2_9_27_1
  doi: 10.1109/TAP.2022.3155204
– ident: e_1_2_9_12_1
  doi: 10.1002/mop.32156
– ident: e_1_2_9_25_1
  doi: 10.1109/TKDE.2009.191
– ident: e_1_2_9_19_1
  doi: 10.1109/ACCESS.2023.3254204
– ident: e_1_2_9_35_1
  doi: 10.1214/aoms/1177729694
– ident: e_1_2_9_7_1
  doi: 10.1002/mop.32649
– ident: e_1_2_9_2_1
  doi: 10.1109/TAP.2017.2671036
– volume: 9
  start-page: 2579
  year: 2008
  ident: e_1_2_9_37_1
  article-title: Visualizing data using t‐SNE
  publication-title: J Mach Learn Res
– ident: e_1_2_9_10_1
  doi: 10.1109/TAP.2018.2860121
– volume: 19
  year: 2008
  ident: e_1_2_9_32_1
  article-title: CST‐computer simulation technology
  publication-title: Bad Nuheimer Str
– ident: e_1_2_9_24_1
  doi: 10.1038/s41467-021-23087-y
– ident: e_1_2_9_4_1
  doi: 10.1109/TAP.2018.2854366
– ident: e_1_2_9_26_1
  doi: 10.1109/TAP.2022.3226343
– ident: e_1_2_9_28_1
  doi: 10.1109/TAP.2021.3060142
– ident: e_1_2_9_5_1
  doi: 10.1002/mop.30769
– ident: e_1_2_9_21_1
  doi: 10.1109/APS/URSI47566.2021.9703937
– ident: e_1_2_9_6_1
  doi: 10.1109/TAP.2018.2806401
SSID ssj0003772
Score 2.447183
Snippet A small‐scale data‐selection method is proposed for deep‐learning‐based inverse design of reflective metasurface antennas (MAs). The overall design process...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
SubjectTerms Antennas
Boresights
Coding
deep convolutional variational autoencoder (DCVAE)
Deep learning
Discretization
Inverse design
Machine learning
metasurface antennas (MAs)
Metasurfaces
Pencil beams
Simulation
statistically‐random data filtering (SRDF)
Unit cell
Title Inverse design of reflective metasurface antennas using deep learning from small‐scale statistically random pico‐cells
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmop.34068
https://www.proquest.com/docview/2931465160
Volume 66
WOSCitedRecordID wos001159063500001&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1098-2760
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003772
  issn: 0895-2477
  databaseCode: DRFUL
  dateStart: 19960101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB5tXxIcoA8QCwVZqIdeojp-bGJxQsCKA7QVolJvkcd29rKbXW1KpXLiJ_Ab-SWMney2SFRC4hZFk8Ty2OPPzsz3ARxZ5N5xiVmBBN-UU2WG3udZVBxFLZRE0YlNFKen5eWlOR_Am1UtTMcPsT5wizMjxes4wS22J7ekobM5bdhpOSo3YCsWVdHOa-v9l_HFp3UglkXSbuKl0ZlQRbEiFuLiZP3wn8vRLca8i1TTUjN-_F-N3IVHPcJkb7shsQeD0OzDwzu8g_uwk_I-XXsA3yPPxrINzKdMDjavGbVx2kVBNgtX8QSxti6w6IGmsS2LmfITsg8L1ktOTFgsUmHtzE6nv378bMntgcVKpUQCTTdvGK2InkwWNO7IIv4taJ_AxfjD13cfs16OIXMi7jWNqJ0leIBKqlpL7a0cceMLrA2FvdpjLXQQQRvkqlCErGzJQ44yHzljvNbyKWw28yY8A-YCAZ1CYtS4VkJwiyGXqNGizq0zoyEcr7xSuZ6rPEpmTKuOZVlU1LFV6tghvF6bLjqCjr8ZHa5cW_VztK0I6ORRCX7E6XPJife_oPp8dp4unv-76Qt4IAgBdSneh7B5tfwWXsK2u6beX77qB-tvmbTw7Q
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Nb9QwEB2VbRH0AKWAKBSwEAcuUR1_xLHEpQJWrbpdKtRKvUX-Si-72dWmIMGJn8Bv7C_p2MluiwQSErcomiSWx555dsbvAbw1lnpHuc2URfgmnCgz632eRcVRK5nglnViE2o8Ls_P9ckavF-ehen4IVYbbnFmpHgdJ3jckN67YQ2dznDFjvmovAProuCqHMD6xy_Ds9EqEnOVxJtoqWXGhFJLZiHK9lYP_56PbkDmbaiacs3w4f-1cgse9BiT7HeD4hGshWYbNm8xD27D3VT56drH8CMybSzaQHyq5SCzmmAjJ10cJNNwGfcQa-MCiT5oGtOSWCt_gfZhTnrRiQsSj6mQdmomk6ufv1p0fCDxrFKigcab3wnmRI8mcxx5aBH_F7RP4Gz46fTDQdYLMmSOxdWmZrUzCBCs4KKWXHrDC6q9srXGwFd7WzMZWJDaUqEEYitT0pBbnhdOay8lfwqDZtaEZ0BcQKijuI0q14IxamzIuZXWWJkbp4sdeLd0S-V6tvIomjGpOp5lVmHHVqljd-DNynTeUXT8yWh36duqn6VthVAnj1rwBcXPJS_-_QXV8eeTdPH8301fw72D0-NRNTocH72A-wzxUFfwvQuDy8XX8BI23Df0xOJVP3KvAfwe9N0
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT9wwEB3RpUVwgJYWAaWtVfXQS4Tjj00scUGFFVVhu6qKxC3yV7jsZlcbQIITP4Hf2F_SsZNdQKISUm9RNEksjz3z7IzfA_iiDXWWcpNkBuGbsCJPjHNpEhRHjWSCG9aITWT9fn52pgYLsDc7C9PwQ8w33MLMiPE6THA_ceXuPWvoaIwrdsxH-QtYFFJJ0YHFg1-90-N5JOZZFG-iuZIJE1k2YxaibHf-8ON8dA8yH0LVmGt6a__Xytew2mJMst8Mijew4Kt1WHnAPLgOr2Llp63fwk1g2pjWnrhYy0HGJcFGDps4SEb-Iuwhltp6EnxQVbomoVb-HO39hLSiE-ckHFMh9UgPh39u72p0vCfhrFKkgcab1wRzokOTCY48tAj_C-p3cNo7_P3tKGkFGRLLwmpTsdJqBAhGcFFKLp3mXapcZkqFga90pmTSMy-VoSITiK10Tn1qeNq1Sjkp-QZ0qnHlN4FYj1An4yaoXAvGqDY-5UYabWSqrepuwdeZWwrbspUH0Yxh0fAsswI7togduwWf56aThqLjKaOdmW-LdpbWBUKdNGjBdyl-Lnrx3y8oTn4O4sX2800_wdLgoFccf-__eA_LDOFQU--9A52L6aX_AC_tFTpi-rEduH8BmT_0WA
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=Inverse+design+of+reflective+metasurface+antennas+using+deep+learning+from+small%E2%80%90scale+statistically+random+pico%E2%80%90cells&rft.jtitle=Microwave+and+optical+technology+letters&rft.au=Xi+Chong+You&rft.au=Feng+Han+Lin&rft.date=2024-02-01&rft.pub=Wiley+Subscription+Services%2C+Inc&rft.issn=0895-2477&rft.eissn=1098-2760&rft.volume=66&rft.issue=2&rft_id=info:doi/10.1002%2Fmop.34068&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0895-2477&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0895-2477&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0895-2477&client=summon