Classification of crystal structure using a convolutional neural network

A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IUCrJ Ročník 4; číslo 4; s. 486 - 494
Hlavní autoři: Park, Woon Bae, Chung, Jiyong, Jung, Jaeyoung, Sohn, Keemin, Singh, Satendra Pal, Pyo, Myoungho, Shin, Namsoo, Sohn, Kee-Sun
Médium: Journal Article
Jazyk:angličtina
Vydáno: England International Union of Crystallography 01.07.2017
Témata:
ISSN:2052-2525, 2052-2525
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN architecture was obtained that allowed determination of the crystal system, extinction group and space group. In sharp contrast with the traditional use of powder XRD pattern analysis, the CNN never treats powder XRD patterns as a deconvoluted and discrete peak position or as intensity data, but instead the XRD patterns are regarded as nothing but a pattern similar to a picture. The CNN interprets features that humans cannot recognize in a powder XRD pattern. As a result, accuracy levels of 81.14, 83.83 and 94.99% were achieved for the space-group, extinction-group and crystal-system classifications, respectively. The well trained CNN was then used for symmetry identification of unknown novel inorganic compounds.
AbstractList A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN architecture was obtained that allowed determination of the crystal system, extinction group and space group. In sharp contrast with the traditional use of powder XRD pattern analysis, the CNN never treats powder XRD patterns as a deconvoluted and discrete peak position or as intensity data, but instead the XRD patterns are regarded as nothing but a pattern similar to a picture. The CNN interprets features that humans cannot recognize in a powder XRD pattern. As a result, accuracy levels of 81.14, 83.83 and 94.99% were achieved for the space-group, extinction-group and crystal-system classifications, respectively. The well trained CNN was then used for symmetry identification of unknown novel inorganic compounds.
A deep-machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been employed for the classification of crystal system, extinction group and space group for given powder X-ray diffraction patterns of inorganic materials. A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN architecture was obtained that allowed determination of the crystal system, extinction group and space group. In sharp contrast with the traditional use of powder XRD pattern analysis, the CNN never treats powder XRD patterns as a deconvoluted and discrete peak position or as intensity data, but instead the XRD patterns are regarded as nothing but a pattern similar to a picture. The CNN interprets features that humans cannot recognize in a powder XRD pattern. As a result, accuracy levels of 81.14, 83.83 and 94.99% were achieved for the space-group, extinction-group and crystal-system classifications, respectively. The well trained CNN was then used for symmetry identification of unknown novel inorganic compounds.
A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN architecture was obtained that allowed determination of the crystal system, extinction group and space group. In sharp contrast with the traditional use of powder XRD pattern analysis, the CNN never treats powder XRD patterns as a deconvoluted and discrete peak position or as intensity data, but instead the XRD patterns are regarded as nothing but a pattern similar to a picture. The CNN interprets features that humans cannot recognize in a powder XRD pattern. As a result, accuracy levels of 81.14, 83.83 and 94.99% were achieved for the space-group, extinction-group and crystal-system classifications, respectively. The well trained CNN was then used for symmetry identification of unknown novel inorganic compounds.A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN architecture was obtained that allowed determination of the crystal system, extinction group and space group. In sharp contrast with the traditional use of powder XRD pattern analysis, the CNN never treats powder XRD patterns as a deconvoluted and discrete peak position or as intensity data, but instead the XRD patterns are regarded as nothing but a pattern similar to a picture. The CNN interprets features that humans cannot recognize in a powder XRD pattern. As a result, accuracy levels of 81.14, 83.83 and 94.99% were achieved for the space-group, extinction-group and crystal-system classifications, respectively. The well trained CNN was then used for symmetry identification of unknown novel inorganic compounds.
Audience Academic
Author Shin, Namsoo
Singh, Satendra Pal
Pyo, Myoungho
Sohn, Kee-Sun
Sohn, Keemin
Jung, Jaeyoung
Park, Woon Bae
Chung, Jiyong
Author_xml – sequence: 1
  givenname: Woon Bae
  surname: Park
  fullname: Park, Woon Bae
– sequence: 2
  givenname: Jiyong
  surname: Chung
  fullname: Chung, Jiyong
– sequence: 3
  givenname: Jaeyoung
  orcidid: 0000-0002-3840-9982
  surname: Jung
  fullname: Jung, Jaeyoung
– sequence: 4
  givenname: Keemin
  surname: Sohn
  fullname: Sohn, Keemin
– sequence: 5
  givenname: Satendra Pal
  orcidid: 0000-0001-8526-3923
  surname: Singh
  fullname: Singh, Satendra Pal
– sequence: 6
  givenname: Myoungho
  surname: Pyo
  fullname: Pyo, Myoungho
– sequence: 7
  givenname: Namsoo
  orcidid: 0000-0003-1943-2236
  surname: Shin
  fullname: Shin, Namsoo
– sequence: 8
  givenname: Kee-Sun
  orcidid: 0000-0002-7496-2283
  surname: Sohn
  fullname: Sohn, Kee-Sun
BackLink https://www.ncbi.nlm.nih.gov/pubmed/28875035$$D View this record in MEDLINE/PubMed
BookMark eNp1kl1rFTEQhoNUbK39Ad7IXnpz6iSbj82NUA7VFgpeqOBdyObjmLonqUm20n9v9pxWWkWGMGHmnYdJZl6ig5iiQ-g1hlOMQbz7TIARwgjDAkBg-u0ZOlpCqyV28Oh-iE5KuQYAjAkTFL9Ah2QYBIOeHaGL9aRLCT4YXUOKXfKdyXel6qkrNc-mztl1cwlx0-nOpHibpnkRtnx0c965-ivlH6_Qc6-n4k7u_TH6-uH8y_pidfXp4-X67GplmIC6IpRaxo0A3Q-CWJC-Bw7E2HGQZrTcDkaORI6WMiZ64YFKITkIAw5zwL4_Rpd7rk36Wt3ksNX5TiUd1C6Q8kbpXIOZnHK454INeBico2OvpQXtqOPtWAJ6bKz3e9bNPG6dNS7W9qIn0KeZGL6rTbpVrTc8YNwAb-8BOf2cXalqG4px06SjS3NRWPaccEaoaNLTvXSjW2sh-tSIppl129A-1vnQ4mdUSroYbwVvHjf3p6uH2TWB2AtMTqVk55UJdTfFRg6TwqCWRVH_LEqrxH9VPsD_X_Mb_f6-8Q
CitedBy_id crossref_primary_10_1039_D1MH00495F
crossref_primary_10_1038_s41467_019_13214_1
crossref_primary_10_1038_s43246_023_00432_w
crossref_primary_10_71267_mencom_7653
crossref_primary_10_1016_j_commatsci_2019_109409
crossref_primary_10_1016_j_scriptamat_2025_116697
crossref_primary_10_1107_S1600576725004169
crossref_primary_10_3390_cryst15050393
crossref_primary_10_1016_j_mtcomm_2020_101662
crossref_primary_10_1107_S2052252524006766
crossref_primary_10_1021_jacs_3c11852
crossref_primary_10_1002_adts_202200613
crossref_primary_10_1088_2053_1591_abd590
crossref_primary_10_3390_ma15041502
crossref_primary_10_1116_6_0001482
crossref_primary_10_1038_s41467_018_05169_6
crossref_primary_10_1002_aisy_202300140
crossref_primary_10_1038_s41524_025_01743_x
crossref_primary_10_1107_S1600576725002419
crossref_primary_10_1038_s41524_022_00734_6
crossref_primary_10_1002_adts_202000039
crossref_primary_10_1007_s00371_021_02165_8
crossref_primary_10_1038_s41467_019_13749_3
crossref_primary_10_1002_adma_202203879
crossref_primary_10_1016_j_jmrt_2022_12_143
crossref_primary_10_1038_s41524_024_01230_9
crossref_primary_10_1039_D0QI01513J
crossref_primary_10_1080_08940886_2022_2112496
crossref_primary_10_3390_rs17091542
crossref_primary_10_1107_S1600576724003704
crossref_primary_10_1016_j_mtcomm_2022_103174
crossref_primary_10_1002_adfm_202108044
crossref_primary_10_1107_S160057672400147X
crossref_primary_10_1038_s41524_021_00536_2
crossref_primary_10_1002_adts_202100337
crossref_primary_10_1021_acs_jcim_5c01506
crossref_primary_10_1088_2632_2153_acab4c
crossref_primary_10_1002_aisy_202200042
crossref_primary_10_1103_PhysRevApplied_16_014005
crossref_primary_10_1038_s41524_020_00466_5
crossref_primary_10_1016_j_jssc_2020_121253
crossref_primary_10_1002_adts_202301219
crossref_primary_10_1016_j_jrras_2024_100870
crossref_primary_10_1002_mp_15366
crossref_primary_10_1038_s41524_023_01055_y
crossref_primary_10_1103_j4f1_shc8
crossref_primary_10_3390_cryst11091039
crossref_primary_10_1021_jacs_4c10244
crossref_primary_10_1038_s41563_025_02220_y
crossref_primary_10_1039_D3SC05081E
crossref_primary_10_1038_s41524_021_00542_4
crossref_primary_10_1038_s41524_020_0317_6
crossref_primary_10_1107_S1600576725002316
crossref_primary_10_1107_S1600576719013311
crossref_primary_10_1080_00223131_2023_2269974
crossref_primary_10_1016_j_joule_2019_05_014
crossref_primary_10_3390_sym16030319
crossref_primary_10_1016_j_ceramint_2022_10_019
crossref_primary_10_1107_S2053273319012804
crossref_primary_10_1038_s41524_023_01096_3
crossref_primary_10_1073_pnas_2309240120
crossref_primary_10_1146_annurev_matsci_070218_010015
crossref_primary_10_1002_wcms_1558
crossref_primary_10_1002_smtd_202400181
crossref_primary_10_1007_s10439_021_02850_8
crossref_primary_10_1107_S1600577521001314
crossref_primary_10_1038_s41524_023_01164_8
crossref_primary_10_1557_s43580_024_00862_9
crossref_primary_10_1107_S2053273319005606
crossref_primary_10_1038_s41524_024_01498_x
crossref_primary_10_1126_sciadv_adu7426
crossref_primary_10_1002_advs_202410722
crossref_primary_10_1107_S2053273324000172
crossref_primary_10_1002_adma_202208683
crossref_primary_10_1007_s10853_023_08343_4
crossref_primary_10_1107_S2052252521002402
crossref_primary_10_1016_j_matt_2020_06_011
crossref_primary_10_1002_aisy_202300501
crossref_primary_10_1107_S1600576721010840
crossref_primary_10_1007_s11837_021_04805_9
crossref_primary_10_1016_j_commatsci_2021_110686
crossref_primary_10_1038_s41598_025_06779_z
crossref_primary_10_1088_1361_6528_acd25a
crossref_primary_10_3390_ma16010334
crossref_primary_10_1107_S1600576722008056
crossref_primary_10_1021_jacs_8b03913
crossref_primary_10_1016_j_matt_2024_06_026
crossref_primary_10_1039_D1RA07156D
crossref_primary_10_1039_D3RA08939H
crossref_primary_10_1002_adfm_202422601
crossref_primary_10_3365_KJMM_2021_59_5_346
crossref_primary_10_1038_s41467_025_62708_8
crossref_primary_10_1038_s41524_024_01402_7
crossref_primary_10_1007_s10489_022_04351_0
crossref_primary_10_1107_S1600576723007446
crossref_primary_10_1107_S1600576721009043
crossref_primary_10_1016_j_matt_2025_102272
crossref_primary_10_1038_s43588_021_00059_2
crossref_primary_10_1088_1674_1056_abc0e3
crossref_primary_10_1038_s41524_019_0196_x
crossref_primary_10_1016_j_measurement_2021_109739
crossref_primary_10_1107_S1600576722009797
crossref_primary_10_1016_j_jeurceramsoc_2021_05_010
crossref_primary_10_1039_D0MH00881H
crossref_primary_10_1038_s41598_020_77474_4
crossref_primary_10_3390_cryst12091324
crossref_primary_10_1002_aenm_201903242
crossref_primary_10_1039_C8SC02648C
crossref_primary_10_1109_TVCG_2020_3030384
crossref_primary_10_1017_S1431927618013107
crossref_primary_10_1107_S205225252401217X
crossref_primary_10_1016_j_actamat_2020_07_065
crossref_primary_10_1107_S1600576724004497
crossref_primary_10_1016_j_cocom_2025_e01009
crossref_primary_10_1016_j_sbi_2022_102421
crossref_primary_10_1016_j_matt_2023_03_015
crossref_primary_10_1116_6_0002912
crossref_primary_10_1016_j_jpowsour_2025_237944
crossref_primary_10_1002_advs_202304546
crossref_primary_10_1038_s41524_019_0221_0
crossref_primary_10_1007_s11467_023_1325_z
crossref_primary_10_1016_j_commatsci_2019_109436
crossref_primary_10_1016_j_scriptamat_2022_115238
crossref_primary_10_1038_s41597_025_05534_3
crossref_primary_10_1088_2632_2153_abf9b1
crossref_primary_10_1016_j_jhazmat_2024_135285
crossref_primary_10_1038_s41524_024_01401_8
crossref_primary_10_3390_app15115851
crossref_primary_10_1126_science_adn2777
crossref_primary_10_1002_smll_201802291
crossref_primary_10_1016_j_cocom_2021_e00605
crossref_primary_10_1038_s42256_021_00384_1
crossref_primary_10_1039_D4NR04531A
crossref_primary_10_1107_S1600576723000596
crossref_primary_10_1002_eng2_12274
crossref_primary_10_1088_2632_2153_aca23d
crossref_primary_10_3390_buildings14020340
crossref_primary_10_1017_S1431927618015131
crossref_primary_10_1002_aidi_202500044
crossref_primary_10_1038_s41524_021_00575_9
crossref_primary_10_1016_j_petrol_2021_109840
crossref_primary_10_1371_journal_pone_0188256
Cites_doi 10.1107/S0021889804000391
10.1154/1.1763152
10.1021/ja409865c
10.1107/S0021889869006558
10.1107/S002188980400038X
10.1038/srep11476
10.1038/nature16961
10.1039/c2jm32032k
10.1155/2011/894143
10.1007/s00521-010-0386-4
10.2477/jchemsoft.4.33
10.1109/TCBB.2014.2343960
10.1107/S0108767307038081
10.1107/S0021889869006649
10.1107/S0021889891006441
10.1002/adfm.201102118
10.1039/c2tc00731b
10.1107/S0021889809042915
10.1107/S0021889885010512
10.1107/S0021889802023348
10.1021/ac050616c
10.1021/ac061991n
10.1109/5.726791
10.1366/000370207783292127
10.1016/S0731-7085(00)00256-9
10.1016/0369-643X(58)90029-X
10.1021/acs.molpharmaceut.5b00982
10.1021/cm501866x
10.1107/S0365110X67000234
ContentType Journal Article
Copyright COPYRIGHT 2017 International Union of Crystallography
Woon Bae Park et al. 2017 2017
Copyright_xml – notice: COPYRIGHT 2017 International Union of Crystallography
– notice: Woon Bae Park et al. 2017 2017
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.1107/S205225251700714X
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList
CrossRef

MEDLINE - Academic
PubMed
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
DocumentTitleAlternate A convolutional neural network
EISSN 2052-2525
EndPage 494
ExternalDocumentID oai_doaj_org_article_e136758188ee4b3a9d0ae4e6e4ed20ab
PMC5571811
A499494946
28875035
10_1107_S205225251700714X
Genre Journal Article
GrantInformation_xml – fundername: National Research Foundation of Korea (NRF)
  grantid: 2015M3D1A1069705
GroupedDBID 5VS
8FE
8FG
AAFWJ
AAYXX
ABJCF
ABUWG
ADBBV
ADRAZ
AENEX
AFFHD
AFKRA
AFPKN
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BCNDV
BENPR
BGLVJ
BPHCQ
CCPQU
CITATION
D1I
EBS
EHMNL
EJD
GROUPED_DOAJ
H13
HCIFZ
HYE
IAO
IPNFZ
ITC
KB.
KQ8
M48
M~E
OK1
PDBOC
PGMZT
PHGZM
PHGZT
PIMPY
PQGLB
PQQKQ
PROAC
RCJ
RIG
ROL
RPM
ZBA
3V.
NPM
7X8
PUEGO
5PM
ID FETCH-LOGICAL-c570t-244d56c70a3872d09f30602cdb89cbd6d8c9b29bd455737f04979607c0e1601f3
IEDL.DBID DOA
ISICitedReferencesCount 181
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000405296500020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2052-2525
IngestDate Fri Oct 03 12:25:59 EDT 2025
Tue Nov 04 02:02:15 EST 2025
Fri Sep 05 08:18:05 EDT 2025
Tue Nov 04 17:28:28 EST 2025
Thu Jan 02 22:29:19 EST 2025
Sat Nov 29 03:53:01 EST 2025
Tue Nov 18 20:29:07 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords crystal system
artificial neural network (ANN)
inorganic materials
properties of solids
convolutional neural network (CNN)
crystal structure prediction
computational modelling
powder X-ray diffraction
Language English
License This is an open-access article distributed under the terms of the Creative Commons Attribution (CC-BY) Licence, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are cited.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c570t-244d56c70a3872d09f30602cdb89cbd6d8c9b29bd455737f04979607c0e1601f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
These authors contributed equally.
ORCID 0000-0002-3840-9982
0000-0001-8526-3923
0000-0003-1943-2236
0000-0002-7496-2283
OpenAccessLink https://doaj.org/article/e136758188ee4b3a9d0ae4e6e4ed20ab
PMID 28875035
PQID 1936265247
PQPubID 23479
PageCount 9
ParticipantIDs doaj_primary_oai_doaj_org_article_e136758188ee4b3a9d0ae4e6e4ed20ab
pubmedcentral_primary_oai_pubmedcentral_nih_gov_5571811
proquest_miscellaneous_1936265247
gale_infotracacademiconefile_A499494946
pubmed_primary_28875035
crossref_citationtrail_10_1107_S205225251700714X
crossref_primary_10_1107_S205225251700714X
PublicationCentury 2000
PublicationDate 2017-07-01
PublicationDateYYYYMMDD 2017-07-01
PublicationDate_xml – month: 07
  year: 2017
  text: 2017-07-01
  day: 01
PublicationDecade 2010
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle IUCrJ
PublicationTitleAlternate IUCrJ
PublicationYear 2017
Publisher International Union of Crystallography
Publisher_xml – name: International Union of Crystallography
References Agatonovic Kustrin (fc5018_bb1) 2000; 22
Park (fc5018_bb23) 2014; 136
Heffernan (fc5018_bb9) 2015; 5
Barr (fc5018_bb4) 2004; 37
Lecun (fc5018_bb14) 1998; 86
Chen (fc5018_bb7) 2005; 77
Mamoshina (fc5018_bb16) 2016; 13
Silver (fc5018_bb28) 2016; 529
Park (fc5018_bb25) 2013; 1
fc5018_bb34
fc5018_bb12
Obeidat (fc5018_bb21) 2011; 26
fc5018_bb19
Neumann (fc5018_bb20) 2003; 36
Spencer (fc5018_bb29) 2015; 12
Gilmore (fc5018_bb8) 2004; 37
Hirosaki (fc5018_bb10) 2014; 26
Visser (fc5018_bb32) 1969; 2
Park (fc5018_bb22) 2012; 22
Caglioti (fc5018_bb6) 1958; 3
Le Bail (fc5018_bb13) 2004; 19
Mitsui (fc5018_bb18) 1997; 4
Boultif (fc5018_bb5) 1991; 24
Werner (fc5018_bb33) 1985; 18
Rietveld (fc5018_bb26) 1967; 22
Altomare (fc5018_bb3) 2009; 42
Rietveld (fc5018_bb27) 1969; 2
Tatlier (fc5018_bb30) 2011; 20
Allmann (fc5018_bb2) 2007; 63
Lee (fc5018_bb15) 2007; 61
Park (fc5018_bb24) 2012; 22
Matos (fc5018_bb17) 2007; 79
16223241 - Anal Chem. 2005 Oct 15;77(20):6563-70
27007977 - Mol Pharm. 2016 May 2;13(5):1445-54
18198034 - Appl Spectrosc. 2007 Dec;61(12):1398-403
25750595 - IEEE/ACM Trans Comput Biol Bioinform. 2015 Jan-Feb;12(1):103-12
10857567 - J Pharm Biomed Anal. 2000 Jul;22(6):985-92
17703075 - Acta Crystallogr A. 2007 Sep;63(Pt 5):412-7
26819042 - Nature. 2016 Jan 28;529(7587):484-9
24437942 - J Am Chem Soc. 2014 Feb 12;136(6):2363-73
References_xml – volume: 37
  start-page: 243
  year: 2004
  ident: fc5018_bb4
  publication-title: J. Appl. Cryst.
  doi: 10.1107/S0021889804000391
– volume: 19
  start-page: 249
  year: 2004
  ident: fc5018_bb13
  publication-title: Powder Diffr.
  doi: 10.1154/1.1763152
– volume: 136
  start-page: 2363
  year: 2014
  ident: fc5018_bb23
  publication-title: J. Am. Chem. Soc.
  doi: 10.1021/ja409865c
– volume: 2
  start-page: 65
  year: 1969
  ident: fc5018_bb27
  publication-title: J. Appl. Cryst.
  doi: 10.1107/S0021889869006558
– volume: 37
  start-page: 231
  year: 2004
  ident: fc5018_bb8
  publication-title: J. Appl. Cryst.
  doi: 10.1107/S002188980400038X
– volume: 5
  start-page: 11746
  year: 2015
  ident: fc5018_bb9
  publication-title: Sci. Rep.
  doi: 10.1038/srep11476
– ident: fc5018_bb19
– volume: 529
  start-page: 484
  year: 2016
  ident: fc5018_bb28
  publication-title: Nature
  doi: 10.1038/nature16961
– volume: 22
  start-page: 14068
  year: 2012
  ident: fc5018_bb24
  publication-title: J. Mater. Chem.
  doi: 10.1039/c2jm32032k
– volume: 26
  start-page: 141
  year: 2011
  ident: fc5018_bb21
  publication-title: Spectroscopy
  doi: 10.1155/2011/894143
– volume: 20
  start-page: 365
  year: 2011
  ident: fc5018_bb30
  publication-title: Neural Comput. Appl.
  doi: 10.1007/s00521-010-0386-4
– volume: 4
  start-page: 33
  year: 1997
  ident: fc5018_bb18
  publication-title: J. Chem. Softw.
  doi: 10.2477/jchemsoft.4.33
– volume: 12
  start-page: 103
  year: 2015
  ident: fc5018_bb29
  publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform.
  doi: 10.1109/TCBB.2014.2343960
– volume: 63
  start-page: 412
  year: 2007
  ident: fc5018_bb2
  publication-title: Acta Cryst. A
  doi: 10.1107/S0108767307038081
– volume: 2
  start-page: 89
  year: 1969
  ident: fc5018_bb32
  publication-title: J. Appl. Cryst.
  doi: 10.1107/S0021889869006649
– volume: 24
  start-page: 987
  year: 1991
  ident: fc5018_bb5
  publication-title: J. Appl. Cryst.
  doi: 10.1107/S0021889891006441
– ident: fc5018_bb34
– volume: 22
  start-page: 2258
  year: 2012
  ident: fc5018_bb22
  publication-title: Adv. Funct. Mater.
  doi: 10.1002/adfm.201102118
– volume: 1
  start-page: 1832
  year: 2013
  ident: fc5018_bb25
  publication-title: J. Mater. Chem. C
  doi: 10.1039/c2tc00731b
– volume: 42
  start-page: 1197
  year: 2009
  ident: fc5018_bb3
  publication-title: J. Appl. Cryst.
  doi: 10.1107/S0021889809042915
– volume: 18
  start-page: 367
  year: 1985
  ident: fc5018_bb33
  publication-title: J. Appl. Cryst.
  doi: 10.1107/S0021889885010512
– volume: 36
  start-page: 356
  year: 2003
  ident: fc5018_bb20
  publication-title: J. Appl. Cryst.
  doi: 10.1107/S0021889802023348
– volume: 77
  start-page: 6563
  year: 2005
  ident: fc5018_bb7
  publication-title: Anal. Chem.
  doi: 10.1021/ac050616c
– volume: 79
  start-page: 2091
  year: 2007
  ident: fc5018_bb17
  publication-title: Anal. Chem.
  doi: 10.1021/ac061991n
– volume: 86
  start-page: 2278
  year: 1998
  ident: fc5018_bb14
  publication-title: Proc. IEEE
  doi: 10.1109/5.726791
– volume: 61
  start-page: 1398
  year: 2007
  ident: fc5018_bb15
  publication-title: Appl. Spectrosc.
  doi: 10.1366/000370207783292127
– volume: 22
  start-page: 985
  year: 2000
  ident: fc5018_bb1
  publication-title: J. Pharm. Biomed. Anal.
  doi: 10.1016/S0731-7085(00)00256-9
– volume: 3
  start-page: 223
  year: 1958
  ident: fc5018_bb6
  publication-title: Nucl. Instrum.
  doi: 10.1016/0369-643X(58)90029-X
– volume: 13
  start-page: 1445
  year: 2016
  ident: fc5018_bb16
  publication-title: Mol. Pharm.
  doi: 10.1021/acs.molpharmaceut.5b00982
– volume: 26
  start-page: 4280
  year: 2014
  ident: fc5018_bb10
  publication-title: Chem. Mater.
  doi: 10.1021/cm501866x
– ident: fc5018_bb12
– volume: 22
  start-page: 151
  year: 1967
  ident: fc5018_bb26
  publication-title: Acta Cryst.
  doi: 10.1107/S0365110X67000234
– reference: 26819042 - Nature. 2016 Jan 28;529(7587):484-9
– reference: 25750595 - IEEE/ACM Trans Comput Biol Bioinform. 2015 Jan-Feb;12(1):103-12
– reference: 27007977 - Mol Pharm. 2016 May 2;13(5):1445-54
– reference: 10857567 - J Pharm Biomed Anal. 2000 Jul;22(6):985-92
– reference: 18198034 - Appl Spectrosc. 2007 Dec;61(12):1398-403
– reference: 17703075 - Acta Crystallogr A. 2007 Sep;63(Pt 5):412-7
– reference: 24437942 - J Am Chem Soc. 2014 Feb 12;136(6):2363-73
– reference: 16223241 - Anal Chem. 2005 Oct 15;77(20):6563-70
SSID ssj0001125741
Score 2.522689
Snippet A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray...
A deep-machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been employed for the classification of crystal system,...
SourceID doaj
pubmedcentral
proquest
gale
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 486
SubjectTerms artificial neural network (ANN)
Artificial neural networks
computational modelling
convolutional neural network (CNN)
Crystal structure
crystal structure prediction
crystal system
inorganic materials
Observations
powder X-ray diffraction
properties of solids
Research Papers
Title Classification of crystal structure using a convolutional neural network
URI https://www.ncbi.nlm.nih.gov/pubmed/28875035
https://www.proquest.com/docview/1936265247
https://pubmed.ncbi.nlm.nih.gov/PMC5571811
https://doaj.org/article/e136758188ee4b3a9d0ae4e6e4ed20ab
Volume 4
WOSCitedRecordID wos000405296500020&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2052-2525
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001125741
  issn: 2052-2525
  databaseCode: DOA
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2052-2525
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001125741
  issn: 2052-2525
  databaseCode: M~E
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Materials Science Database
  customDbUrl:
  eissn: 2052-2525
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001125741
  issn: 2052-2525
  databaseCode: KB.
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/materialsscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2052-2525
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001125741
  issn: 2052-2525
  databaseCode: BENPR
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2052-2525
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001125741
  issn: 2052-2525
  databaseCode: PIMPY
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: UK & Ireland Database (ProQuest)
  customDbUrl:
  eissn: 2052-2525
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001125741
  issn: 2052-2525
  databaseCode: EHMNL
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/ukireland
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3da9RAEB-0-qAPUr9T6xFBEITYzX5ks489aamIx-EHnE9hv6KFkpNrK_jfd2aTHgkFffEhCcxuYHdmdmcmO_kNwGv0wCUToi04b-tCOlMXTpiyqGKpWxaCqCqbik3oxaJercxyVOqLcsJ6eOCecQeRMMUUmpU6RumENYHZKGOFV-DMOtp90esZBVPp6wrabZ3KVnKmeMEVV8ORJoY7B1-ISDQCp9OlXE2MUsLuv7lDj0zUNH1yZI-Od-HB4Ejmh_0EHsKt2D2C-yN4wcdwkipeUi5QYn--bnO_-YPu4Fnew8ZebmJOie8_cptT-vmghthOMJfpkZLEn8C346Ov70-KoXJC4ZVmFwXa7KAqr5kVteaBmRYjA8Z9cLXxLlSh9sZx44JUSgsUijQaQxntWSwxQmvFU9jp1l18DrmNvLKOTktNJVF-hiAEgxFBlLF0SmTArlnX-AFWnKpbnDUpvGC6ucHtDN5uX_nVY2r8rfOc5LHtSHDYiYBK0gxK0vxLSTJ4Q9JsaNHi4Lwd_j3AKRL8VXOIcR_B9Mgqg1fXAm9wodHpie3i-vK8QU8Xgz_Fpc7gWa8A20Fx3KoVEyoDPVGNyainLd3pzwTmjQJAJ6vc-x_TfAH3OHkdKZt4H3ZQleJLuOt_X5yeb2ZwW6_qGdyZHy2Wn2dpveD94_wd0pYfPi2_XwEfmRZV
linkProvider Directory of Open Access Journals
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=Classification+of+crystal+structure+using+a+convolutional+neural+network&rft.jtitle=IUCrJ&rft.au=Park%2C+Woon+Bae&rft.au=Chung%2C+Jiyong&rft.au=Jung%2C+Jaeyoung&rft.au=Sohn%2C+Keemin&rft.date=2017-07-01&rft.issn=2052-2525&rft.eissn=2052-2525&rft.volume=4&rft.issue=Pt+4&rft.spage=486&rft_id=info:doi/10.1107%2FS205225251700714X&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2052-2525&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2052-2525&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2052-2525&client=summon