Simulation of the of the DeepLabv3 neural network learning process for the agricultural fields segmentation

Objective . Monitoring and determining the state of crops in agricultural production requires the use and improvement of neural network methods of artificial intelligence. The aim of the study is to create a mathematical model of the learning process of the DeepLabV3 neural network for intelligent a...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Vestnik Dagestanskogo gosudarstvennogo tehničeskogo universiteta. Tehničeskie nauki (Online) Ročník 50; číslo 3; s. 142 - 149
Hlavní autoři: Rogachev, A. F., Belousov, I. S.
Médium: Journal Article
Jazyk:angličtina
ruština
Vydáno: Dagestan State Technical University 29.10.2023
Témata:
artificial neural networks
crops
mathematical modeling
segmentation problem
ISSN:2073-6185, 2542-095X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Objective . Monitoring and determining the state of crops in agricultural production requires the use and improvement of neural network methods of artificial intelligence. The aim of the study is to create a mathematical model of the learning process of the DeepLabV3 neural network for intelligent analysis and segmentation of agricultural fields. Method . Based on the newly formed RGB database of images of agricultural fields, marked up into four classes, a neural network of the DeepLabV3 architecture was developed and trained. Approximations of the learning curve by the modified Johnson function are obtained by the methods of least squares and least modules. Result . A statistical assessment of the quality of training and approximation of neural networks to the DeepLabV3 architecture in combination with ResNet 50 was carried out. The constructed DNN family based on DeepLabV3 with ResNet50 showed the efficiency of recognition and sufficient speed in determining the state of crops. Conclusions . Approximation of the neural network learning diagram to the DeepLabV3 architecture, using a modified Johnson function, allows us to estimate the value of the “saturation” of the simulated dependence and predict the maximum value of the neural network metric without taking into account its possible retraining.
AbstractList Objective. Monitoring and determining the state of crops in agricultural production requires the use and improvement of neural network methods of artificial intelligence.The aim of the study is to create a mathematical model of the learning process of the DeepLabV3 neural network for intelligent analysis and segmentation of agricultural fields.Method. Based on the newly formed RGB database of images of agricultural fields, marked up into four classes, a neural network of the DeepLabV3 architecture was developed and trained. Approximations of the learning curve by the modified Johnson function are obtained by the methods of least squares and least modules.Result. A statistical assessment of the quality of training and approximation of neural networks to the DeepLabV3 architecture in combination with ResNet 50 was carried out. The constructed DNN family based on DeepLabV3 with ResNet50 showed the efficiency of recognition and sufficient speed in determining the state of crops.Conclusions. Approximation of the neural network learning diagram to the DeepLabV3 architecture, using a modified Johnson function, allows us to estimate the value of the “saturation” of the simulated dependence and predict the maximum value of the neural network metric without taking into account its possible retraining.
Objective . Monitoring and determining the state of crops in agricultural production requires the use and improvement of neural network methods of artificial intelligence. The aim of the study is to create a mathematical model of the learning process of the DeepLabV3 neural network for intelligent analysis and segmentation of agricultural fields. Method . Based on the newly formed RGB database of images of agricultural fields, marked up into four classes, a neural network of the DeepLabV3 architecture was developed and trained. Approximations of the learning curve by the modified Johnson function are obtained by the methods of least squares and least modules. Result . A statistical assessment of the quality of training and approximation of neural networks to the DeepLabV3 architecture in combination with ResNet 50 was carried out. The constructed DNN family based on DeepLabV3 with ResNet50 showed the efficiency of recognition and sufficient speed in determining the state of crops. Conclusions . Approximation of the neural network learning diagram to the DeepLabV3 architecture, using a modified Johnson function, allows us to estimate the value of the “saturation” of the simulated dependence and predict the maximum value of the neural network metric without taking into account its possible retraining.
Author Belousov, I. S.
Rogachev, A. F.
Author_xml – sequence: 1
  givenname: A. F.
  orcidid: 0000-0002-3077-6622
  surname: Rogachev
  fullname: Rogachev, A. F.
  organization: Volgograd State Agricultural University
– sequence: 2
  givenname: I. S.
  surname: Belousov
  fullname: Belousov, I. S.
  organization: Volgograd State Technical University
BookMark eNo9kUFLJDEQhYOMoDv6H_qw13ark07Sgb2IurvCgAcVvIUkXRmjPZ0h6dnFf2-mx9lD8R5F1VdQ7xtZjHFEQr43cEWbjtIfFCSrRdPxmgJlNYea1U1LS6kTck55saD4y6L44-QZucw5WCj7EoSEc_L-GDa7wUwhjlX01fSKR7lF3K6M_cuqEXfJDEWmfzG9VwOaNIZxXW1TdJhz5WOaN8w6BbcbpnnaBxz6XGVcb3Cc5gMX5NSbIePlly7J86-7p5s_9erh9_3N9ap2jWSqltK6DlplW4sAiinpLFIvPS0enDCmV5Z6znknhQeBvrfedKZz0LaCC7Yk9wduH82b3qawMelDRxP03IhprU2aghtQyx6kEIAUuGglFAwY1XhueyW4BVZYPw8sl2LOCf1_XgN6zkHvv6v339X7HDQHzXTJoZRinxw2frI
Cites_doi 10.3390/agronomy10020207
10.1016/j.scitotenv.2021.149726
10.1016/j.rse.2021.112599
10.21822/2073-6185-2023-50-2-67-75
10.1016/j.rse.2020.112000
10.1109/CVPR.2016.90
10.1007/978-3-031-11058-0_72
10.1016/j.rse.2016.10.010
10.1007/978-3-319-33816-3_14
10.14529/cmse170303
10.1109/IGARSS.2016.7729467
10.3390/rs13224668
10.1109/LGRS.2017.2681128
10.1109/IGARSS.2004.1369747
10.15217/issn2079-0996.2018.4.70
10.1590/1678-992x-2022-0041
10.1371/journal.pone.0245230
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.21822/2073-6185-2023-50-3-142-149
DatabaseName CrossRef
DOAJ: Directory of Open Access Journal (DOAJ)
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2542-095X
EndPage 149
ExternalDocumentID oai_doaj_org_article_7d07660e2056470fa80a91f5bd965b03
10_21822_2073_6185_2023_50_3_142_149
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
ID FETCH-LOGICAL-c1739-77bc8049b4be009397cbe2f7f29390c6aad9b2f555876f06efdbfa8a8c0446563
IEDL.DBID DOA
ISSN 2073-6185
IngestDate Fri Oct 03 12:34:28 EDT 2025
Sat Nov 29 03:22:15 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
Russian
License https://vestnik.dgtu.ru/jour/about/editorialPolicies#openAccessPolicy
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c1739-77bc8049b4be009397cbe2f7f29390c6aad9b2f555876f06efdbfa8a8c0446563
ORCID 0000-0002-3077-6622
OpenAccessLink https://doaj.org/article/7d07660e2056470fa80a91f5bd965b03
PageCount 8
ParticipantIDs doaj_primary_oai_doaj_org_article_7d07660e2056470fa80a91f5bd965b03
crossref_primary_10_21822_2073_6185_2023_50_3_142_149
PublicationCentury 2000
PublicationDate 2023-10-29
PublicationDateYYYYMMDD 2023-10-29
PublicationDate_xml – month: 10
  year: 2023
  text: 2023-10-29
  day: 29
PublicationDecade 2020
PublicationTitle Vestnik Dagestanskogo gosudarstvennogo tehničeskogo universiteta. Tehničeskie nauki (Online)
PublicationYear 2023
Publisher Dagestan State Technical University
Publisher_xml – name: Dagestan State Technical University
References ref13
ref12
ref15
ref14
ref11
ref10
ref2
ref1
ref17
ref16
ref19
ref18
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref5
References_xml – ident: ref1
  doi: 10.3390/agronomy10020207
– ident: ref3
– ident: ref20
– ident: ref11
  doi: 10.1016/j.scitotenv.2021.149726
– ident: ref12
  doi: 10.1016/j.rse.2021.112599
– ident: ref22
– ident: ref24
  doi: 10.21822/2073-6185-2023-50-2-67-75
– ident: ref25
– ident: ref7
  doi: 10.1016/j.rse.2020.112000
– ident: ref27
– ident: ref23
  doi: 10.1109/CVPR.2016.90
– ident: ref29
  doi: 10.1007/978-3-031-11058-0_72
– ident: ref5
  doi: 10.1016/j.rse.2016.10.010
– ident: ref9
– ident: ref19
– ident: ref15
  doi: 10.1007/978-3-319-33816-3_14
– ident: ref17
– ident: ref21
  doi: 10.14529/cmse170303
– ident: ref2
– ident: ref6
  doi: 10.1109/IGARSS.2016.7729467
– ident: ref13
  doi: 10.3390/rs13224668
– ident: ref14
  doi: 10.1109/LGRS.2017.2681128
– ident: ref4
  doi: 10.1109/IGARSS.2004.1369747
– ident: ref8
– ident: ref26
  doi: 10.15217/issn2079-0996.2018.4.70
– ident: ref28
  doi: 10.1590/1678-992x-2022-0041
– ident: ref18
  doi: 10.1371/journal.pone.0245230
– ident: ref16
– ident: ref10
SSID ssib018270670
ssib044764369
ssj0002774599
Score 2.2362616
Snippet Objective . Monitoring and determining the state of crops in agricultural production requires the use and improvement of neural network methods of artificial...
Objective. Monitoring and determining the state of crops in agricultural production requires the use and improvement of neural network methods of artificial...
SourceID doaj
crossref
SourceType Open Website
Index Database
StartPage 142
SubjectTerms artificial neural networks
crops
mathematical modeling
segmentation problem
Title Simulation of the of the DeepLabv3 neural network learning process for the agricultural fields segmentation
URI https://doaj.org/article/7d07660e2056470fa80a91f5bd965b03
Volume 50
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2542-095X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002774599
  issn: 2073-6185
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center)
  customDbUrl:
  eissn: 2542-095X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044764369
  issn: 2073-6185
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3LSsQwFA0yiOhCfOKbLGYbzKRp0yx94mIcBBXchTwHEWeGebj0271JOkNduXHRlgYS6OGSe265OQehbvC-sq7gxNbOEW5NQXRBa1K6QKXpaWGya0lfDAb125t8all9xZ6wLA-cgbsUDirtinoGmZoLGnRNteyF0jhZlSbrfFIhW8UURBKQZhEPoCzfOReQebOVdtqjGbCeMplLwuQC6qe63EDd2BcNU9nlapBEd3FSwlZFepzBJX_lr5bMf8pH9ztouyGS-Cp_wC5amy720FZLXnAffTy_fzbuXHgcMFC95ePW-0lfm68CRz1LWGaUu8FxYyIxxJN8gAADp00z9HC6UunAqe1thmd--NkcXRodoNf7u5ebB9KYKxDbE4UEVm1sDeWB4cbH3xpSWONZEAHyv6S20tpJw0KUAxNVoJUPzgD4urY0aawVh6gzGo_8EcI8aM2scw5SG7CroIEUBga8yEXx_Iofo3IJmZpkDQ0FtUeCWkWoVYRaRahVSVUB5QiDSx6j64jvak5Uwk4DEB-qiQ_1V3yc_Mcip2gzBQLkLCbPUGc-XfhztG6_5u-z6UUKPbg_ft_9AOyS1hA
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=Simulation+of+the+of+the+DeepLabv3+neural+network+learning+process+for+the+agricultural+fields+segmentation&rft.jtitle=Vestnik+Dagestanskogo+gosudarstvennogo+tehni%C4%8Deskogo+universiteta.+Tehni%C4%8Deskie+nauki+%28Online%29&rft.au=A.+F.+Rogachev&rft.au=I.+S.+Belousov&rft.date=2023-10-29&rft.pub=Dagestan+State+Technical+University&rft.issn=2073-6185&rft.eissn=2542-095X&rft.volume=50&rft.issue=3&rft.spage=142&rft.epage=149&rft_id=info:doi/10.21822%2F2073-6185-2023-50-3-142-149&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_7d07660e2056470fa80a91f5bd965b03
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2073-6185&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2073-6185&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2073-6185&client=summon