On Ensemble Learning Models for Autoencoder-Based Identification of Nonlinear Dynamical Systems

Identifying the dynamic model of a system has been a subject of extensive research for decades. However, dealing with highly complex, possibly nonlinear, and noisy systems remains an open problem. In recent years, the use of data-driven techniques based on machine learning for system identification...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE access Ročník 13; s. 169071 - 169082
Hlavní autori:	Arridu, Nicola, Lippi, Martina, Franceschelli, Mauro, Gasparri, Andrea
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Piscataway IEEE 2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Accuracy Autoencoders Biological system modeling Complex systems Data models data-driven analysis Decoding Dynamic models Dynamical systems Ensemble learning Machine learning Neural networks Nonlinear dynamical systems Nonlinear system identification Nonlinear systems Numerical models System dynamics System identification
ISSN:	2169-3536, 2169-3536
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Identifying the dynamic model of a system has been a subject of extensive research for decades. However, dealing with highly complex, possibly nonlinear, and noisy systems remains an open problem. In recent years, the use of data-driven techniques based on machine learning for system identification has represented a promising solution for addressing the challenges of complex system identification. Among these methods, auto-encoders have been successfully applied to compactly represent the system state in a latent space used for estimating the system dynamics. In this work, we propose leveraging the ensemble paradigm for system identification, and in particular to exploit an ensemble of autoencoders, to reduce the uncertainty compared to individual autoencoders. To this end, we propose an algorithm for selecting autoencoders based on a combination of an accuracy metric and a diversity index. We validate this approach using traditional benchmarks in the field of nonlinear system identification.
AbstractList	Identifying the dynamic model of a system has been a subject of extensive research for decades. However, dealing with highly complex, possibly nonlinear, and noisy systems remains an open problem. In recent years, the use of data-driven techniques based on machine learning for system identification has represented a promising solution for addressing the challenges of complex system identification. Among these methods, auto-encoders have been successfully applied to compactly represent the system state in a latent space used for estimating the system dynamics. In this work, we propose leveraging the ensemble paradigm for system identification, and in particular to exploit an ensemble of autoencoders, to reduce the uncertainty compared to individual autoencoders. To this end, we propose an algorithm for selecting autoencoders based on a combination of an accuracy metric and a diversity index. We validate this approach using traditional benchmarks in the field of nonlinear system identification.
Author	Lippi, Martina Arridu, Nicola Gasparri, Andrea Franceschelli, Mauro
Author_xml	– sequence: 1 givenname: Nicola orcidid: 0000-0002-8594-0629 surname: Arridu fullname: Arridu, Nicola organization: Università degli Studi Roma Tre, Rome, Italy – sequence: 2 givenname: Martina orcidid: 0000-0003-0470-9191 surname: Lippi fullname: Lippi, Martina email: martina.lippi@uniroma3.it organization: Università degli Studi Roma Tre, Rome, Italy – sequence: 3 givenname: Mauro orcidid: 0000-0001-6522-4046 surname: Franceschelli fullname: Franceschelli, Mauro organization: Università degli Studi di Cagliari, Cagliari, Italy – sequence: 4 givenname: Andrea orcidid: 0000-0001-5765-9736 surname: Gasparri fullname: Gasparri, Andrea organization: Università degli Studi Roma Tre, Rome, Italy
BookMark	eNpNUU1v2zAMFYYOWNf1F3QHATs7FfXl-Jhl2RogWw9pz4Is0YUCR-ok55B_P7UutvFC4pHvkeD7SC5iikjIDbAFAOtuV-v1Zr9fcMbVQmiADuQ7cslBd41QQl_8V38g16UcWI1lhVR7Scx9pJtY8NiPSHdocwzxif5MHsdCh5Tp6jQljK4CuflqC3q69RinMARnp5AiTQP9leIYYiXTb-doj7Uz0v25THgsn8j7wY4Fr9_yFXn8vnlY3zW7-x_b9WrXuHry1KiW875nFmyPTghkS68lR9cxRNdKq7yzCEqjalnbgrBCKs0kCs4cF4MTV2Q76_pkD-Y5h6PNZ5NsMK9Ayk_G5im4EQ1nig3eia4HL13vlp2U2sv6S965nkHV-jJrPef0-4RlMod0yrGebwRXGlTXgqxTYp5yOZWScfi7FZh5McbMxpgXY8ybMZX1eWYFRPzHAGiF1kL8AQuriu0
CODEN	IAECCG
Cites_doi	10.1007/978-0-387-84858-7 10.1201/9781003456285 10.1002/aic.690370209 10.1038/nature14541 10.17648/sbai-2019-111167 10.1137/18M1177846 10.1017/9781108380690 10.1109/LCSYS.2023.3335036 10.1016/j.ins.2015.09.048 10.1007/s11704-019-8208-z 10.1016/j.iswa.2024.200344 10.1002/047134608X.W1046 10.1109/CDC49753.2023.10384143 10.1023/A:1022859003006 10.1016/j.jcp.2018.10.045 10.1016/j.automatica.2021.109666 10.1201/b12207 10.1146/annurev-control-053018-023744 10.1016/j.ifacol.2021.08.406 10.1061/(ASCE)EM.1943-7889.0001556 10.1007/978-3-662-12616-5 10.1109/TNNLS.2020.2980383 10.1109/CVPR46437.2021.01620 10.1109/ICNN.1996.548872 10.1016/j.automatica.2012.09.018 10.1007/978-1-4419-9326-7 10.1109/CDC40024.2019.9030219 10.1016/j.automatica.2023.111210 10.1109/ICNN.1994.374611 10.1002/9781118535561 10.1016/j.ifacol.2020.12.1329 10.1109/72.80202 10.1098/rspl.1895.0041 10.1016/j.ifacol.2017.08.071 10.1016/j.neucom.2017.02.029
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2025.3611914
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ: Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	169082
ExternalDocumentID	oai_doaj_org_article_2050fdc39b1d4cbc89446d411029cb01 10_1109_ACCESS_2025_3611914 11173663
Genre	orig-research
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c361t-5722bb0a1abec33e08d642ec90eec74a5dcae156e5707713a345604e320c23fc3
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001586193100008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Tue Oct 07 09:25:21 EDT 2025 Mon Dec 08 03:37:56 EST 2025 Sat Nov 29 07:18:34 EST 2025 Wed Oct 08 06:22:38 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c361t-5722bb0a1abec33e08d642ec90eec74a5dcae156e5707713a345604e320c23fc3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-8594-0629 0000-0001-5765-9736 0000-0003-0470-9191 0000-0001-6522-4046
OpenAccessLink	https://ieeexplore.ieee.org/document/11173663
PQID	3256159714
PQPubID	4845423
PageCount	12
ParticipantIDs	proquest_journals_3256159714 crossref_primary_10_1109_ACCESS_2025_3611914 doaj_primary_oai_doaj_org_article_2050fdc39b1d4cbc89446d411029cb01 ieee_primary_11173663
PublicationCentury	2000
PublicationDate	20250000 2025-00-00 20250101 2025-01-01
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– year: 2025 text: 20250000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2025
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 ref15 ref37 ref31 ref11 ref33 ref10 ref32 ref1 Hinton (ref30); 6 ref17 ref39 Billings (ref4) 2013 ref16 ref38 ref19 ref18 Wood (ref22) 2023 Pearson (ref36) 1895; 58 ref24 ref23 ref26 ref25 ref20 ref21 ref28 ref27 ref29 ref8 ref7 ref9 ref3 ref6 ref5 Negrini (ref14) 2021 Schetzen (ref2) 2006
References_xml	– ident: ref34 doi: 10.1007/978-0-387-84858-7 – ident: ref39 doi: 10.1201/9781003456285 – ident: ref31 doi: 10.1002/aic.690370209 – ident: ref10 doi: 10.1038/nature14541 – ident: ref29 doi: 10.17648/sbai-2019-111167 – ident: ref9 doi: 10.1137/18M1177846 – ident: ref7 doi: 10.1017/9781108380690 – ident: ref15 doi: 10.1109/LCSYS.2023.3335036 – ident: ref25 doi: 10.1016/j.ins.2015.09.048 – ident: ref18 doi: 10.1007/s11704-019-8208-z – volume: 6 start-page: 3 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref30 article-title: Autoencoders, minimum description length and Helmholtz free energy – ident: ref5 doi: 10.1016/j.iswa.2024.200344 – ident: ref1 doi: 10.1002/047134608X.W1046 – start-page: 1 year: 2023 ident: ref22 article-title: A unified theory of diversity in ensemble learning publication-title: J. Mach. Learn. Res. – ident: ref12 doi: 10.1109/CDC49753.2023.10384143 – ident: ref21 doi: 10.1023/A:1022859003006 – ident: ref11 doi: 10.1016/j.jcp.2018.10.045 – ident: ref8 doi: 10.1016/j.automatica.2021.109666 – ident: ref20 doi: 10.1201/b12207 – ident: ref24 doi: 10.1146/annurev-control-053018-023744 – ident: ref17 doi: 10.1016/j.ifacol.2021.08.406 – ident: ref27 doi: 10.1061/(ASCE)EM.1943-7889.0001556 – ident: ref6 doi: 10.1007/978-3-662-12616-5 – ident: ref33 doi: 10.1109/TNNLS.2020.2980383 – ident: ref23 doi: 10.1109/CVPR46437.2021.01620 – ident: ref37 doi: 10.1109/ICNN.1996.548872 – ident: ref3 doi: 10.1016/j.automatica.2012.09.018 – ident: ref19 doi: 10.1007/978-1-4419-9326-7 – ident: ref26 doi: 10.1109/CDC40024.2019.9030219 – ident: ref28 doi: 10.1016/j.automatica.2023.111210 – ident: ref35 doi: 10.1109/ICNN.1994.374611 – volume-title: Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains year: 2013 ident: ref4 doi: 10.1002/9781118535561 – ident: ref16 doi: 10.1016/j.ifacol.2020.12.1329 – ident: ref13 doi: 10.1109/72.80202 – volume: 58 start-page: 240 year: 1895 ident: ref36 article-title: Note on regression and inheritance in the case of two parents publication-title: Proc. Roy. Soc. London doi: 10.1098/rspl.1895.0041 – ident: ref38 doi: 10.1016/j.ifacol.2017.08.071 – ident: ref32 doi: 10.1016/j.neucom.2017.02.029 – year: 2021 ident: ref14 article-title: A neural network ensemble approach to system identification publication-title: arXiv:2110.08382 – volume-title: The Volterra and Wiener Theories of Nonlinear Systems year: 2006 ident: ref2
SSID	ssj0000816957
Score	2.3343499
Snippet	Identifying the dynamic model of a system has been a subject of extensive research for decades. However, dealing with highly complex, possibly nonlinear, and...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Index Database Publisher
StartPage	169071
SubjectTerms	Accuracy Autoencoders Biological system modeling Complex systems Data models data-driven analysis Decoding Dynamic models Dynamical systems Ensemble learning Machine learning Neural networks Nonlinear dynamical systems Nonlinear system identification Nonlinear systems Numerical models System dynamics System identification
SummonAdditionalLinks	– databaseName: DOAJ: Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELUQYoAB8VFEoSAPjATs2K7jsRQQAyoMIHWzbOeCkCBF_eD3c4kNFDGwMEVKIl38Lrm7Z-XeEXICWgvnATLFQ5FJIU1WAHMZD0rKSoAxum0UvtWjUTEem_ulUV_NP2FRHjgCh-RcsaoMwnheyuBDYZDAlBKzVm6Cj51bTJslMtXG4IL3jdJJZogzcz4YDnFFSAhzdSb6razZj1TUKvanESu_4nKbbK63yGaqEukgPt02WYF6h2wsaQfuEntX06t6Bq_-BWhSSX2izWizlxnFSpQOFvNJo1JZwjS7wFxV0tiUW6VdOjqp6CgKZbgpvYyT6dFo0jDvkMfrq4fhTZamJWQB1zPPlM5z75njCH0QAlhRIreAYBhA0NKpMjhAtgZKM43U1AmsnZgEkbOQiyqIPbJaT2rYJxSjp2N4wYU8SOlLPKpcVUwpAcqLqktOP4Gzb1EUw7ZkghkbcbYNzjbh3CUXDbhftzaK1u0J9LNNfrZ_-blLOo1rvu1xrgWWS13S-_SVTZ_fzAos5LBO01we_IftQ7LerCfuvPTI6ny6gCOyFt7nz7PpcfvmfQC8DNop priority: 102 providerName: Directory of Open Access Journals
Title	On Ensemble Learning Models for Autoencoder-Based Identification of Nonlinear Dynamical Systems
URI	https://ieeexplore.ieee.org/document/11173663 https://www.proquest.com/docview/3256159714 https://doaj.org/article/2050fdc39b1d4cbc89446d411029cb01
Volume	13
WOSCitedRecordID	wos001586193100008&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: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 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 customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 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/eLvHCXMwlV1Jb9QwFLZoxQEOXaCo000-cCStE9t1fJwOU3GgAweQerPs5xeEVDJolh772_vsuAtCHLgkURLHyxf7Lcn7HmPv0RjpA2Kla2grJZWtWhS-qkEr1Um01uRA4c9mNmuvr-3XEqyeY2EQMf98hqfpMH_Lj3NYJ1fZGc1LI0lEbrANY86HYK1Hh0rKIGG1KcxCtbBn48mEOkE2YKNP5XlmMvtD-mSS_pJV5a-lOMuXy-3_bNkO2yqKJB8PyO-yF9i_Ya-f0Qu-Ze5Lz6f9En-FG-SFSPUHT9nPbpaclFU-Xq_micgy4qK6IHEW-RC32xVHHp93fDZwafgF_zgkr6dKC835Hvt-Of02-VSVhAoVUP9XlTZNE4LwNaEDUqJoI5kfCFYgglFeR_BIBh1qIwxZr16SeiUUykZAIzuQ79hmP-9xn3FaYL2gCx4aUCpE2utGd0JriTrIbsQ-PAy0-z3wZrhsbwjrBlxcwsUVXEbsIoHxeGsivc4naJRdmUNUQIsugrShjgoCtJZs2ajomY2FIOoR20vIPNVXQBmxowdsXZmhSydJ1yNVztTq4B_FDtmr1MTB33LENleLNR6zl3C7-rlcnGTjnbZXd9OT_CLeA7wB2lw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB7RgtRyoECLWGiLDxxJ68Q2jo_bpVUrloVDkXqz_JggpJKt9sHvZ-y4BYR64JQojuPHF3seyXwD8Ba1Fs4jVqoObSWFNFWL3FV1UFJ2Ao3ROVB4qmez9urKfCnB6jkWBhHzz2d4lE7zt_w4D-vkKjumdakFicgNeJhSZ5VwrTuXSsohYZQu3EI1N8fjyYSGQVZgo47E-8xl9pf8yTT9Ja_KP5txljBnO__Zt6fwpKiSbDxg_wweYP8cHv9BMLgL9nPPTvsl_vDXyAqV6jeW8p9dLxmpq2y8Xs0TlWXERXVCAi2yIXK3K648Nu_YbGDTcAv2YUhfT40WovM9-Hp2ejk5r0pKhSrQ-FeV0k3jPXc14ROEQN5GMkAwGI4YtHQqBodk0qHSXJP96gQpWFyiaHhoRBfEC9js5z2-BEZbrONU4EITpPSRjqpRHVdKoPKiG8G724m2NwNzhs0WBzd2wMUmXGzBZQQnCYy7WxPtdb5As2zLKqIKincxCOPrKIMPrSFrNkp6ZmOC5_UI9hIyv9sroIxg_xZbW9bo0grS9kiZ07V8dU-1N7B1fvlpaqcXs4-vYTt1d_C-7MPmarHGA3gUfq6-LxeH-UX8BfeF238
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=On+Ensemble+Learning+Models+for+Autoencoder-Based+Identification+of+Nonlinear+Dynamical+Systems&rft.jtitle=IEEE+access&rft.au=Arridu%2C+Nicola&rft.au=Lippi%2C+Martina&rft.au=Franceschelli%2C+Mauro&rft.au=Gasparri%2C+Andrea&rft.date=2025&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=13&rft.spage=169071&rft.epage=169082&rft_id=info:doi/10.1109%2FACCESS.2025.3611914&rft.externalDocID=11173663
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon