Constructing a Meta-Learner for Unsupervised Anomaly Detection

Unsupervised anomaly detection (AD) is critical for a wide range of practical applications, from network security to health and medical tools. Due to the diversity of problems, no single algorithm has been found to be superior for all AD tasks. Choosing an algorithm, otherwise known as the Algorithm...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE access Vol. 11; pp. 45815 - 45825
Main Authors:	Gutowska, Malgorzata, Little, Suzanne, Mccarren, Andrew
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	algorithm selection problem Algorithms Anomalies Anomaly detection Benchmark testing Classification algorithms Datasets Machine learning algorithms Measurement meta-features Meta-learning model selection Statistical analysis unsupervised anomaly detection Unsupervised learning
ISSN:	2169-3536, 2169-3536
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Unsupervised anomaly detection (AD) is critical for a wide range of practical applications, from network security to health and medical tools. Due to the diversity of problems, no single algorithm has been found to be superior for all AD tasks. Choosing an algorithm, otherwise known as the Algorithm Selection Problem (ASP), has been extensively examined in supervised classification problems, through the use of meta-learning and AutoML, however, it has received little attention in unsupervised AD tasks. This research proposes a new meta-learning approach that identifies an appropriate unsupervised AD algorithm given a set of meta-features generated from the unlabelled input dataset. The performance of the proposed meta-learner is superior to the current state of the art solution. In addition, a mixed model statistical analysis has been conducted to examine the impact of the meta-learner components: the meta-model, meta-features, and the base set of AD algorithms, on the overall performance of the meta-learner. The analysis was conducted using more than 10,000 datasets, which is significantly larger than previous studies. Results indicate that a relatively small number of meta-features can be used to identify an appropriate AD algorithm, but the choice of a meta-model in the meta-learner has a considerable impact.
AbstractList	Unsupervised anomaly detection (AD) is critical for a wide range of practical applications, from network security to health and medical tools. Due to the diversity of problems, no single algorithm has been found to be superior for all AD tasks. Choosing an algorithm, otherwise known as the Algorithm Selection Problem (ASP), has been extensively examined in supervised classification problems, through the use of meta-learning and AutoML, however, it has received little attention in unsupervised AD tasks. This research proposes a new meta-learning approach that identifies an appropriate unsupervised AD algorithm given a set of meta-features generated from the unlabelled input dataset. The performance of the proposed meta-learner is superior to the current state of the art solution. In addition, a mixed model statistical analysis has been conducted to examine the impact of the meta-learner components: the meta-model, meta-features, and the base set of AD algorithms, on the overall performance of the meta-learner. The analysis was conducted using more than 10,000 datasets, which is significantly larger than previous studies. Results indicate that a relatively small number of meta-features can be used to identify an appropriate AD algorithm, but the choice of a meta-model in the meta-learner has a considerable impact.
Author	Gutowska, Malgorzata Mccarren, Andrew Little, Suzanne
Author_xml	– sequence: 1 givenname: Malgorzata orcidid: 0000-0002-1724-4912 surname: Gutowska fullname: Gutowska, Malgorzata email: malgorzata.gutowska2@mail.dcu.ie organization: School of Computing, Dublin City University, Dublin 9, Ireland – sequence: 2 givenname: Suzanne orcidid: 0000-0003-3281-3471 surname: Little fullname: Little, Suzanne organization: School of Computing, Dublin City University, Dublin 9, Ireland – sequence: 3 givenname: Andrew orcidid: 0000-0002-7297-0984 surname: Mccarren fullname: Mccarren, Andrew organization: School of Computing, Dublin City University, Dublin 9, Ireland
BookMark	eNp9kFtLxDAQhYMoeP0F-lDwuWsuzbZ5EZZ6hRUf1OcwbSbSZU3WJCvsvzdrFcQHA0PCMN_JmXNIdp13SMgpoxPGqLqYte3109OEUy4mgtcVY2KHHHA2VaWQYrr7671PTmJc0Hya3JL1AblsvYsprPs0uNcCigdMUM4RgsNQWB-KFxfXKwwfQ0RTzJx_g-WmuMKEmfDumOxZWEY8-b6PyMvN9XN7V84fb-_b2bzsK6pS2eXfKBhoJE6FNRZBMeQNUx2lsgFQ3JjaMmZrSSW3FXIA2jfQG7otI47I_ahrPCz0KgxvEDbaw6C_Gj68aghp6JeouaW0RuyaDqEyVd9ZZQ0qqRrFp4zJrHU-aq2Cf19jTHrh18Fl-zpbqqTkteB5So1TffAxBrS6HxJsd04BhqVmVG_T12P6epu-_k4_s-IP--P4f-pspAZE_EUwzipWi08kspK_
CODEN	IAECCG
CitedBy_id	crossref_primary_10_1109_JSEN_2024_3383416 crossref_primary_10_1109_ACCESS_2024_3420090 crossref_primary_10_1016_j_jmsy_2025_06_023
Cites_doi	10.1007/s10462-013-9406-y 10.1016/j.neucom.2016.04.027 10.1109/IJCNN.2015.7280644 10.3390/electronics10182236 10.1109/ACCESS.2020.2964726 10.1145/342009.335437 10.1109/ICDM.2008.17 10.25080/Majora-14bd3278-006 10.1109/TKDE.2019.2905606 10.1007/978-3-030-05318-5 10.1109/ICDM.2017.137 10.1007/s10618-019-00661-z 10.1016/S0065-2458(08)60520-3 10.1016/j.artint.2016.04.003 10.1371/journal.pone.0152173 10.4324/9780203771587 10.1016/j.patrec.2022.07.019 10.1109/ACCESS.2021.3090936 10.1109/ICDM50108.2020.00135 10.1007/978-3-030-05318-5_4 10.1109/ACCESS.2019.2932769 10.1145/1456650.1456656 10.1145/342009.335388 10.1007/s10994-015-5521-0 10.1109/ACCESS.2018.2883681 10.1016/j.eswa.2016.11.034 10.1007/s10618-012-0300-z 10.1145/1401890.1401946 10.1007/978-3-030-05318-5_9 10.1007/3-540-47887-6_53 10.1007/978-3-319-46128-1_13 10.1016/j.ins.2019.06.005 10.1109/JPROC.2021.3052449 10.1016/j.eswa.2018.10.036 10.1023/A:1019956318069 10.1145/1541880.1541882 10.1007/978-3-030-05318-5_7 10.1016/j.ins.2015.05.010 10.1609/aaai.v29i1.9354 10.1007/978-3-030-05318-5_2 10.1007/s10618-015-0444-8 10.1109/4235.585893 10.1016/j.procs.2018.08.250
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 ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2023.3274113
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE 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	45825
ExternalDocumentID	oai_doaj_org_article_2f007eeb8bea4d4cbf9fde9598926115 10_1109_ACCESS_2023_3274113 10121417
Genre	orig-research
GrantInformation_xml	– fundername: Science Foundation Ireland Centre for Research Training in Artificial Intelligence grantid: 18/CRT/6223 funderid: 10.13039/501100001602
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-c409t-b1690ada85e63fdfea91e2819b0058aa92dd7f11f75052f4e2aa0c8acd0acd0d3
IEDL.DBID	RIE
ISICitedReferencesCount	2
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000991569600001&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	Fri Oct 03 12:47:04 EDT 2025 Sun Jun 29 14:12:59 EDT 2025 Sat Nov 29 04:02:37 EST 2025 Tue Nov 18 22:52:11 EST 2025 Wed Aug 27 02:22:08 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-c409t-b1690ada85e63fdfea91e2819b0058aa92dd7f11f75052f4e2aa0c8acd0acd0d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-1724-4912 0000-0002-7297-0984 0000-0003-3281-3471
OpenAccessLink	https://ieeexplore.ieee.org/document/10121417
PQID	2814552732
PQPubID	4845423
PageCount	11
ParticipantIDs	ieee_primary_10121417 crossref_citationtrail_10_1109_ACCESS_2023_3274113 doaj_primary_oai_doaj_org_article_2f007eeb8bea4d4cbf9fde9598926115 crossref_primary_10_1109_ACCESS_2023_3274113 proquest_journals_2814552732
PublicationCentury	2000
PublicationDate	20230000 2023-00-00 20230101 2023-01-01
PublicationDateYYYYMMDD	2023-01-01
PublicationDate_xml	– year: 2023 text: 20230000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
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 ref12 ref15 ref59 ref14 ref52 ref11 ref55 ref10 schölkopf (ref46) 2000 ref16 ref19 zhao (ref18) 2021; 34 biewald (ref58) 2020 le clei (ref21) 2022 ref51 chollet (ref57) 2015 ref45 ref48 goldstein (ref50) 2012; 9 ref47 ref42 demidenko (ref62) 2013 ref44 ref43 guyon (ref36) 2019 ref49 ref8 ref7 ref9 ref4 haibo (ref63) 2013; 1 ref6 ref5 feurer (ref39) 2022; 23 ref40 ref34 ref37 ref31 ref33 ref32 mu noz (ref35) 2015; 317 ref2 ref1 kingma (ref54) 2013 shyu (ref53) 2003 mcculloch (ref61) 2004 ref24 ref23 chalapathy (ref3) 2019 ref25 ref20 ref64 mantovani (ref30) 2020 ref22 stroup (ref60) 2012 zhao (ref56) 2019; 20 ref28 ref27 feurer (ref38) 2015; 28 horváth (ref26) 2016 ref29 kandanaarachchi (ref17) 2019 olson (ref41) 2016
References_xml	– ident: ref13 doi: 10.1007/s10462-013-9406-y – ident: ref31 doi: 10.1016/j.neucom.2016.04.027 – volume: 23 start-page: 11936 year: 2022 ident: ref39 article-title: Auto-sklearn 2.0: Hands-free AutoML via meta-learning publication-title: J Mach Learn Res – ident: ref25 doi: 10.1109/IJCNN.2015.7280644 – ident: ref20 doi: 10.3390/electronics10182236 – year: 2004 ident: ref61 publication-title: Generalized Linear and Mixed Models – ident: ref12 doi: 10.1109/ACCESS.2020.2964726 – ident: ref45 doi: 10.1145/342009.335437 – year: 2019 ident: ref36 article-title: Analysis of the AutoML challenge series publication-title: Automata Machine Learning – year: 2012 ident: ref60 publication-title: Generalized Linear Mixed Models Modern Concepts Methods and Applications – ident: ref49 doi: 10.1109/ICDM.2008.17 – ident: ref23 doi: 10.25080/Majora-14bd3278-006 – ident: ref55 doi: 10.1109/TKDE.2019.2905606 – ident: ref14 doi: 10.1007/978-3-030-05318-5 – ident: ref27 doi: 10.1109/ICDM.2017.137 – ident: ref43 doi: 10.1007/s10618-019-00661-z – ident: ref16 doi: 10.1016/S0065-2458(08)60520-3 – ident: ref11 doi: 10.1016/j.artint.2016.04.003 – start-page: 66 year: 2016 ident: ref41 article-title: TPOT: A tree-based pipeline optimization tool for automating machine learning publication-title: Proc Workshop Autom Mach Learn – year: 2013 ident: ref54 article-title: Auto-encoding variational Bayes publication-title: arXiv 1312 6114 – ident: ref5 doi: 10.1371/journal.pone.0152173 – ident: ref59 doi: 10.4324/9780203771587 – ident: ref64 doi: 10.1016/j.patrec.2022.07.019 – ident: ref19 doi: 10.1109/ACCESS.2021.3090936 – ident: ref52 doi: 10.1109/ICDM50108.2020.00135 – ident: ref37 doi: 10.1007/978-3-030-05318-5_4 – ident: ref2 doi: 10.1109/ACCESS.2019.2932769 – ident: ref15 doi: 10.1145/1456650.1456656 – volume: 20 start-page: 1 year: 2019 ident: ref56 article-title: PyOD: A Python toolbox for scalable outlier detection publication-title: J Mach Learn Res – year: 2020 ident: ref30 article-title: Rethinking default values: A low cost and efficient strategy to define hyperparameters publication-title: arXiv 2008 00025 – ident: ref44 doi: 10.1145/342009.335388 – ident: ref51 doi: 10.1007/s10994-015-5521-0 – ident: ref8 doi: 10.1109/ACCESS.2018.2883681 – ident: ref10 doi: 10.1016/j.eswa.2016.11.034 – ident: ref7 doi: 10.1007/s10618-012-0300-z – start-page: 32 year: 2019 ident: ref17 article-title: Instance space analysis for unsupervised outlier detection publication-title: Proc EDML SDM – year: 2020 ident: ref58 publication-title: Experiment Tracking With Weights and Biases – year: 2022 ident: ref21 article-title: N-1 experts: Unsupervised anomaly detection model selection publication-title: Proc 1st Conf Automated Mach Learn (Late-Breaking Workshop) – ident: ref48 doi: 10.1145/1401890.1401946 – year: 2019 ident: ref3 article-title: Deep learning for anomaly detection: A survey publication-title: arXiv 1901 03407 – year: 2015 ident: ref57 publication-title: Keras – volume: 1 start-page: 27 year: 2013 ident: ref63 publication-title: Imbalanced Learning Foundations Algorithms and Applications – ident: ref42 doi: 10.1007/978-3-030-05318-5_9 – start-page: 172 year: 2003 ident: ref53 article-title: A novel anomaly detection scheme based on principal component classifier publication-title: Proc IEEE Found New Directions Data Mining Workshop Conjunct 3rd IEEE Int Conf Data Mining (ICDM03) – start-page: 268 year: 2016 ident: ref26 article-title: Effects of random sampling on SVM hyper-parameter tuning publication-title: Proc Int Conf Intell Syst Design Appl – ident: ref47 doi: 10.1007/3-540-47887-6_53 – ident: ref28 doi: 10.1007/978-3-319-46128-1_13 – ident: ref29 doi: 10.1016/j.ins.2019.06.005 – year: 2013 ident: ref62 publication-title: Mixed Models Theory and Applications With R – ident: ref4 doi: 10.1109/JPROC.2021.3052449 – ident: ref33 doi: 10.1016/j.eswa.2018.10.036 – volume: 9 start-page: 65 year: 2012 ident: ref50 article-title: Histogram-based outlier score (HBOS): A fast unsupervised anomaly detection algorithm publication-title: Proc KI Poster Demo Track – ident: ref34 doi: 10.1023/A:1019956318069 – volume: 28 start-page: 2962 year: 2015 ident: ref38 article-title: Efficient and robust automated machine learning publication-title: Proc Adv Neural Inf Process Syst – volume: 34 start-page: 4489 year: 2021 ident: ref18 article-title: Automatic unsupervised outlier model selection publication-title: Proc Adv Neural Inf Process Syst – ident: ref6 doi: 10.1145/1541880.1541882 – ident: ref40 doi: 10.1007/978-3-030-05318-5_7 – volume: 317 start-page: 224 year: 2015 ident: ref35 article-title: Algorithm selection for black-box continuous optimization problems: A survey on methods and challenges publication-title: Inf Sci doi: 10.1016/j.ins.2015.05.010 – ident: ref24 doi: 10.1609/aaai.v29i1.9354 – ident: ref22 doi: 10.1007/978-3-030-05318-5_2 – ident: ref1 doi: 10.1007/s10618-015-0444-8 – ident: ref9 doi: 10.1109/4235.585893 – start-page: 582 year: 2000 ident: ref46 article-title: Support vector method for novelty detection publication-title: Proc Adv Neural Inf Process Syst – ident: ref32 doi: 10.1016/j.procs.2018.08.250
SSID	ssj0000816957
Score	2.2785294
Snippet	Unsupervised anomaly detection (AD) is critical for a wide range of practical applications, from network security to health and medical tools. Due to the...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	45815
SubjectTerms	algorithm selection problem Algorithms Anomalies Anomaly detection Benchmark testing Classification algorithms Datasets Machine learning algorithms Measurement meta-features Meta-learning model selection Statistical analysis unsupervised anomaly detection Unsupervised learning
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NS8MwFA8yPOhB_Jg4ndKDR7s1_UpyEeZ0eHF4cLBbyKcIs461Cv735qXdqAh68dBLSUnze30v7yXp74fQpc0jJXIVh1JkKkwxVaG0RIaGWSMkwzSSqRebINMpnc_ZY0vqC86E1fTANXDD2LpZzBhJpRGpTpW0zGrDMkaZS_797-VxRFirmPIxmOKcZaShGcIRG47GYzeiAaiFDxLgbMHJt6nIM_Y3Eis_4rKfbCb7aK_JEoNR_XYHaMsUh2i3xR14hK5BarMmfy2eAxE8mEqEni3VrAKXiQazonxfQiQojQ5clf8qFp_Bran82auii2aTu6fxfdiIIYTKlWBVKGE_S2hBM5MnVjskGTawCwZ-RIVgsdbEYmwJSNPZ1MRCRIoKpSO4dHKMOsVbYU5Q4GoIDSrjSiYy1QQyEk2Ea4-l816ieyhe48JVwxQOghUL7iuGiPEaTA5g8gbMHrraPLSsiTJ-b34DgG-aAsu1v-Fszxvb879s30NdMFerPxzjFJMe6q_txxuXLLnDKvV0c_Hpf_R9hnZgPPVqTB91nMHNOdpWH9VLubrwX-MXvu7iOA priority: 102 providerName: Directory of Open Access Journals
Title	Constructing a Meta-Learner for Unsupervised Anomaly Detection
URI	https://ieeexplore.ieee.org/document/10121417 https://www.proquest.com/docview/2814552732 https://doaj.org/article/2f007eeb8bea4d4cbf9fde9598926115
Volume	11
WOSCitedRecordID	wos000991569600001&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/eLvHCXMwlV1LS8QwEB5UPOjBt7i-6MGjXZs-Ns1FWFfFi-JBwVvIYyKCdhd3Fbz4282kcVFEwUNLKQlNv-mkM3l8H8CB62VG9UyealWZtGS1SbXjOkXhUGnB6kyXQWyCX13Vd3fiOm5WD3thEDEsPsMuXYa5fDs0LzRUdkRcVKxkfBZmOe-1m7WmAyqkICEqHpmFWCaO-oOBf4kuCYR3C6JpYcW3v08g6Y-qKj-64vB_OV_-Z8tWYCkGkkm_tfwqzGCzBotf6AXX4ZjUOFt-2OY-UcklTlQaCFXxOfHBanLbjF9G1FmM0Sb9ZvikHt-SU5yE5VnNBtyen90MLtKol5Aan6VNUk1TXsqqusJe4awHWzCkiTJytVopkVvLHWOOk3qdKzFXKjO1MjajwxabMNcMG9yCxKcZloTIjS50aTkFLZYrX55p7-DcdiD_xFGaSCZOmhaPMiQVmZAt-JLAlxH8DhxOK41aLo2_i5-QgaZFiQg73PDIy-hXMnc-yEHUtUZV2tJoJ5xFUYla-NyQVR3YIGt9eV5rqA7sftpbRq8dS49VGRjp8u1fqu3AAjWxHYPZhTlvQ9yDefM6eRg_74eE3p8v38_2w8f5Acmr4OI
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB7aJND0kPSRkE22rQ891hvLllfWJbDdNiQkWXpIIDehx6gUNt4luyn031cja5eU0EIPBmMkLH_jkWb0-D6Aj35YWD20ZW50bXPOGpsbL0yO0qM2kjWF4VFsQkwmze2t_JYOq8ezMIgYN5_hgG7jWr6b2QeaKjsmLirGmXgOmzXnZdEd11pPqZCGhKxF4hZihTwejcfhMwYkET6oiKiFVX-MP5GmP-mqPOmM4whzuvufbXsFOymUzEad7V_DM2zfwMtHBINv4YT0ODuG2PZ7prMrXOo8UqrifRbC1eymXTzMqbtYoMtG7exOT39lX3AZN2i1e3Bz-vV6fJYnxYTchjxtmRta9NJONzUOK-8C3JIhLZWRszVay9I54RnzgvTrPMdS68I22rqCLlftw0Y7a_EAspBoOJIit6Yy3AkKW5zQoTwzwcWF60G5wlHZRCdOqhZTFdOKQqoOfEXgqwR-Dz6tK807No1_F_9MBloXJSrs-CAgr5JnqdKHMAfRNAY1d9waL71DWctGhuyQ1T3YI2s9el9nqB70V_ZWyW8XKmDFIyddefiXah_gxdn11aW6PJ9cHME2NbebkenDRrAnvoMt-3P5Y3H_Pv6cvwEJFeID
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=Constructing+a+Meta-Learner+for+Unsupervised+Anomaly+Detection&rft.jtitle=IEEE+access&rft.au=Gutowska%2C+Malgorzata&rft.au=Little%2C+Suzanne&rft.au=Mccarren%2C+Andrew&rft.date=2023&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=11&rft.spage=45815&rft.epage=45825&rft_id=info:doi/10.1109%2FACCESS.2023.3274113&rft.externalDocID=10121417
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