Please use this identifier to cite or link to this item:https://hdl.handle.net/20.500.12259/54731
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGvardinskas, Mindaugas-
dc.contributor.authorTamošiūnaitė, Minija-
dc.coverage.spatialLT-
dc.date.accessioned2018-10-07T00:20:15Z-
dc.date.available2018-10-07T00:20:15Z-
dc.date.issued2016-
dc.identifier.issn1392124X-
dc.identifier.otherVDU02-000020515-
dc.identifier.urihttps://doi.org/10.5755/j01.itc.45.2.12052-
dc.description.abstractConvex classification error rate estimator is described as weighted combination of the low-biased estimator and the high-biased estimator. If the underlying data model is known, the coefficients (weights) can be optimized so that the bias and root-mean-square error of the estimator is minimized. However, in most situations, data model is unknown. In this paper we propose a new error estimation method, based on approximation of unbiased convex error rate estimator. Experiments with real world and synthetic data sets show that common error estimation methods, such as resubstitution, repeated 10-foldcross-validation, leave-one-out and random subsampling are outperformed (in terms of root-mean-square error) by the proposed methoden
dc.description.sponsorshipMatematikos ir statistikos katedra-
dc.description.sponsorshipVytauto Didžiojo universitetas-
dc.format.extentp. 148-155-
dc.language.isoen-
dc.relation.ispartofInformacinės technologijos ir valdymas = Information technology and control. Kaunas : Technologija, 2016, t. 45, nr. 2-
dc.relation.isreferencedbyScience Citation Index Expanded (Web of Science)-
dc.relation.isreferencedbyINSPEC-
dc.relation.isreferencedbyVINITI-
dc.relation.isreferencedbyScopus-
dc.subjectError estimationen
dc.subjectResubstitutionen
dc.subjectCross-validationen
dc.subjectBootstrapen
dc.subject.classificationStraipsnis Clarivate Analytics Web of Science / Article in Clarivate Analytics Web of Science (S1)-
dc.subject.otherInformatika / Informatics (N009)-
dc.titleApproximation of unbiased convex classification error rate estimatoren
dc.typeresearch article-
dc.identifier.doihttps://doi.org/10.5755/j01.itc.45.2.12052-
dc.identifier.isiWOS:000378875700003-
dcterms.bibliographicCitation20-
dc.date.updated2019-06-07T13:39Z-
local.object{"source": {"code": "vdu", "handle": "20515"}, "publisher": {"name": "Technologija", "list": false}, "db": {"clarivate": true, "scopus": true, "list": true}, "issn": ["1392-124X"], "doi": "10.5755/j01.itc.45.2.12052", "code": "S1", "subject": ["N009"], "url": ["https://doi.org/10.5755/j01.itc.45.2.12052"], "country": "LT", "language": "en", "area": "N", "original": true, "pages": 8, "sheets": 0.571, "timestamp": "20190607133919.0", "account": {"year": 2016, "late": false}, "na": 2, "nip": 1, "affiliation": [{"contribution": 0.5, "aip": 1, "country": ["LT"], "rel": "aut", "org": [{"create": true, "contribution": 0.5, "name": "Vytauto Didžiojo universitetas", "id": "111950396", "level": "0", "type": "uni", "research": "1", "status": "0", "unit": {"name": "Informatikos fakultetas", "id": "04", "level": "1", "type": "fak", "research": "1", "status": "0", "unit": {"name": "Matematikos ir statistikos katedra", "id": "0402", "level": "2", "type": "kat", "research": "1", "status": "0"}}}], "id": "FB3859C160AE2A813DEAB032B4600AE7", "lname": "Gvardinskas", "fname": "Mindaugas", "status": "0", "name": "Gvardinskas, Mindaugas"}, {"contribution": 0.5, "aip": 1, "country": ["DE"], "rel": "aut", "lname": "Tamošiūnaitė", "fname": "Minija", "status": "0", "id": "4C8B5181D7B34E850F690CE2CAC13C05", "name": "Tamošiūnaitė, Minija"}]}-
local.typeS-
item.grantfulltextopen-
item.fulltextWith Fulltext-
crisitem.author.deptMatematikos ir statistikos katedra-
crisitem.author.deptTaikomosios informatikos katedra-
Appears in Collections:Universiteto mokslo publikacijos / University Research Publications
Files in This Item:
marc.xml7.71 kBXMLView/Open

MARC21 XML metadata

Show simple item record
Export via OAI-PMH Interface in XML Formats
Export to Other Non-XML Formats


CORE Recommender

Page view(s)

76
checked on May 1, 2021

Download(s)

8
checked on May 1, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.