File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Sequential combination of weighted and nonparametric bagging for classification

TitleSequential combination of weighted and nonparametric bagging for classification
Authors
KeywordsBayes rule
Classification
Hard thresholding
Nearest neighbour
Sequential bagging
Issue Date2014
PublisherBiometrika Trust. The Journal's web site is located at http://biomet.oxfordjournals.org/
Citation
Biometrika, 2014, v. 101, p. 491-498 How to Cite?
AbstractWe propose a simple sequential procedure for bagged classification, which modifies nonparametric bagging by randomizing class labels of resampled data points. The random labelling feature of the procedure also enables us to undertake unsupervised classification with the benefit of supervised learning. Theoretical properties are given for the nearest neighbour classifier in the case of supervised learning and a hard-thresholding indicator in the case of unsupervised learning, showing that sequential bagging accelerates convergence of the bagged predictor to the Bayes rule. Simulation results are provided in support of the proposed method.
Persistent Identifierhttp://hdl.handle.net/10722/200911
ISSN
2023 Impact Factor: 2.4
2023 SCImago Journal Rankings: 3.358
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorSoleymani, Men_US
dc.contributor.authorLee, SMSen_US
dc.date.accessioned2014-08-21T07:07:07Z-
dc.date.available2014-08-21T07:07:07Z-
dc.date.issued2014en_US
dc.identifier.citationBiometrika, 2014, v. 101, p. 491-498en_US
dc.identifier.issn0006-3444-
dc.identifier.urihttp://hdl.handle.net/10722/200911-
dc.description.abstractWe propose a simple sequential procedure for bagged classification, which modifies nonparametric bagging by randomizing class labels of resampled data points. The random labelling feature of the procedure also enables us to undertake unsupervised classification with the benefit of supervised learning. Theoretical properties are given for the nearest neighbour classifier in the case of supervised learning and a hard-thresholding indicator in the case of unsupervised learning, showing that sequential bagging accelerates convergence of the bagged predictor to the Bayes rule. Simulation results are provided in support of the proposed method.en_US
dc.languageengen_US
dc.publisherBiometrika Trust. The Journal's web site is located at http://biomet.oxfordjournals.org/en_US
dc.relation.ispartofBiometrikaen_US
dc.subjectBayes rule-
dc.subjectClassification-
dc.subjectHard thresholding-
dc.subjectNearest neighbour-
dc.subjectSequential bagging-
dc.titleSequential combination of weighted and nonparametric bagging for classificationen_US
dc.typeArticleen_US
dc.identifier.emailSoleymani, M: mehdi@hku.hken_US
dc.identifier.emailLee, SMS: smslee@hku.hken_US
dc.identifier.authorityLee, SMS=rp00726en_US
dc.identifier.doi10.1093/biomet/ast068en_US
dc.identifier.scopuseid_2-s2.0-84901465358-
dc.identifier.hkuros231942en_US
dc.identifier.volume101en_US
dc.identifier.spage491en_US
dc.identifier.epage498en_US
dc.identifier.eissn1464-3510-
dc.identifier.isiWOS:000337042700018-
dc.publisher.placeUKen_US
dc.identifier.issnl0006-3444-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats