File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Efficient Parameter Selection for Support Vector Machines

TitleEfficient Parameter Selection for Support Vector Machines
Authors
KeywordsPercentiles
grid search
classification
radial basis function (RBF) kernel
hyperparameter
Issue Date2019
PublisherTaylor & Francis Ltd. The Journal's web site is located at http://www.tandf.co.uk/journals/titles/17517575.asp
Citation
Enterprise Information Systems, 2019, v. 13 n. 6, p. 916-932 How to Cite?
AbstractThe support vector machines (SVM) is a popular classification method. Many users may not well tune hyperparameters because this step is time-consuming. However, the performance of SVM relies on the values of hyperparameters. To get around the problem, users may resort to anecdotal methods or default values set by software developers, but these methods may compromise the performance of classification accuracy. We investigate the theory that justifies P-SVM for tuning (γ,C) P-SVM significantly improved accuracy for classifying the business intelligence data. Experiments of simulation and real datasets show that P-SVM reducescomputational time substantially without much loss in accuracy.
Persistent Identifierhttp://hdl.handle.net/10722/278969
ISSN
2017 Impact Factor: 1.683
2015 SCImago Journal Rankings: 1.287

 

DC FieldValueLanguage
dc.contributor.authorHuang, H-H-
dc.contributor.authorWang, Z-
dc.contributor.authorChung, W-
dc.date.accessioned2019-10-21T02:17:15Z-
dc.date.available2019-10-21T02:17:15Z-
dc.date.issued2019-
dc.identifier.citationEnterprise Information Systems, 2019, v. 13 n. 6, p. 916-932-
dc.identifier.issn1751-7575-
dc.identifier.urihttp://hdl.handle.net/10722/278969-
dc.description.abstractThe support vector machines (SVM) is a popular classification method. Many users may not well tune hyperparameters because this step is time-consuming. However, the performance of SVM relies on the values of hyperparameters. To get around the problem, users may resort to anecdotal methods or default values set by software developers, but these methods may compromise the performance of classification accuracy. We investigate the theory that justifies P-SVM for tuning (γ,C) P-SVM significantly improved accuracy for classifying the business intelligence data. Experiments of simulation and real datasets show that P-SVM reducescomputational time substantially without much loss in accuracy.-
dc.languageeng-
dc.publisherTaylor & Francis Ltd. The Journal's web site is located at http://www.tandf.co.uk/journals/titles/17517575.asp-
dc.relation.ispartofEnterprise Information Systems-
dc.rightsAOM/Preprint Before Accepted: his article has been accepted for publication in [JOURNAL TITLE], published by Taylor & Francis. AOM/Preprint After Accepted: This is an [original manuscript / preprint] of an article published by Taylor & Francis in [JOURNAL TITLE] on [date of publication], available online: http://www.tandfonline.com/[Article DOI]. Accepted Manuscript (AM) i.e. Postprint This is an Accepted Manuscript of an article published by Taylor & Francis in [JOURNAL TITLE] on [date of publication], available online: http://www.tandfonline.com/[Article DOI].-
dc.subjectPercentiles-
dc.subjectgrid search-
dc.subjectclassification-
dc.subjectradial basis function (RBF) kernel-
dc.subjecthyperparameter-
dc.titleEfficient Parameter Selection for Support Vector Machines-
dc.typeArticle-
dc.identifier.emailChung, W: wchun@hku.hk-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1080/17517575.2019.1592233-
dc.identifier.scopuseid_2-s2.0-85064172144-
dc.identifier.hkuros307639-
dc.identifier.volume13-
dc.identifier.issue6-
dc.identifier.spage916-
dc.identifier.epage932-
dc.publisher.placeUnited Kingdom-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats