DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, K | ko |
dc.contributor.author | Kim, DW | ko |
dc.contributor.author | Lee, Doheon | ko |
dc.contributor.author | Lee, Kwang-Hyung | ko |
dc.date.accessioned | 2013-03-06T21:08:29Z | - |
dc.date.available | 2013-03-06T21:08:29Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2005-10 | - |
dc.identifier.citation | PATTERN RECOGNITION, v.38, pp.1768 - 1771 | - |
dc.identifier.issn | 0031-3203 | - |
dc.identifier.uri | http://hdl.handle.net/10203/88466 | - |
dc.description.abstract | We propose a new support vector data description (SVDD) incorporating the local density of a training data set by introducing a local density degree for each data point. By using a density-induced distance measure based on the degree, we reformulate a conventional SVDD. Experiments with various real data sets show that the proposed method more accurately describes training data sets than the conventional SVDD in all tested cases. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved. | - |
dc.language | English | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.title | Improving support vector data description using local density degree | - |
dc.type | Article | - |
dc.identifier.wosid | 000231291900024 | - |
dc.identifier.scopusid | 2-s2.0-22844442781 | - |
dc.type.rims | ART | - |
dc.citation.volume | 38 | - |
dc.citation.beginningpage | 1768 | - |
dc.citation.endingpage | 1771 | - |
dc.citation.publicationname | PATTERN RECOGNITION | - |
dc.identifier.doi | 10.1016/j.patcog.2005.03.020 | - |
dc.contributor.localauthor | Lee, Doheon | - |
dc.contributor.localauthor | Lee, Kwang-Hyung | - |
dc.contributor.nonIdAuthor | Lee, K | - |
dc.contributor.nonIdAuthor | Kim, DW | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | D-SVDD | - |
dc.subject.keywordAuthor | support vector data description | - |
dc.subject.keywordAuthor | one-class classification | - |
dc.subject.keywordAuthor | data domain description | - |
dc.subject.keywordAuthor | outlier detection | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.