DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ahn, Jeongyoun | ko |
dc.contributor.author | Marron, J. S. | ko |
dc.date.accessioned | 2021-06-02T02:50:38Z | - |
dc.date.available | 2021-06-02T02:50:38Z | - |
dc.date.created | 2021-06-02 | - |
dc.date.created | 2021-06-02 | - |
dc.date.issued | 2010-03 | - |
dc.identifier.citation | BIOMETRIKA, v.97, no.1, pp.254 - 259 | - |
dc.identifier.issn | 0006-3444 | - |
dc.identifier.uri | http://hdl.handle.net/10203/285433 | - |
dc.description.abstract | We study a discriminant direction vector that generally exists only in high-dimension, low sample size settings. Projections of data onto this direction vector take on only two distinct values, one for each class. There exist infinitely many such directions in the subspace generated by the data; but the maximal data piling vector has the longest distance between the projections. This paper investigates mathematical properties and classification performance of this discrimination method. | - |
dc.language | English | - |
dc.publisher | OXFORD UNIV PRESS | - |
dc.title | The maximal data piling direction for discrimination | - |
dc.type | Article | - |
dc.identifier.wosid | 000274778000022 | - |
dc.identifier.scopusid | 2-s2.0-77249090732 | - |
dc.type.rims | ART | - |
dc.citation.volume | 97 | - |
dc.citation.issue | 1 | - |
dc.citation.beginningpage | 254 | - |
dc.citation.endingpage | 259 | - |
dc.citation.publicationname | BIOMETRIKA | - |
dc.identifier.doi | 10.1093/biomet/asp084 | - |
dc.contributor.localauthor | Ahn, Jeongyoun | - |
dc.contributor.nonIdAuthor | Marron, J. S. | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Classification | - |
dc.subject.keywordAuthor | Fisher&apos | - |
dc.subject.keywordAuthor | s linear discrimination | - |
dc.subject.keywordAuthor | High dimension | - |
dc.subject.keywordAuthor | low sample size | - |
dc.subject.keywordAuthor | Maximal data piling | - |
dc.subject.keywordAuthor | Support vector machine | - |
dc.subject.keywordPlus | GEOMETRIC REPRESENTATION | - |
dc.subject.keywordPlus | HIGH-DIMENSION | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.