File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Article: Regularized orthogonal linear discriminant analysis
  • Basic View
  • Metadata View
  • XML View
TitleRegularized orthogonal linear discriminant analysis
 
AuthorsChing, WK1
Chu, D3
Liao, LZ2
Wang, X3
 
KeywordsData dimensionality reduction
Orthogonal linear discriminant analysis
QR factorization
Regularized orthogonal linear discriminant analysis
 
Issue Date2012
 
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pr
 
CitationPattern Recognition, 2012, v. 45 n. 7, p. 2719-2732 [How to Cite?]
DOI: http://dx.doi.org/10.1016/j.patcog.2012.01.007
 
AbstractIn this paper the regularized orthogonal linear discriminant analysis (ROLDA) is studied. The major issue of the regularized linear discriminant analysis is to choose an appropriate regularization parameter. In existing regularized linear discriminant analysis methods, they all select the best regularization parameter from a given parameter candidate set by using cross-validation for classification. An obvious limitation of such regularized linear discriminant analysis methods is that it is not clear how to choose an appropriate candidate set. Therefore, up to now, there is no concrete mathematical theory available in selecting an appropriate regularization parameter in practical applications of the regularized linear discriminant analysis. The present work is to fill this gap. Here we derive the mathematical relationship between orthogonal linear discriminant analysis and the regularized orthogonal linear discriminant analysis first, and then by means of this relationship we find a mathematical criterion for selecting the regularization parameter in ROLDA and consequently we develop a new regularized orthogonal linear discriminant analysis method, in which no candidate set of regularization parameter is needed. The effectiveness of our proposed regularized orthogonal linear discriminant analysis is illustrated by some real-world data sets. © 2012 Elsevier Ltd. All rights reserved.
 
ISSN0031-3203
2013 Impact Factor: 2.584
2013 SCImago Journal Rankings: 1.653
 
DOIhttp://dx.doi.org/10.1016/j.patcog.2012.01.007
 
ISI Accession Number IDWOS:000302451000022
Funding AgencyGrant Number
University of Hong Kong
Research Grant Council of Hong Kong
NUSR-146-000-140-112
GRF from Research Grant Council of Hong KongHKBU201409
HKBU201611
Funding Information:

This author was supported in part by grants from The University of Hong Kong, and the Research Grant Council of Hong Kong.

 
ReferencesReferences in Scopus
 
DC FieldValue
dc.contributor.authorChing, WK
 
dc.contributor.authorChu, D
 
dc.contributor.authorLiao, LZ
 
dc.contributor.authorWang, X
 
dc.date.accessioned2012-03-27T09:00:58Z
 
dc.date.available2012-03-27T09:00:58Z
 
dc.date.issued2012
 
dc.description.abstractIn this paper the regularized orthogonal linear discriminant analysis (ROLDA) is studied. The major issue of the regularized linear discriminant analysis is to choose an appropriate regularization parameter. In existing regularized linear discriminant analysis methods, they all select the best regularization parameter from a given parameter candidate set by using cross-validation for classification. An obvious limitation of such regularized linear discriminant analysis methods is that it is not clear how to choose an appropriate candidate set. Therefore, up to now, there is no concrete mathematical theory available in selecting an appropriate regularization parameter in practical applications of the regularized linear discriminant analysis. The present work is to fill this gap. Here we derive the mathematical relationship between orthogonal linear discriminant analysis and the regularized orthogonal linear discriminant analysis first, and then by means of this relationship we find a mathematical criterion for selecting the regularization parameter in ROLDA and consequently we develop a new regularized orthogonal linear discriminant analysis method, in which no candidate set of regularization parameter is needed. The effectiveness of our proposed regularized orthogonal linear discriminant analysis is illustrated by some real-world data sets. © 2012 Elsevier Ltd. All rights reserved.
 
dc.description.naturelink_to_subscribed_fulltext
 
dc.identifier.citationPattern Recognition, 2012, v. 45 n. 7, p. 2719-2732 [How to Cite?]
DOI: http://dx.doi.org/10.1016/j.patcog.2012.01.007
 
dc.identifier.citeulike10296103
 
dc.identifier.doihttp://dx.doi.org/10.1016/j.patcog.2012.01.007
 
dc.identifier.epage2732
 
dc.identifier.hkuros198996
 
dc.identifier.isiWOS:000302451000022
Funding AgencyGrant Number
University of Hong Kong
Research Grant Council of Hong Kong
NUSR-146-000-140-112
GRF from Research Grant Council of Hong KongHKBU201409
HKBU201611
Funding Information:

This author was supported in part by grants from The University of Hong Kong, and the Research Grant Council of Hong Kong.

 
dc.identifier.issn0031-3203
2013 Impact Factor: 2.584
2013 SCImago Journal Rankings: 1.653
 
dc.identifier.issue7
 
dc.identifier.scopuseid_2-s2.0-84862798516
 
dc.identifier.spage2719
 
dc.identifier.urihttp://hdl.handle.net/10722/145892
 
dc.identifier.volume45
 
dc.languageeng
 
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pr
 
dc.publisher.placeNetherlands
 
dc.relation.ispartofPattern Recognition
 
dc.relation.referencesReferences in Scopus
 
dc.subjectData dimensionality reduction
 
dc.subjectOrthogonal linear discriminant analysis
 
dc.subjectQR factorization
 
dc.subjectRegularized orthogonal linear discriminant analysis
 
dc.titleRegularized orthogonal linear discriminant analysis
 
dc.typeArticle
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Ching, WK</contributor.author>
<contributor.author>Chu, D</contributor.author>
<contributor.author>Liao, LZ</contributor.author>
<contributor.author>Wang, X</contributor.author>
<date.accessioned>2012-03-27T09:00:58Z</date.accessioned>
<date.available>2012-03-27T09:00:58Z</date.available>
<date.issued>2012</date.issued>
<identifier.citation>Pattern Recognition, 2012, v. 45 n. 7, p. 2719-2732</identifier.citation>
<identifier.issn>0031-3203</identifier.issn>
<identifier.uri>http://hdl.handle.net/10722/145892</identifier.uri>
<description.abstract>In this paper the regularized orthogonal linear discriminant analysis (ROLDA) is studied. The major issue of the regularized linear discriminant analysis is to choose an appropriate regularization parameter. In existing regularized linear discriminant analysis methods, they all select the best regularization parameter from a given parameter candidate set by using cross-validation for classification. An obvious limitation of such regularized linear discriminant analysis methods is that it is not clear how to choose an appropriate candidate set. Therefore, up to now, there is no concrete mathematical theory available in selecting an appropriate regularization parameter in practical applications of the regularized linear discriminant analysis. The present work is to fill this gap. Here we derive the mathematical relationship between orthogonal linear discriminant analysis and the regularized orthogonal linear discriminant analysis first, and then by means of this relationship we find a mathematical criterion for selecting the regularization parameter in ROLDA and consequently we develop a new regularized orthogonal linear discriminant analysis method, in which no candidate set of regularization parameter is needed. The effectiveness of our proposed regularized orthogonal linear discriminant analysis is illustrated by some real-world data sets. &#169; 2012 Elsevier Ltd. All rights reserved.</description.abstract>
<language>eng</language>
<publisher>Elsevier BV. The Journal&apos;s web site is located at http://www.elsevier.com/locate/pr</publisher>
<relation.ispartof>Pattern Recognition</relation.ispartof>
<subject>Data dimensionality reduction</subject>
<subject>Orthogonal linear discriminant analysis</subject>
<subject>QR factorization</subject>
<subject>Regularized orthogonal linear discriminant analysis</subject>
<title>Regularized orthogonal linear discriminant analysis</title>
<type>Article</type>
<description.nature>link_to_subscribed_fulltext</description.nature>
<identifier.doi>10.1016/j.patcog.2012.01.007</identifier.doi>
<identifier.scopus>eid_2-s2.0-84862798516</identifier.scopus>
<identifier.hkuros>198996</identifier.hkuros>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-84857995419&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
<identifier.volume>45</identifier.volume>
<identifier.issue>7</identifier.issue>
<identifier.spage>2719</identifier.spage>
<identifier.epage>2732</identifier.epage>
<identifier.isi>WOS:000302451000022</identifier.isi>
<publisher.place>Netherlands</publisher.place>
<identifier.citeulike>10296103</identifier.citeulike>
</item>
Author Affiliations
  1. The University of Hong Kong
  2. Hong Kong Baptist University
  3. National University of Singapore