On feature selection with principal component analysis for one-class SVM

In this short note, we demonstrate the use of principal components analysis (PCA) for one-class support vector machine (one-class SVM) as a dimension reduction tool. However, unlike almost all other usage of PCA which extracts the eigenvectors associated with top eigenvalues as the projection direct...

Full description

Saved in:

Bibliographic Details
Main Author:	Lian, Heng
Other Authors:	School of Physical and Mathematical Sciences
Format:	Article
Language:	English
Published:	2013
Subjects:	DRNTU::Science::Mathematics
Online Access:	https://hdl.handle.net/10356/105603 http://hdl.handle.net/10220/17154 http://dx.doi.org/10.1016/j.patrec.2012.01.019
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-105603
record_format	dspace
spelling	sg-ntu-dr.10356-1056032019-12-06T21:54:18Z On feature selection with principal component analysis for one-class SVM Lian, Heng School of Physical and Mathematical Sciences DRNTU::Science::Mathematics In this short note, we demonstrate the use of principal components analysis (PCA) for one-class support vector machine (one-class SVM) as a dimension reduction tool. However, unlike almost all other usage of PCA which extracts the eigenvectors associated with top eigenvalues as the projection directions, here it is the eigenvectors associated with small eigenvalues that are of interests, and in particular the null of the eigenspace, since the null space in fact characterizes the common features of the training samples. Image retrieval examples are used to illustrate the effectiveness of dimension reduction. 2013-10-31T07:43:56Z 2019-12-06T21:54:18Z 2013-10-31T07:43:56Z 2019-12-06T21:54:18Z 2012 2012 Journal Article Lian, H. (2012). On feature selection with principal component analysis for one-class SVM. Pattern recognition letters, 33(9), 1027-1031. 0167-8655 https://hdl.handle.net/10356/105603 http://hdl.handle.net/10220/17154 http://dx.doi.org/10.1016/j.patrec.2012.01.019 en Pattern recognition letters
institution	Nanyang Technological University
building	NTU Library
country	Singapore
collection	DR-NTU
language	English
topic	DRNTU::Science::Mathematics
spellingShingle	DRNTU::Science::Mathematics Lian, Heng On feature selection with principal component analysis for one-class SVM
description	In this short note, we demonstrate the use of principal components analysis (PCA) for one-class support vector machine (one-class SVM) as a dimension reduction tool. However, unlike almost all other usage of PCA which extracts the eigenvectors associated with top eigenvalues as the projection directions, here it is the eigenvectors associated with small eigenvalues that are of interests, and in particular the null of the eigenspace, since the null space in fact characterizes the common features of the training samples. Image retrieval examples are used to illustrate the effectiveness of dimension reduction.
author2	School of Physical and Mathematical Sciences
author_facet	School of Physical and Mathematical Sciences Lian, Heng
format	Article
author	Lian, Heng
author_sort	Lian, Heng
title	On feature selection with principal component analysis for one-class SVM
title_short	On feature selection with principal component analysis for one-class SVM
title_full	On feature selection with principal component analysis for one-class SVM
title_fullStr	On feature selection with principal component analysis for one-class SVM
title_full_unstemmed	On feature selection with principal component analysis for one-class SVM
title_sort	on feature selection with principal component analysis for one-class svm
publishDate	2013
url	https://hdl.handle.net/10356/105603 http://hdl.handle.net/10220/17154 http://dx.doi.org/10.1016/j.patrec.2012.01.019
_version_	1681043574470213632

On feature selection with principal component analysis for one-class SVM

Similar Items