Kernel pooled local subspaces for classification

Peng Zhang, Jing Peng, Carlotta Domeniconi

Research output: Contribution to journalArticleResearchpeer-review

9 Citations (Scopus)

Abstract

We investigate the use of subspace analysis methods for learning low-dimensional representations for classification. We propose a kernel-pooled local discriminant subspace method and compare it against competing techniques: kernel principal component analysis (KPCA) and generalized discriminant analysis (GDA) in classification problems. We evaluate the classification performance of the nearest-neighbor rule with each subspace representation. The experimental results using several data sets demonstrate the effectiveness and performance superiority of the kernel-pooled subspace method over competing methods such as KPCA and GDA in some classification problems.

Original languageEnglish
Pages (from-to)489-502
Number of pages14
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume35
Issue number3
DOIs
StatePublished - 1 Jun 2005

Fingerprint

Discriminant Analysis
Discriminant analysis
Principal Component Analysis
Principal component analysis
Learning
Datasets

Keywords

  • Classification
  • Kernel machines
  • Nearest neighbors
  • Subspace analysis

Cite this

@article{1c71f08117624ed8a9c26195a198c1e0,
title = "Kernel pooled local subspaces for classification",
abstract = "We investigate the use of subspace analysis methods for learning low-dimensional representations for classification. We propose a kernel-pooled local discriminant subspace method and compare it against competing techniques: kernel principal component analysis (KPCA) and generalized discriminant analysis (GDA) in classification problems. We evaluate the classification performance of the nearest-neighbor rule with each subspace representation. The experimental results using several data sets demonstrate the effectiveness and performance superiority of the kernel-pooled subspace method over competing methods such as KPCA and GDA in some classification problems.",
keywords = "Classification, Kernel machines, Nearest neighbors, Subspace analysis",
author = "Peng Zhang and Jing Peng and Carlotta Domeniconi",
year = "2005",
month = "6",
day = "1",
doi = "10.1109/TSMCB.2005.846641",
language = "English",
volume = "35",
pages = "489--502",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",
issn = "1083-4419",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

Kernel pooled local subspaces for classification. / Zhang, Peng; Peng, Jing; Domeniconi, Carlotta.

In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 35, No. 3, 01.06.2005, p. 489-502.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Kernel pooled local subspaces for classification

AU - Zhang, Peng

AU - Peng, Jing

AU - Domeniconi, Carlotta

PY - 2005/6/1

Y1 - 2005/6/1

N2 - We investigate the use of subspace analysis methods for learning low-dimensional representations for classification. We propose a kernel-pooled local discriminant subspace method and compare it against competing techniques: kernel principal component analysis (KPCA) and generalized discriminant analysis (GDA) in classification problems. We evaluate the classification performance of the nearest-neighbor rule with each subspace representation. The experimental results using several data sets demonstrate the effectiveness and performance superiority of the kernel-pooled subspace method over competing methods such as KPCA and GDA in some classification problems.

AB - We investigate the use of subspace analysis methods for learning low-dimensional representations for classification. We propose a kernel-pooled local discriminant subspace method and compare it against competing techniques: kernel principal component analysis (KPCA) and generalized discriminant analysis (GDA) in classification problems. We evaluate the classification performance of the nearest-neighbor rule with each subspace representation. The experimental results using several data sets demonstrate the effectiveness and performance superiority of the kernel-pooled subspace method over competing methods such as KPCA and GDA in some classification problems.

KW - Classification

KW - Kernel machines

KW - Nearest neighbors

KW - Subspace analysis

UR - http://www.scopus.com/inward/record.url?scp=20444381620&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2005.846641

DO - 10.1109/TSMCB.2005.846641

M3 - Article

VL - 35

SP - 489

EP - 502

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

SN - 1083-4419

IS - 3

ER -