Kernel nonparametric discriminant analysis

Xueliang Zhan; Bo Ma

doi:10.1109/ICECENG.2011.6057678

Kernel nonparametric discriminant analysis

Xueliang Zhan^*, Bo Ma

^*Corresponding author for this work

School of Computer Science and Technology

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

Abstract

In this paper, a kernelized version of nonparametric discriminant analysis is proposed that we name KNDA. The main idea is to first map the original data into another high-dimensional space, and then to perform nonparametric discriminant analysis in the high dimensional space. Nonparametric discriminant analysis can relax the Gaussian assumption required for the classical linear discriminant analysis, and Kernel trick can further improve the separation ability. A group of tests on several UCI standard benchmarks have been carried out that prove our proposed method is very promising.

Original language	English
Title of host publication	2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings
Pages	4544-4547
Number of pages	4
DOIs	https://doi.org/10.1109/ICECENG.2011.6057678
Publication status	Published - 2011
Event	2nd Annual Conference on Electrical and Control Engineering, ICECE 2011 - Yichang, China Duration: 16 Sept 2011 → 18 Sept 2011

Publication series

Name	2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings

Conference

Conference	2nd Annual Conference on Electrical and Control Engineering, ICECE 2011
Country/Territory	China
City	Yichang
Period	16/09/11 → 18/09/11

Keywords

Kernel Linear Discriminant Analysis (KLDA)
Kernel Nonparametric Discriminant Analysis (KNDA)
Linear Discriminant Analysis (LDA)
Nonparametric discriminant analysis

Access to Document

10.1109/ICECENG.2011.6057678

Cite this

@inproceedings{f308d68b74ef4e87a5dfec6b6a734785,

title = "Kernel nonparametric discriminant analysis",

abstract = "In this paper, a kernelized version of nonparametric discriminant analysis is proposed that we name KNDA. The main idea is to first map the original data into another high-dimensional space, and then to perform nonparametric discriminant analysis in the high dimensional space. Nonparametric discriminant analysis can relax the Gaussian assumption required for the classical linear discriminant analysis, and Kernel trick can further improve the separation ability. A group of tests on several UCI standard benchmarks have been carried out that prove our proposed method is very promising.",

keywords = "Kernel Linear Discriminant Analysis (KLDA), Kernel Nonparametric Discriminant Analysis (KNDA), Linear Discriminant Analysis (LDA), Nonparametric discriminant analysis",

author = "Xueliang Zhan and Bo Ma",

year = "2011",

doi = "10.1109/ICECENG.2011.6057678",

language = "English",

isbn = "9781424481637",

series = "2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings",

pages = "4544--4547",

booktitle = "2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings",

note = "2nd Annual Conference on Electrical and Control Engineering, ICECE 2011 ; Conference date: 16-09-2011 Through 18-09-2011",

}

Zhan, X & Ma, B 2011, Kernel nonparametric discriminant analysis. in 2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings., 6057678, 2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings, pp. 4544-4547, 2nd Annual Conference on Electrical and Control Engineering, ICECE 2011, Yichang, China, 16/09/11. https://doi.org/10.1109/ICECENG.2011.6057678

Kernel nonparametric discriminant analysis. / Zhan, Xueliang; Ma, Bo.
2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings. 2011. p. 4544-4547 6057678 (2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Kernel nonparametric discriminant analysis

AU - Zhan, Xueliang

AU - Ma, Bo

PY - 2011

Y1 - 2011

N2 - In this paper, a kernelized version of nonparametric discriminant analysis is proposed that we name KNDA. The main idea is to first map the original data into another high-dimensional space, and then to perform nonparametric discriminant analysis in the high dimensional space. Nonparametric discriminant analysis can relax the Gaussian assumption required for the classical linear discriminant analysis, and Kernel trick can further improve the separation ability. A group of tests on several UCI standard benchmarks have been carried out that prove our proposed method is very promising.

AB - In this paper, a kernelized version of nonparametric discriminant analysis is proposed that we name KNDA. The main idea is to first map the original data into another high-dimensional space, and then to perform nonparametric discriminant analysis in the high dimensional space. Nonparametric discriminant analysis can relax the Gaussian assumption required for the classical linear discriminant analysis, and Kernel trick can further improve the separation ability. A group of tests on several UCI standard benchmarks have been carried out that prove our proposed method is very promising.

KW - Kernel Linear Discriminant Analysis (KLDA)

KW - Kernel Nonparametric Discriminant Analysis (KNDA)

KW - Linear Discriminant Analysis (LDA)

KW - Nonparametric discriminant analysis

UR - http://www.scopus.com/inward/record.url?scp=80955172371&partnerID=8YFLogxK

U2 - 10.1109/ICECENG.2011.6057678

DO - 10.1109/ICECENG.2011.6057678

M3 - Conference contribution

AN - SCOPUS:80955172371

SN - 9781424481637

T3 - 2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings

SP - 4544

EP - 4547

BT - 2011 International Conference on Electrical and Control Engineering, ICECE 2011 - Proceedings

T2 - 2nd Annual Conference on Electrical and Control Engineering, ICECE 2011

Y2 - 16 September 2011 through 18 September 2011

ER -

Kernel nonparametric discriminant analysis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this