Combining independent component analysis with support vector machines

Yan Genting; Ma Guangfu; Lv Jianting; Song Bin

Combining independent component analysis with support vector machines

Yan Genting^*
, Ma Guangfu
, Lv Jianting
, Song Bin

^*Corresponding author for this work

School of Astronautics

Harbin Institute of Technology

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

3 Scopus citations

Abstract

Recently, support vector machine (SVM) has become a popular tool in pattern recognition. In developing a successful SVM classifier, the first step is feature extraction. This paper proposes the application of independent component analysis (ICA) to SVM for feature extraction. In ICA, the original inputs are linearly transformed into features which are mutually statistically independent. By examining the Statlog heart disease data and satimage data, the experimental shows that SVM by feature extraction using ICA can perform better than that without feature extraction.

Original language	English
Title of host publication	1st International Symposium on Systems and Control in Aerospace and Astronautics
Pages	493-496
Number of pages	4
State	Published - 2006
Event	1st International Symposium on Systems and Control in Aerospace and Astronautics - Harbin, China Duration: 19 Jan 2006 → 21 Jan 2006

Publication series

Name	1st International Symposium on Systems and Control in Aerospace and Astronautics
Volume	2006

Conference

Conference	1st International Symposium on Systems and Control in Aerospace and Astronautics
Country/Territory	China
City	Harbin
Period	19/01/06 → 21/01/06

Cite this

@inproceedings{7c07c2191d964989b704adc7123e663a,

title = "Combining independent component analysis with support vector machines",

abstract = "Recently, support vector machine (SVM) has become a popular tool in pattern recognition. In developing a successful SVM classifier, the first step is feature extraction. This paper proposes the application of independent component analysis (ICA) to SVM for feature extraction. In ICA, the original inputs are linearly transformed into features which are mutually statistically independent. By examining the Statlog heart disease data and satimage data, the experimental shows that SVM by feature extraction using ICA can perform better than that without feature extraction.",

author = "Yan Genting and Ma Guangfu and Lv Jianting and Song Bin",

year = "2006",

language = "英语",

isbn = "0780393953",

series = "1st International Symposium on Systems and Control in Aerospace and Astronautics",

pages = "493--496",

booktitle = "1st International Symposium on Systems and Control in Aerospace and Astronautics",

note = "1st International Symposium on Systems and Control in Aerospace and Astronautics ; Conference date: 19-01-2006 Through 21-01-2006",

}

Genting, Y, Guangfu, M, Jianting, L & Bin, S 2006, Combining independent component analysis with support vector machines. in 1st International Symposium on Systems and Control in Aerospace and Astronautics., 1627671, 1st International Symposium on Systems and Control in Aerospace and Astronautics, vol. 2006, pp. 493-496, 1st International Symposium on Systems and Control in Aerospace and Astronautics, Harbin, China, 19/01/06.

Combining independent component analysis with support vector machines. / Genting, Yan; Guangfu, Ma; Jianting, Lv et al.
1st International Symposium on Systems and Control in Aerospace and Astronautics. 2006. p. 493-496 1627671 (1st International Symposium on Systems and Control in Aerospace and Astronautics; Vol. 2006).

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

TY - GEN

T1 - Combining independent component analysis with support vector machines

AU - Genting, Yan

AU - Guangfu, Ma

AU - Jianting, Lv

AU - Bin, Song

PY - 2006

Y1 - 2006

N2 - Recently, support vector machine (SVM) has become a popular tool in pattern recognition. In developing a successful SVM classifier, the first step is feature extraction. This paper proposes the application of independent component analysis (ICA) to SVM for feature extraction. In ICA, the original inputs are linearly transformed into features which are mutually statistically independent. By examining the Statlog heart disease data and satimage data, the experimental shows that SVM by feature extraction using ICA can perform better than that without feature extraction.

AB - Recently, support vector machine (SVM) has become a popular tool in pattern recognition. In developing a successful SVM classifier, the first step is feature extraction. This paper proposes the application of independent component analysis (ICA) to SVM for feature extraction. In ICA, the original inputs are linearly transformed into features which are mutually statistically independent. By examining the Statlog heart disease data and satimage data, the experimental shows that SVM by feature extraction using ICA can perform better than that without feature extraction.

UR - https://www.scopus.com/pages/publications/33750944985

M3 - 会议稿件

AN - SCOPUS:33750944985

SN - 0780393953

SN - 9780780393950

T3 - 1st International Symposium on Systems and Control in Aerospace and Astronautics

SP - 493

EP - 496

BT - 1st International Symposium on Systems and Control in Aerospace and Astronautics

T2 - 1st International Symposium on Systems and Control in Aerospace and Astronautics

Y2 - 19 January 2006 through 21 January 2006

ER -

Combining independent component analysis with support vector machines

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this