A new support vector machine for microarray classification and adaptive gene selection

Juntao Li; Yingmin Jia; Junping Du; Fashan Yu

doi:10.1109/ACC.2009.5160235

A new support vector machine for microarray classification and adaptive gene selection

Juntao Li^*
, Yingmin Jia
, Junping Du
, Fashan Yu

^*Corresponding author for this work

School of Automation Science and Electrical Engineering

Beihang University
Beijing University of Posts and Telecommunications
Henan Polytechnic University

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

8 Scopus citations

Abstract

This paper presents a new support vector machine for simultaneous gene selection and microarray classification. By introducing the adaptive elastic net penalty which is a convex combination of weighted 1-norm penalty and weighted 2-norm penalty, the proposed support vector machine can encourage an adaptive grouping effect and reduce the shrinkage bias for the large coefficients. According to a reasonable correlation between the two regularization parameters, the optimal coefficient paths are shown to be piecewise linear and the corresponding solving algorithm is developed. Experiments are performed on leukaemia data that verify the research results.

Original language	English
Title of host publication	2009 American Control Conference, ACC 2009
Pages	5410-5415
Number of pages	6
DOIs	https://doi.org/10.1109/ACC.2009.5160235
State	Published - 2009
Event	2009 American Control Conference, ACC 2009 - St. Louis, MO, United States Duration: 10 Jun 2009 → 12 Jun 2009

Publication series

Name	Proceedings of the American Control Conference
ISSN (Print)	0743-1619

Conference

Conference	2009 American Control Conference, ACC 2009
Country/Territory	United States
City	St. Louis, MO
Period	10/06/09 → 12/06/09

Keywords

Gene selection
Grouping effect
Microarray classification
Solution path
Support vector machine (SVM)

Access to Document

10.1109/ACC.2009.5160235

Cite this

@inproceedings{3050517bd817435db7ac150e46a2224e,

title = "A new support vector machine for microarray classification and adaptive gene selection",

abstract = "This paper presents a new support vector machine for simultaneous gene selection and microarray classification. By introducing the adaptive elastic net penalty which is a convex combination of weighted 1-norm penalty and weighted 2-norm penalty, the proposed support vector machine can encourage an adaptive grouping effect and reduce the shrinkage bias for the large coefficients. According to a reasonable correlation between the two regularization parameters, the optimal coefficient paths are shown to be piecewise linear and the corresponding solving algorithm is developed. Experiments are performed on leukaemia data that verify the research results.",

keywords = "Gene selection, Grouping effect, Microarray classification, Solution path, Support vector machine (SVM)",

author = "Juntao Li and Yingmin Jia and Junping Du and Fashan Yu",

year = "2009",

doi = "10.1109/ACC.2009.5160235",

language = "英语",

isbn = "9781424445240",

series = "Proceedings of the American Control Conference",

pages = "5410--5415",

booktitle = "2009 American Control Conference, ACC 2009",

note = "2009 American Control Conference, ACC 2009 ; Conference date: 10-06-2009 Through 12-06-2009",

}

TY - GEN

T1 - A new support vector machine for microarray classification and adaptive gene selection

AU - Li, Juntao

AU - Jia, Yingmin

AU - Du, Junping

AU - Yu, Fashan

PY - 2009

Y1 - 2009

N2 - This paper presents a new support vector machine for simultaneous gene selection and microarray classification. By introducing the adaptive elastic net penalty which is a convex combination of weighted 1-norm penalty and weighted 2-norm penalty, the proposed support vector machine can encourage an adaptive grouping effect and reduce the shrinkage bias for the large coefficients. According to a reasonable correlation between the two regularization parameters, the optimal coefficient paths are shown to be piecewise linear and the corresponding solving algorithm is developed. Experiments are performed on leukaemia data that verify the research results.

AB - This paper presents a new support vector machine for simultaneous gene selection and microarray classification. By introducing the adaptive elastic net penalty which is a convex combination of weighted 1-norm penalty and weighted 2-norm penalty, the proposed support vector machine can encourage an adaptive grouping effect and reduce the shrinkage bias for the large coefficients. According to a reasonable correlation between the two regularization parameters, the optimal coefficient paths are shown to be piecewise linear and the corresponding solving algorithm is developed. Experiments are performed on leukaemia data that verify the research results.

KW - Gene selection

KW - Grouping effect

KW - Microarray classification

KW - Solution path

KW - Support vector machine (SVM)

UR - https://www.scopus.com/pages/publications/70449631403

U2 - 10.1109/ACC.2009.5160235

DO - 10.1109/ACC.2009.5160235

M3 - 会议稿件

AN - SCOPUS:70449631403

SN - 9781424445240

T3 - Proceedings of the American Control Conference

SP - 5410

EP - 5415

BT - 2009 American Control Conference, ACC 2009

T2 - 2009 American Control Conference, ACC 2009

Y2 - 10 June 2009 through 12 June 2009

ER -

A new support vector machine for microarray classification and adaptive gene selection

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this