A muti-SVMs design for cancer diagnosis using DNA microarray data

Jinglin Yang; Yongli Xu; Hanxiong Li

doi:10.1109/WCICA.2008.4593271

A muti-SVMs design for cancer diagnosis using DNA microarray data

Jinglin Yang, Yongli Xu, Hanxiong Li

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

Abstract

Microarray data of gene expression pattern provide useful information for the diagnosis of certain diseases. However the dimension of microarray data is always very high and the volume of samples is small. How to select informative genes remains a challenge. In this research, multiple support vector machine (MSVM) were designed for disease diagnosis. Each SVM was trained using a few gene features. The importance of genes was evaluated by the structure error loss. SVMs with most important genes were linearly combined to form the disease classifier. The algorithm was applied to an artificial dataset. The human acute leukemia dataset was used as a test case. © 2008 IEEE.

Original language	English
Title of host publication	Proceedings of the World Congress on Intelligent Control and Automation (WCICA)
Pages	2241-2246
DOIs	https://doi.org/10.1109/WCICA.2008.4593271
Publication status	Published - 2008
Event	7th World Congress on Intelligent Control and Automation, WCICA'08 - Chongqing, China Duration: 25 Jun 2008 → 27 Jun 2008

Conference

Conference	7th World Congress on Intelligent Control and Automation, WCICA'08
Country/Territory	China
City	Chongqing
Period	25/06/08 → 27/06/08

Research Keywords

Classification
Feature selection
Gene classification
SVM

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access Output

10.1109/WCICA.2008.4593271

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{f0e7727feeff42c18d1efb7adf39efc9,

title = "A muti-SVMs design for cancer diagnosis using DNA microarray data",

abstract = "Microarray data of gene expression pattern provide useful information for the diagnosis of certain diseases. However the dimension of microarray data is always very high and the volume of samples is small. How to select informative genes remains a challenge. In this research, multiple support vector machine (MSVM) were designed for disease diagnosis. Each SVM was trained using a few gene features. The importance of genes was evaluated by the structure error loss. SVMs with most important genes were linearly combined to form the disease classifier. The algorithm was applied to an artificial dataset. The human acute leukemia dataset was used as a test case. {\textcopyright} 2008 IEEE.",

keywords = "Classification, Feature selection, Gene classification, SVM",

author = "Jinglin Yang and Yongli Xu and Hanxiong Li",

year = "2008",

doi = "10.1109/WCICA.2008.4593271",

language = "English",

isbn = "9781424421145",

pages = "2241--2246",

booktitle = "Proceedings of the World Congress on Intelligent Control and Automation (WCICA)",

note = "7th World Congress on Intelligent Control and Automation, WCICA'08 ; Conference date: 25-06-2008 Through 27-06-2008",

}

A muti-SVMs design for cancer diagnosis using DNA microarray data. / Yang, Jinglin; Xu, Yongli; Li, Hanxiong.
Proceedings of the World Congress on Intelligent Control and Automation (WCICA). 2008. p. 2241-2246 4593271.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A muti-SVMs design for cancer diagnosis using DNA microarray data

AU - Yang, Jinglin

AU - Xu, Yongli

AU - Li, Hanxiong

PY - 2008

Y1 - 2008

N2 - Microarray data of gene expression pattern provide useful information for the diagnosis of certain diseases. However the dimension of microarray data is always very high and the volume of samples is small. How to select informative genes remains a challenge. In this research, multiple support vector machine (MSVM) were designed for disease diagnosis. Each SVM was trained using a few gene features. The importance of genes was evaluated by the structure error loss. SVMs with most important genes were linearly combined to form the disease classifier. The algorithm was applied to an artificial dataset. The human acute leukemia dataset was used as a test case. © 2008 IEEE.

AB - Microarray data of gene expression pattern provide useful information for the diagnosis of certain diseases. However the dimension of microarray data is always very high and the volume of samples is small. How to select informative genes remains a challenge. In this research, multiple support vector machine (MSVM) were designed for disease diagnosis. Each SVM was trained using a few gene features. The importance of genes was evaluated by the structure error loss. SVMs with most important genes were linearly combined to form the disease classifier. The algorithm was applied to an artificial dataset. The human acute leukemia dataset was used as a test case. © 2008 IEEE.

KW - Classification

KW - Feature selection

KW - Gene classification

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=52149106469&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-52149106469&origin=recordpage

U2 - 10.1109/WCICA.2008.4593271

DO - 10.1109/WCICA.2008.4593271

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781424421145

SP - 2241

EP - 2246

BT - Proceedings of the World Congress on Intelligent Control and Automation (WCICA)

T2 - 7th World Congress on Intelligent Control and Automation, WCICA'08

Y2 - 25 June 2008 through 27 June 2008

ER -

A muti-SVMs design for cancer diagnosis using DNA microarray data

Abstract

Conference

Research Keywords

UN SDGs

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this