A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue
Chen, ZY; Li, JP; Wei, LW
2007
Source PublicationARTIFICIAL INTELLIGENCE IN MEDICINE
ISSN0933-3657
Volume41Issue:2Pages:15,161-175
AbstractObjective: Recently, gene expression profiling using microarray techniques has been shown as a promising tool to improve the diagnosis and treatment of cancer. Gene expression data contain high level. of noise and the overwhelming number of genes relative to the number of available samples. It brings out a great challenge for machine learning and statistic techniques. Support vector machine (SVM) has been successfully used to classify gene expression data of cancer tissue. In the medical field, it is crucial to deliver the user a transparent decision process. How to explain the computed solutions and present the extracted knowledge becomes a main obstacle for SVM. Material and methods: A multiple kernel support vector machine (MK-SVM) scheme, consisting of feature selection, rule extraction and prediction modeling is proposed to improve the explanation capacity of SVM. In this scheme, we show that the feature selection problem can be translated into an ordinary multiple parameters learning problem. And a shrinkage approach: 1-norm based linear programming is proposed to obtain the sparse parameters and the corresponding selected features. We propose a novel rule extraction approach using the information provided by the separating hyperplane and support vectors to improve the generalization capacity and comprehensibility of rules and reduce the computational complexity. Results and conclusion: Two public gene expression datasets: leukemia dataset and colon tumor dataset are used to demonstrate the performance of this approach. Using the small number of selected genes, MK-SVM achieves encouraging classification accuracy: more than 90% for both two datasets. Moreover, very simple rules with linguist labels are extracted. The rule sets have high diagnostic power because of their good classification performance. (C) 2007 Elsevier B.V. All rights reserved.
KeywordMultiple Kernel Learning Support Vector Machine Feature Selection Rule Extraction Gene Expression Data
Subject AreaComputer Science ; Artificial Intelligence ; Biomedical ; Engineering ; Medical Informatics
Indexed BySCI
Language英语
WOS IDWOS:000250714000008
Citation statistics
Cited Times:65[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.casisd.cn/handle/190111/4837
Collection中国科学院科技政策与管理科学研究所(1985年6月-2015年12月)
Recommended Citation
GB/T 7714
Chen, ZY,Li, JP,Wei, LW. A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue[J]. ARTIFICIAL INTELLIGENCE IN MEDICINE,2007,41(2):15,161-175.
APA Chen, ZY,Li, JP,&Wei, LW.(2007).A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue.ARTIFICIAL INTELLIGENCE IN MEDICINE,41(2),15,161-175.
MLA Chen, ZY,et al."A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue".ARTIFICIAL INTELLIGENCE IN MEDICINE 41.2(2007):15,161-175.
Files in This Item:
File Name/Size DocType Version Access License
A multiple kernel su(250KB) 开放获取--View Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen, ZY]'s Articles
[Li, JP]'s Articles
[Wei, LW]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, ZY]'s Articles
[Li, JP]'s Articles
[Wei, LW]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, ZY]'s Articles
[Li, JP]'s Articles
[Wei, LW]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A multiple kernel support vector machine scheme for__ feature.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.