File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Kernel techniques in support vector machines for classification of biological data

TitleKernel techniques in support vector machines for classification of biological data
Authors
KeywordsEigen-matrix Translation Techniques
Motif
Protein Classification
Support Vector Machine
Spectrum Kernel Method
Issue Date2011
PublisherModern Education & Computer Science Press. The Journal's web site is located at http://www.mecs-press.org/ijitcs/
Citation
International Journal of Information Technology and Computer Science, 2011, v. 3 n. 2, p. 1-8 How to Cite?
AbstractIn this paper, we consider the problem of protein classification, which is a important and hot topic in bioinformatics. We propose a novel kernel based on the KSpectrum Kernel by incorporating physico-chemical and biological properties of amino acids as well as the motif information for the captured protein classification problem. Similarity matrix is constructed based on an AAindex2 substitution matrix which measures the amino acid pair distance. Together with the motif content posing importance on the protein sequences, a new kernel is then constructed. We adopt the Eigen-matrix translation techniques for improving the classification accuracy. Experimental results indicate that the string-based kernel in conjunction with SVM classifier performs significantly better than the traditional spectrum kernel method. Furthermore, numerical examples also confirm the use of the Eigenmatrix translation techniques as general strategy.
Persistent Identifierhttp://hdl.handle.net/10722/135165
ISSN

 

DC FieldValueLanguage
dc.contributor.authorJiang, Hen_US
dc.contributor.authorChing, WKen_US
dc.contributor.authorZheng, Zen_US
dc.date.accessioned2011-07-27T01:29:11Z-
dc.date.available2011-07-27T01:29:11Z-
dc.date.issued2011en_US
dc.identifier.citationInternational Journal of Information Technology and Computer Science, 2011, v. 3 n. 2, p. 1-8en_US
dc.identifier.issn2074-9007-
dc.identifier.urihttp://hdl.handle.net/10722/135165-
dc.description.abstractIn this paper, we consider the problem of protein classification, which is a important and hot topic in bioinformatics. We propose a novel kernel based on the KSpectrum Kernel by incorporating physico-chemical and biological properties of amino acids as well as the motif information for the captured protein classification problem. Similarity matrix is constructed based on an AAindex2 substitution matrix which measures the amino acid pair distance. Together with the motif content posing importance on the protein sequences, a new kernel is then constructed. We adopt the Eigen-matrix translation techniques for improving the classification accuracy. Experimental results indicate that the string-based kernel in conjunction with SVM classifier performs significantly better than the traditional spectrum kernel method. Furthermore, numerical examples also confirm the use of the Eigenmatrix translation techniques as general strategy.-
dc.languageengen_US
dc.publisherModern Education & Computer Science Press. The Journal's web site is located at http://www.mecs-press.org/ijitcs/-
dc.relation.ispartofInternational Journal of Information Technology and Computer Scienceen_US
dc.rightsInternational Journal of Information Technology and Computer Science. Copyright © MECS Publisher-
dc.subjectEigen-matrix Translation Techniques-
dc.subjectMotif-
dc.subjectProtein Classification-
dc.subjectSupport Vector Machine-
dc.subjectSpectrum Kernel Method-
dc.titleKernel techniques in support vector machines for classification of biological dataen_US
dc.typeArticleen_US
dc.identifier.emailJiang, H: haohao@hkusuc.hku.hken_US
dc.identifier.emailChing, WK: wching@hku.hk-
dc.identifier.authorityChing, WK=rp00679en_US
dc.description.naturelink_to_OA_fulltext-
dc.identifier.doi10.5815/ijitcs.2011.02.01-
dc.identifier.hkuros188185en_US
dc.identifier.volume3en_US
dc.identifier.issue2-
dc.identifier.spage1en_US
dc.identifier.epage8en_US
dc.publisher.placeHong Kong-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats