Local linear multi-SVM method for gene function classification

Benhui Chen, Feiran Sun, Takayuki Furuzuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

This paper proposes a local linear multi-SVM method based on composite kernel for solving classification tasks in gene function prediction. The proposed method realizes a nonlinear separating boundary by estimating a series of piecewise linear boundaries. Firstly, according to the distribution information of training data, a guided partitioning approach composed of separating boundary detection and clustering technique is used to obtain local subsets, and each subset is utilized to capture prior knowledge of corresponding local linear boundary. Secondly, a composite kernel is introduced to realize the local linear multi-SVM model. Instead of building multiple local SVM models separately, the prior knowledge of local subsets is used to construct a composite kernel, then the local linear multi-SVM model is realized by using the composite kernel exactly in the same way as a single SVM model. Experimental results on benchmark datasets demonstrate that the proposed method improves the classification performance efficiently.

Original languageEnglish
Title of host publicationProceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010
Pages183-188
Number of pages6
DOIs
Publication statusPublished - 2010
Event2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010 - Kitakyushu
Duration: 2010 Dec 152010 Dec 17

Other

Other2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010
CityKitakyushu
Period10/12/1510/12/17

Fingerprint

Genes
Gene
Composite materials
Composite
kernel
Prior Knowledge
Subset
Boundary Detection
Piecewise Linear
Model
Partitioning
Clustering
Benchmark
Series
Prediction
Experimental Results
Demonstrate

Keywords

  • Composite kernel
  • Gene function classification
  • Local linear
  • Multi-SVM model
  • Prior knowledge

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Chen, B., Sun, F., & Furuzuki, T. (2010). Local linear multi-SVM method for gene function classification. In Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010 (pp. 183-188). [5716332] https://doi.org/10.1109/NABIC.2010.5716332

Local linear multi-SVM method for gene function classification. / Chen, Benhui; Sun, Feiran; Furuzuki, Takayuki.

Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010. 2010. p. 183-188 5716332.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, B, Sun, F & Furuzuki, T 2010, Local linear multi-SVM method for gene function classification. in Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010., 5716332, pp. 183-188, 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010, Kitakyushu, 10/12/15. https://doi.org/10.1109/NABIC.2010.5716332
Chen B, Sun F, Furuzuki T. Local linear multi-SVM method for gene function classification. In Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010. 2010. p. 183-188. 5716332 https://doi.org/10.1109/NABIC.2010.5716332
Chen, Benhui ; Sun, Feiran ; Furuzuki, Takayuki. / Local linear multi-SVM method for gene function classification. Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010. 2010. pp. 183-188
@inproceedings{89b75b6383c2411492940578881d1199,
title = "Local linear multi-SVM method for gene function classification",
abstract = "This paper proposes a local linear multi-SVM method based on composite kernel for solving classification tasks in gene function prediction. The proposed method realizes a nonlinear separating boundary by estimating a series of piecewise linear boundaries. Firstly, according to the distribution information of training data, a guided partitioning approach composed of separating boundary detection and clustering technique is used to obtain local subsets, and each subset is utilized to capture prior knowledge of corresponding local linear boundary. Secondly, a composite kernel is introduced to realize the local linear multi-SVM model. Instead of building multiple local SVM models separately, the prior knowledge of local subsets is used to construct a composite kernel, then the local linear multi-SVM model is realized by using the composite kernel exactly in the same way as a single SVM model. Experimental results on benchmark datasets demonstrate that the proposed method improves the classification performance efficiently.",
keywords = "Composite kernel, Gene function classification, Local linear, Multi-SVM model, Prior knowledge",
author = "Benhui Chen and Feiran Sun and Takayuki Furuzuki",
year = "2010",
doi = "10.1109/NABIC.2010.5716332",
language = "English",
isbn = "9781424473762",
pages = "183--188",
booktitle = "Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010",

}

TY - GEN

T1 - Local linear multi-SVM method for gene function classification

AU - Chen, Benhui

AU - Sun, Feiran

AU - Furuzuki, Takayuki

PY - 2010

Y1 - 2010

N2 - This paper proposes a local linear multi-SVM method based on composite kernel for solving classification tasks in gene function prediction. The proposed method realizes a nonlinear separating boundary by estimating a series of piecewise linear boundaries. Firstly, according to the distribution information of training data, a guided partitioning approach composed of separating boundary detection and clustering technique is used to obtain local subsets, and each subset is utilized to capture prior knowledge of corresponding local linear boundary. Secondly, a composite kernel is introduced to realize the local linear multi-SVM model. Instead of building multiple local SVM models separately, the prior knowledge of local subsets is used to construct a composite kernel, then the local linear multi-SVM model is realized by using the composite kernel exactly in the same way as a single SVM model. Experimental results on benchmark datasets demonstrate that the proposed method improves the classification performance efficiently.

AB - This paper proposes a local linear multi-SVM method based on composite kernel for solving classification tasks in gene function prediction. The proposed method realizes a nonlinear separating boundary by estimating a series of piecewise linear boundaries. Firstly, according to the distribution information of training data, a guided partitioning approach composed of separating boundary detection and clustering technique is used to obtain local subsets, and each subset is utilized to capture prior knowledge of corresponding local linear boundary. Secondly, a composite kernel is introduced to realize the local linear multi-SVM model. Instead of building multiple local SVM models separately, the prior knowledge of local subsets is used to construct a composite kernel, then the local linear multi-SVM model is realized by using the composite kernel exactly in the same way as a single SVM model. Experimental results on benchmark datasets demonstrate that the proposed method improves the classification performance efficiently.

KW - Composite kernel

KW - Gene function classification

KW - Local linear

KW - Multi-SVM model

KW - Prior knowledge

UR - http://www.scopus.com/inward/record.url?scp=79952767363&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952767363&partnerID=8YFLogxK

U2 - 10.1109/NABIC.2010.5716332

DO - 10.1109/NABIC.2010.5716332

M3 - Conference contribution

AN - SCOPUS:79952767363

SN - 9781424473762

SP - 183

EP - 188

BT - Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010

ER -