COMBINING NEURAL NETWORK AND SUPPORT VECTOR MACHINE INTO INTEGRATED APPROACH FOR BIODATA MINING

Keivan Kianmehr, Hongchao Zhang, Konstantin Nikolov, Tansel Özyer, Reda Alhajj

2005

Abstract

Bioinformatics is the science of managing, mining, and interpreting information from biological sequences and structures. In this paper, we discuss two data mining techniques that can be applied in bioinformatics: namely, Neural Networks (NN) and Support Vector Machines (SVM), and their application in gene expression classification. First, we provide description of the two techniques. Then we propose a new method that combines both SVM and NN. Finally, we present the results obtained from our method and the results obtained from SVM alone on a sample dataset.

References

  1. Lee Y.-J. and Mangasarian O.L., “RSVM: Reduced Support Vector Machines,” Proc. SIAM ICDM, 2001. http://sdmc.lit.org.sg/GEDatasets/Datasets.html
  2. Krishnapuram B., Carin L., and Hartemink A.J., “Joint Classifier and Feature Optimization for Cancer Diagnosis Using Gene Expression Data,” Proc. of RECOMB, 2003.
  3. Weston J., Mukherjee S., Chapelle O., et al, “Feature Selection for SVMs,” Proc. of NIPS, 2000.
  4. Vapnik V.N., The Nature of Statistical Learning Theory, Second Ed., Springer, New York, 1999.
  5. Cai C.Z., Wang W.L., Sun L.Z., Chen Y.Z., “Protein function classification via support vector machine approach,” Math Biosci., 185(2), pp.111-22, 2003.
  6. Theiler J., Harvey N.R., Brumby S.P., et al, Evolving Retrieval Algorithms with a Genetic Programming Scheme, Proc. SPIE 3753, pp.416-425, 1999.
  7. Duda R.O. and Hart P.E., Pattern Classification and Scene Analysis, John Wiley and Sons, New York, NY, 1973.
  8. Cristianini N., An Introduction to Support Vector Machines, Cambridge University Press, 2000.
  9. Barzilay and Brailovsky V.L., On domain knowledge and feature selection using a support vector machines, Pattern Recognition Letters, Vol.20, No.5, pp. 475- 484, May 1999.
  10. Burgess C., A Tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery, Vol.2, No.2, pp.121-167, 1998.
  11. Gunn S.R., Support Vector Machines for Classification and Regression, ISIS technical report, Image Speech & Intelligent Systems Group, University of Southampton, 1997
  12. Roth F.P., Bringing Out the Best Features of Expression Data, Genome Research (Insight/Outlook), 11(11):1801-1802, 2001.
  13. Guyon I., Weston J., Barnhill S., and Vapnik V., “Gene Selection for Cancer Classification Using Support Vector Machines,” Machine Learning, Vol.46, Nos.1- 3, pp.389-422, 2002.
  14. Gordon G.J., Jensen R.V., Hsiao L.L., et al, “Translation of Microarray Data into Clinically Relevant Cancer Diagnostic Tests Using Gene Expression Ratios in Lung Cancer and Mesothelioma,” Cancer Research, 62, pp.4963-4967, 2002.
Download


Paper Citation


in Harvard Style

Kianmehr K., Zhang H., Nikolov K., Özyer T. and Alhajj R. (2005). COMBINING NEURAL NETWORK AND SUPPORT VECTOR MACHINE INTO INTEGRATED APPROACH FOR BIODATA MINING . In Proceedings of the Seventh International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 972-8865-19-8, pages 182-187. DOI: 10.5220/0002512701820187


in Bibtex Style

@conference{iceis05,
author={Keivan Kianmehr and Hongchao Zhang and Konstantin Nikolov and Tansel Özyer and Reda Alhajj},
title={COMBINING NEURAL NETWORK AND SUPPORT VECTOR MACHINE INTO INTEGRATED APPROACH FOR BIODATA MINING},
booktitle={Proceedings of the Seventh International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2005},
pages={182-187},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002512701820187},
isbn={972-8865-19-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Seventh International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - COMBINING NEURAL NETWORK AND SUPPORT VECTOR MACHINE INTO INTEGRATED APPROACH FOR BIODATA MINING
SN - 972-8865-19-8
AU - Kianmehr K.
AU - Zhang H.
AU - Nikolov K.
AU - Özyer T.
AU - Alhajj R.
PY - 2005
SP - 182
EP - 187
DO - 10.5220/0002512701820187