A new SVM model for classifying genetic data

Wang Juh Chen, Hongbin Guo, Rosemary Renaut, Kewei Chen

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

1 Citation (Scopus)

Abstract

We propose a new formulation of the Support VectorMachine (SVM) for classifying genetic data. It is based on the development of ideas from the method of total least squares, in which assumed error in measured data are incorporated in the model design. For genetic data the number of features is always far greater than the sample size. Consequently, in our method, we introduce Lagrange multipliers and solve for the dual variables. Instead of finding the minimum value of the Lagrangian function, we solve the nonlinear system of equations obtained from the Karush-Kuhn-Tucker conditions. We also implement complementarity constraints and incorporate weighting of the linear system by the inverse covariance matrix of the measured data. The proposed algorithm gives improved results and higher sensitivity for classifying a set of Alzheimer's Disease Positron Emission Tomography images as compared with SVM. It is also more robust to noise than SVM. Copyright

Original languageEnglish (US)
Title of host publicationInternational Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics 2010, BCBGC 2010
Pages54-60
Number of pages7
StatePublished - 2010
Event2010 International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics, BCBGC 2010 - Orlando, FL, United States
Duration: Jul 12 2010Jul 14 2010

Other

Other2010 International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics, BCBGC 2010
CountryUnited States
CityOrlando, FL
Period7/12/107/14/10

Fingerprint

Genetic Models
Least-Squares Analysis
Positron-Emission Tomography
Sample Size
Noise
Alzheimer Disease

ASJC Scopus subject areas

  • Biotechnology
  • Genetics

Cite this

Chen, W. J., Guo, H., Renaut, R., & Chen, K. (2010). A new SVM model for classifying genetic data. In International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics 2010, BCBGC 2010 (pp. 54-60)

A new SVM model for classifying genetic data. / Chen, Wang Juh; Guo, Hongbin; Renaut, Rosemary; Chen, Kewei.

International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics 2010, BCBGC 2010. 2010. p. 54-60.

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

Chen, WJ, Guo, H, Renaut, R & Chen, K 2010, A new SVM model for classifying genetic data. in International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics 2010, BCBGC 2010. pp. 54-60, 2010 International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics, BCBGC 2010, Orlando, FL, United States, 7/12/10.
Chen WJ, Guo H, Renaut R, Chen K. A new SVM model for classifying genetic data. In International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics 2010, BCBGC 2010. 2010. p. 54-60
Chen, Wang Juh ; Guo, Hongbin ; Renaut, Rosemary ; Chen, Kewei. / A new SVM model for classifying genetic data. International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics 2010, BCBGC 2010. 2010. pp. 54-60
@inproceedings{e6b207bed6a948a5a9cf2b014ab68869,
title = "A new SVM model for classifying genetic data",
abstract = "We propose a new formulation of the Support VectorMachine (SVM) for classifying genetic data. It is based on the development of ideas from the method of total least squares, in which assumed error in measured data are incorporated in the model design. For genetic data the number of features is always far greater than the sample size. Consequently, in our method, we introduce Lagrange multipliers and solve for the dual variables. Instead of finding the minimum value of the Lagrangian function, we solve the nonlinear system of equations obtained from the Karush-Kuhn-Tucker conditions. We also implement complementarity constraints and incorporate weighting of the linear system by the inverse covariance matrix of the measured data. The proposed algorithm gives improved results and higher sensitivity for classifying a set of Alzheimer's Disease Positron Emission Tomography images as compared with SVM. It is also more robust to noise than SVM. Copyright",
author = "Chen, {Wang Juh} and Hongbin Guo and Rosemary Renaut and Kewei Chen",
year = "2010",
language = "English (US)",
isbn = "9781617820694",
pages = "54--60",
booktitle = "International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics 2010, BCBGC 2010",

}

TY - GEN

T1 - A new SVM model for classifying genetic data

AU - Chen, Wang Juh

AU - Guo, Hongbin

AU - Renaut, Rosemary

AU - Chen, Kewei

PY - 2010

Y1 - 2010

N2 - We propose a new formulation of the Support VectorMachine (SVM) for classifying genetic data. It is based on the development of ideas from the method of total least squares, in which assumed error in measured data are incorporated in the model design. For genetic data the number of features is always far greater than the sample size. Consequently, in our method, we introduce Lagrange multipliers and solve for the dual variables. Instead of finding the minimum value of the Lagrangian function, we solve the nonlinear system of equations obtained from the Karush-Kuhn-Tucker conditions. We also implement complementarity constraints and incorporate weighting of the linear system by the inverse covariance matrix of the measured data. The proposed algorithm gives improved results and higher sensitivity for classifying a set of Alzheimer's Disease Positron Emission Tomography images as compared with SVM. It is also more robust to noise than SVM. Copyright

AB - We propose a new formulation of the Support VectorMachine (SVM) for classifying genetic data. It is based on the development of ideas from the method of total least squares, in which assumed error in measured data are incorporated in the model design. For genetic data the number of features is always far greater than the sample size. Consequently, in our method, we introduce Lagrange multipliers and solve for the dual variables. Instead of finding the minimum value of the Lagrangian function, we solve the nonlinear system of equations obtained from the Karush-Kuhn-Tucker conditions. We also implement complementarity constraints and incorporate weighting of the linear system by the inverse covariance matrix of the measured data. The proposed algorithm gives improved results and higher sensitivity for classifying a set of Alzheimer's Disease Positron Emission Tomography images as compared with SVM. It is also more robust to noise than SVM. Copyright

UR - http://www.scopus.com/inward/record.url?scp=84878121643&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878121643&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84878121643

SN - 9781617820694

SP - 54

EP - 60

BT - International Conference on Bioinformatics, Computational Biology, Genomics and Chemoinformatics 2010, BCBGC 2010

ER -