Welcome to the InfoSci Platform
Kernel Width Selection for SVM Classification: A Meta-Learning Approach

Kernel Width Selection for SVM Classification: A Meta-Learning Approach

Ali Smith, Kate A. Smith
Copyright: © 2008 |Pages: 15
ISBN13: 9781599045283|ISBN10: 1599045281|EISBN13: 9781599045306
DOI: 10.4018/978-1-59904-528-3.ch006
Cite Chapter Cite Chapter

MLA

Smith, Ali, and Kate A. Smith. "Kernel Width Selection for SVM Classification: A Meta-Learning Approach." Mathematical Methods for Knowledge Discovery and Data Mining, edited by Giovanni Felici and Carlo Vercellis, IGI Global, 2008, pp. 101-115. https://doi.org/10.4018/978-1-59904-528-3.ch006

APA

Smith, A. & Smith, K. A. (2008). Kernel Width Selection for SVM Classification: A Meta-Learning Approach. In G. Felici & C. Vercellis (Eds.), Mathematical Methods for Knowledge Discovery and Data Mining (pp. 101-115). IGI Global. https://doi.org/10.4018/978-1-59904-528-3.ch006

Chicago

Smith, Ali, and Kate A. Smith. "Kernel Width Selection for SVM Classification: A Meta-Learning Approach." In Mathematical Methods for Knowledge Discovery and Data Mining, edited by Giovanni Felici and Carlo Vercellis, 101-115. Hershey, PA: IGI Global, 2008. https://doi.org/10.4018/978-1-59904-528-3.ch006

Export Reference

Mendeley
Favorite

Abstract

The most critical component of kernel based learning algorithms is the choice of an appropriate kernel and its optimal parameters. In this paper we propose a rule based meta-learning approach for automatic radial basis function (rbf) kernel and its parameter selection for Support Vector Machine (SVM) classification. First, the best parameter selection is considered on the basis of prior information of the data with the help of Maximum Likelihood (ML) method and Nelder-Mead (N-M) simplex method. Then the new rule based meta-learning approach is constructed and tested on different sizes of 112 datasets with binary class as well as multi class classification problems. We observe that our rule based methodology provides significant improvement of computational time as well as accuracy in some specific cases.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.