Cross-Validation, Bootstrap, and Support Vector Machines.pdfVIP

Hindawi Publishing Corporation Advances in Artificial Neural Systems Volume 2011, Article ID 302572, 6 pages doi:10.1155/2011/302572 Research Article Cross-Validation, Bootstrap, and Support Vector Machines Masaaki Tsujitani1, 2 and Yusuke Tanaka1, 2 1 Division of Informatics and Computer Sciences, Graduate School of Engineering, Osaka Electro-Communication University, Osaka 572-8530, Japan 2 Biometrics Department, Statistics Analysis Division, EPS Co., Ltd., 3-4-30 Miyahara, Yodogawa-ku, Osaka 532-0003, Japan Correspondence should be addressed to Masaaki Tsujitani, ekaaf900@ricv.zaq.ne.jp Received 2 April 2011; Accepted 7 June 2011 Academic Editor: Tomasz G. Smolinski Copyright © 2011 M. Tsujitani and Y. Tanaka. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This paper considers the applications of resampling methods to support vector machines (SVMs). We take into account the leaving- one-out cross-validation (CV) when determining the optimum tuning parameters and bootstrapping the deviance in order to summarize the measure of goodness-of-fit in SVMs. The leaving-one-out CV is also adapted in order to provide estimates of the bias of the excess error in a prediction rule constructed with training samples. We analyze the data from a mackerel-egg survey and a liver-disease study. 1. Introduction is also adapted in order to provide estimates of the bias of the excess error in a prediction rule constructed with training In recent years, support vector machines (SVM