SVM classification for large data sets by support vector estimating and selecting

Abstract

As a kind of statistical learning theory, in solving the small data set, nonlinear and high dimensional problems, support vector machine (SVM) has shown many advantages. It has been widely applied in recent years. However, with the increase of the training samples, normal SVM training speed becomes the bottleneck of restricting its application. Therefore, this paper presents a new method called support vector estimating and selecting (SVES). It improves SVM for large sample training speed by remove the sample, which help smeller, redundancy or obvious noise. © 2012 Springer-Verlag GmbH.