The Community for Technology Leaders
Circuits, Communications and Systems, Pacific-Asia Conference on (2009)
Chengdu, China
May 16, 2009 to May 17, 2009
ISBN: 978-0-7695-3614-9
pp: 520-525
ABSTRACT
Hyper-Sphere Multi-Class SVM (HSMC-SVM) is a kind of direct-model multi-class classifiers, and its training and testing speed are high. However, with the one-order norm soft-margin, classifying precision of HSMC-SVM is affected. In order to improve the classifying precision, least square method is introduced in HSMC-SVM. As a result, a kind of new multi-class classifiers, Least Square Hyper-Sphere Multi-Class SVM (LSHS-MCSVM), is proposed. Simultaneously, the training algorithm and decision rules of LSHS-MCSVM are discussed too. Thus the classifying theory of LSHS-MCSVM is built completely. Shown in the numeric experiments, LSHS-MCSVM excels HSMC-SVM at both training speed and classifying precision. Hence, it is suitable for the situations with lots of classification categories and large scale of training samples.
INDEX TERMS
support vector machine (SVM); multi-class SVM; SMO algorithm; work set selection; LSHS-MCSVM
CITATION
Tu Xu, "A New Sphere-Structure Multi-Class Classifier", Circuits, Communications and Systems, Pacific-Asia Conference on, vol. 00, no. , pp. 520-525, 2009, doi:10.1109/PACCS.2009.64
88 ms
(Ver 3.3 (11022016))