迭代再权共轭梯度q范数正则化线性最小二乘–支持+向量机分类算法.pdfVIP

31 3 Vol. 31 No. 3 2014 3 Control Theory Applications Mar. 2014 DOI: 10.7641/CTA.2014.30690 – , , , , ( , 102249) : –(square support vector machine algorithm, LS–SVM) , , . LS–SVM , , . , , , , . , , LS–SVM. : ; –(LS–SVM); : TP181 : A –norm regularizing least-square-support-vector-machine linear classifier algorithm via iterative reweighted conjugate gradient LIU Jian-wei , LI Hai-en, LIU Yuan, FU Jie, LUO Xiong-lin (Research Institute of Automation, China University of Petroleum, Beijing 102249, China) Abstract: The –norm penalty least-square-support-vector-machine algorithm (LS–SVM) has been extensively stud- ied and is probably the most widely used machine learning algorithm. The regularization parameter in LS–SVM is prede- termined with default value . Based on the iterative reweighted conjugate gradient algorithm, the –norm regularizing LS-SVM is proposed with , a rational number. We design a grid method to change the value of two adjustable parameters, the regularization parameter and the order of regularization, by performance indicators of prediction error rate. On the selected values of and , using the iterative reweighted conjugate gradient algorithm for solving classification object function and finding the minimum prediction error, we can improve the feature selection and predict the error rate. The experimental results on real datasets in different fields indicate that the prediction performance is more accurate than –norm LS-SVM, and can carry out feature selecti