Single Directional SMO Algorithm for Least Squares Support Vector Machines

Single Directional SMO Algorithm for Least Squares Support Vector Machines

Working set selection is a major step in decomposition methods for training least squares support vector machines (LS-SVMs). In this paper, a new technique for the selection of working set in sequential minimal optimization- (SMO-) type decomposition methods is proposed. By the new method, we can se...

Full description

Bibliographic Details
Main Authors: Xigao Shao, Kun Wu, Bifeng Liao
Format: Article
Language:English
Published: Hindawi Limited 2013-01-01
Series:Computational Intelligence and Neuroscience
Online Access:http://dx.doi.org/10.1155/2013/968438
id doaj-1ee3c06a74a047bcb62a1b53019261b3
record_format Article
spelling doaj-1ee3c06a74a047bcb62a1b53019261b32020-11-25T00:19:57ZengHindawi LimitedComputational Intelligence and Neuroscience1687-52651687-52732013-01-01201310.1155/2013/968438968438Single Directional SMO Algorithm for Least Squares Support Vector MachinesXigao Shao0Kun Wu1Bifeng Liao2School of Mathematics and Statistics, Central South University, Changsha, Hunan 41007, ChinaSchool of Mathematics and Statistics, Central South University, Changsha, Hunan 41007, ChinaSchool of Mathematics and Information Science, Yantai University, Yantai, Shandong 264005, ChinaWorking set selection is a major step in decomposition methods for training least squares support vector machines (LS-SVMs). In this paper, a new technique for the selection of working set in sequential minimal optimization- (SMO-) type decomposition methods is proposed. By the new method, we can select a single direction to achieve the convergence of the optimality condition. A simple asymptotic convergence proof for the new algorithm is given. Experimental comparisons demonstrate that the classification accuracy of the new method is not largely different from the existing methods, but the training speed is faster than existing ones.http://dx.doi.org/10.1155/2013/968438
collection DOAJ
language English
format Article
sources DOAJ
author Xigao Shao
Kun Wu
Bifeng Liao
spellingShingle Xigao Shao
Kun Wu
Bifeng Liao
Single Directional SMO Algorithm for Least Squares Support Vector Machines
Computational Intelligence and Neuroscience
author_facet Xigao Shao
Kun Wu
Bifeng Liao
author_sort Xigao Shao
title Single Directional SMO Algorithm for Least Squares Support Vector Machines
title_short Single Directional SMO Algorithm for Least Squares Support Vector Machines
title_full Single Directional SMO Algorithm for Least Squares Support Vector Machines
title_fullStr Single Directional SMO Algorithm for Least Squares Support Vector Machines
title_full_unstemmed Single Directional SMO Algorithm for Least Squares Support Vector Machines
title_sort single directional smo algorithm for least squares support vector machines
publisher Hindawi Limited
series Computational Intelligence and Neuroscience
issn 1687-5265
1687-5273
publishDate 2013-01-01
description Working set selection is a major step in decomposition methods for training least squares support vector machines (LS-SVMs). In this paper, a new technique for the selection of working set in sequential minimal optimization- (SMO-) type decomposition methods is proposed. By the new method, we can select a single direction to achieve the convergence of the optimality condition. A simple asymptotic convergence proof for the new algorithm is given. Experimental comparisons demonstrate that the classification accuracy of the new method is not largely different from the existing methods, but the training speed is faster than existing ones.
url http://dx.doi.org/10.1155/2013/968438
work_keys_str_mv AT xigaoshao singledirectionalsmoalgorithmforleastsquaressupportvectormachines
AT kunwu singledirectionalsmoalgorithmforleastsquaressupportvectormachines
AT bifengliao singledirectionalsmoalgorithmforleastsquaressupportvectormachines
_version_ 1725369536965771264

Similar Items