| Solving large-scale multiclass learning problems via an efficient support vector classifier |
| |
| 作者姓名： | Zheng Shuibo Tang Houjun Han Zhengzhi & Zhang Haoran . School of Electrical and Information Engineering Shanghai Jiaotong Univ. Shanghai P. R. China . Dept. of Electronic Engineering Zhejiang Normal Univ. Jinhua P. R. China |
| |
| 作者单位： | Zheng Shuibo1，Tang Houjun1，Han Zhengzhi1 & Zhang Haoran2 1. School of Electrical and Information Engineering，Shanghai Jiaotong Univ.，Shanghai 200030，P. R. China; 2. Dept. of Electronic Engineering，Zhejiang Normal Univ.，Jinhua 321004，P. R. China |
| |
| 摘 要： | 1. INTRODUCTION In recent years, a new type of classifier, support vector machines1~2], is receiving adoption increasingly as a state-of-the-art tool to solve knowledge discovery pro- blems. SVMs are based on the statistical learning the- ory of Vapnik1] and quadratic programming optimiz- ation. Support vector machines (SVMs) are initially designed for binary classification problem. How to effectively extend them for multiclass classification is still an ongoing research topic. Curr…
|
| 收稿时间： | 23 May 2005. |
Solving large-scale multiclass learning problems via an efficient support vector classifier |
| |
| Zheng Shuibo,Tang Houjun,Han Zhengzhi & Zhang Haoran . School of Electrical and Information Engineering,Shanghai Jiaotong Univ.,Shanghai ,P. R. China, . Dept. of Electronic Engineering,Zhejiang Normal Univ.,Jinhua ,P. R. China.Solving large-scale multiclass learning problems via an efficient support vector classifier[J].Journal of Systems Engineering and Electronics,2006,17(4):910-915. |
| |
| Authors: | Zheng Shuibo Tang Houjun Han Zhengzhi Zhang Haoran |
| |
| Institution: | 1. School of Electrical and Information Engineering, Shanghai Jiaotong Univ., Shanghai 200030, P. R. China
2. Dept. of Electronic Engineering, Zhejiang Normal Univ., Jinhua 321004, P. R. China |
| |
| Abstract: | Support vector machines (SVMs) are initially designed for binary classification. How to effectively extend them for multiclass classification is still an ongoing research topic. A multiclass classifier is constructed by combining SVMlight algorithm with directed acyclic graph SVM (DAGSVM) method, named DAGSVMlight. A new method is proposed to select the working set which is identical to the working set selected by SVMlight approach. Experimental results indicate DAGSVMlight is competitive with DAGSMO. It is more suitable for practice use. It may be an especially useful tool for large-scale multiclass classification problems and lead to more widespread use of SVMs in the engineering community due to its good performance. |
| |
| Keywords: | support vector machines (SVMs) multiclass classification decomposition method SVMlight sequential minimal optimization (SMO) |
| 本文献已被 CNKI 万方数据 ScienceDirect 等数据库收录！ |
