Novel linear search for support vector machine parameter selection

Selecting the optimal parameters for support vector machine （SVM） has long been a hot research topic. Aiming for support vector classification/regression （SVC/SVR） with the radial basis function （RBF） kernel, we summarize the rough line rule of the penalty parameter and kernel width, and propose a n...

Full description

Saved in:
Bibliographic Details
Published in:Journal of Zhejiang University. C Science 2011-11, Vol.12 (11), p.885-896
Main Authors: Pang, Hong-xia, Dong, Wen-de, Xu, Zhi-hai, Feng, Hua-jun, Li, Qi, Chen, Yue-ting
Format: Article
Language:English
Subjects:
Classification
Communications Engineering
Computational efficiency
Computer Hardware
Computer Science
Computer Systems Organization and Communication Networks
Electrical Engineering
Electronics and Microelectronics
Instrumentation
Kernels
Mathematical analysis
Networks
Optimization
Regression
Searching
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Selecting the optimal parameters for support vector machine （SVM） has long been a hot research topic. Aiming for support vector classification/regression （SVC/SVR） with the radial basis function （RBF） kernel, we summarize the rough line rule of the penalty parameter and kernel width, and propose a novel linear search method to obtain these two optimal parameters. We use a direct-setting method with thresholds to set the epsilon parameter of SVR. The proposed method directly locates the right search field, which greatly saves computing time and achieves a stable, high accuracy. The method is more competitive for both SVC and SVR. It is easy to use and feasible for a new data set without any adjustments, since it requires no parameters to set.
ISSN:1869-1951
1869-196X
DOI:10.1631/jzus.C1100006