The problem of choosing the kernel for one-class support vector machines
Autor: | A. N. Budynkov, S. I. Masolkin |
---|---|
Rok vydání: | 2017 |
Předmět: |
020301 aerospace & aeronautics
business.industry Pattern recognition 02 engineering and technology Kernel principal component analysis Kernel method 0203 mechanical engineering Control and Systems Engineering String kernel Kernel embedding of distributions Polynomial kernel Variable kernel density estimation 020204 information systems Radial basis function kernel 0202 electrical engineering electronic engineering information engineering Artificial intelligence Electrical and Electronic Engineering Tree kernel business Mathematics |
Zdroj: | Automation and Remote Control. 78:138-145 |
ISSN: | 1608-3032 0005-1179 |
Popis: | The article presents a review of one-class support vector machine (1-SVM) used when there is not enough data for abnormal technological object's behavior detection. Investigated are three procedures of the SVM's kernel parameter evaluation. Two of them are known in literature as the cross validation method and the maximum dispersion method, and the third one is an author-suggested modification of the maximum dispersion method, minimizing the kernel matrix's entropy. It is shown that for classification without counting training data set ejections the suggested procedure provides the classification's quality equal to the first one, and with less value of the kernel parameter. |
Databáze: | OpenAIRE |
Externí odkaz: |