- Issue
- Journal of Siberian Federal University. Mathematics & Physics. 2016 9 (4)
- Authors
- Mihov, Eugene D.; Nepomnyashchiy, Oleg V.
- Contact information
- Mihov, Eugene D.: Institute of Space and Information Technology Siberian Federal University Kirensky, 26, Krasnoyarsk, 660074 Russia; ; Nepomnyashchiy, Oleg V.: Institute of Space and Information Technology Siberian Federal University Kirensky, 26, Krasnoyarsk, 660074 Russia;
- Keywords
- classification; small training sample; informative variable; optimization of the coefficient vector of the kernel fuzziness
- Abstract
The problem of multidimensional object classification with small training sample is considered. The following algorithms of estimating variable informativeness are considered: Ad, Del, AdDel. A new algorithm for selecting informative variables is proposed. It is based on the optimization of the coefficient vector of the kernel fuzziness. Some modification of this algorithm is also discussed. The comparative analysis of existing methods for selecting informative variables is presented.
- Pages
- 473-480
- Paper at repository of SibFU
- https://elib.sfu-kras.ru/handle/2311/29994
Journal of Siberian Federal University. Mathematics & Physics / Selecting Informative Variables in the Identification Problem
Full text (.pdf)