Geodesic
Selecting informative variables in the identification problem
Žurnal Sibirskogo federalʹnogo universiteta. Matematika i fizika, Tome 9 (2016) no. 4, pp. 473-480.

Voir la notice de l'article provenant de la source Math-Net.Ru

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.
Keywords: small training sample, optimization of the coefficient vector of the kernel fuzziness.
Mots-clés : classification, informative variable 
@article{JSFU_2016_9_4_a10,
     author = {Eugene D. Mihov and Oleg V. Nepomnyashchiy},
     title = {Selecting informative variables in the identification problem},
     journal = {\v{Z}urnal Sibirskogo federalʹnogo universiteta. Matematika i fizika},
     pages = {473--480},
     publisher = {mathdoc},
     volume = {9},
     number = {4},
     year = {2016},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/JSFU_2016_9_4_a10/}
}
TY  - JOUR
AU  - Eugene D. Mihov
AU  - Oleg V. Nepomnyashchiy
TI  - Selecting informative variables in the identification problem
JO  - Žurnal Sibirskogo federalʹnogo universiteta. Matematika i fizika
PY  - 2016
SP  - 473
EP  - 480
VL  - 9
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/JSFU_2016_9_4_a10/
LA  - en
ID  - JSFU_2016_9_4_a10
ER  - 
%0 Journal Article
%A Eugene D. Mihov
%A Oleg V. Nepomnyashchiy
%T Selecting informative variables in the identification problem
%J Žurnal Sibirskogo federalʹnogo universiteta. Matematika i fizika
%D 2016
%P 473-480
%V 9
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/JSFU_2016_9_4_a10/
%G en
%F JSFU_2016_9_4_a10
Eugene D. Mihov; Oleg V. Nepomnyashchiy. Selecting informative variables in the identification problem. Žurnal Sibirskogo federalʹnogo universiteta. Matematika i fizika, Tome 9 (2016) no. 4, pp. 473-480. http://geodesic.mathdoc.fr/item/JSFU_2016_9_4_a10/

[1] N. G. Zagoruyko, Cognitive data's analysis, Academic Press GEO, Novosibirsk, 2013 (in Russian)

[2] A. V. Medvedev, “Some notes on $H$–models for non-inertia systems with a delay”, Vestnik SibGAU, 54:5 (2014), 24–34 (in Russian)

[3] E. D. Mihov, “Parameter's of core's smooth optimization in the case of nonparametric modeling”, Vestnik SibGAU, 16:2 (2015), 338–342 (in Russian)