FUNCTIONS OF RIVAL SIMILARITY IN ALGORITHMS OF RECOGNITION OF COMBINED TYPE


Citar

Texto integral

Resumo

For decision of combined tasks of pattern recognition we offer methods based on function of rival similarity (FRiS-function). With the help of the function we can estimate similarity between objects, build decision rules, estimate compactness ofpatterns and informativeness of attributes. Examples of use of the offered methods for decision of tasks of recognition and forecasting are given in the article.

Bibliografia

  1. Methods of Recognition Based on the Function of Rival Similarity / N. G. Zagoruiko [et al.] // Pattern Recognition and Image Analysis. 2008. Vol. 18. P. 1-6.
  2. Attribute selection through decision rules construction (algorithm FRiS-GRAD) / N. G. Zagoruiko [et al.] // Pattern Recognition and Image Analysis : New Information Technologies : Proc. of 9th Intern Conf. Nizhni Novgorod. 2008. Vol. 2. P. 335-338.
  3. Gene Selection for Cancer Classification using Support Vector Machines / I. Guyon [et al.] // Machine Learning. 2002. Vol. 46 (1-3). P. 389-395.
  4. Дюбанов В. В. Использование FRiS-функции в алгоритмах предсказания количественных переменных (Алгоритм FRiS-Pro) // Знания-Онтологии-Теории (ЗОНТ-09) : тр. Всерос. конф. Новосибирск, 2009. Т. 2. С. 258-260.

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML
Baixar

Declaração de direitos autorais © Zagoruyko N.G., Borisova I.A., Dyubanov V.V., Kutnenko O.A., Zagoruiko N.G., Borisova I.A., Dyubanov V.V., Kutnenko O.A., 2010

Creative Commons License
Este artigo é disponível sob a Licença Creative Commons Atribuição 4.0 Internacional.

Este site utiliza cookies

Ao continuar usando nosso site, você concorda com o procedimento de cookies que mantêm o site funcionando normalmente.

Informação sobre cookies