SciELO - Scientific Electronic Library Online

 
vol.21 número6Programa de Cálculo para la Evaluación de Contaminantes en Efluentes Gaseosos y Pulverulentos de Hornos de FundiciónProceso de Adaptación de una Aplicación de e-aprendizaje a t-aprendizaje índice de autoresíndice de assuntospesquisa de artigos
Home Pagelista alfabética de periódicos  

Serviços Personalizados

Journal

Artigo

Indicadores

Links relacionados

Compartilhar


Información tecnológica

versão On-line ISSN 0718-0764

Resumo

MATEUS, Sandra P. A Technique of Artificial Intelligence to Fit one of the Elements that Define a Non-Uniform Rational B-Spline (NURBS). Inf. tecnol. [online]. 2010, vol.21, n.6, pp.19-26. ISSN 0718-0764.  http://dx.doi.org/10.4067/S0718-07642010000600004.

In the existing techniques of Artificial Intelligence, two Artificial Neural Networks (ANN) were selected and adapted to fit one of the elements that define a Non-Uniform Rational B-Spline (NURBS) and thus obtaining an appropriate modeling of the NURBS. The selected elements were the checkpoints. The ANN used were the Radial Basis Function and the Kohonen model or Self-Organizing Maps. Based on the analysis of the results and characterization of the ANN the Radial Basis Function had a more appropriate and optimum performance for a large number of data, which is a disadvantage of the Self-Organizing Maps. In this model, additional processes must be done to determine the winning neuron and the weights must be refitted.

Palavras-chave : artificial neural network; NURBS; control points; radial basis functions; self-organizing maps.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )

 

Creative Commons License Todo o conteúdo deste periódico, exceto onde está identificado, está licenciado sob uma Licença Creative Commons