BDBComp
Parceria:
SBC
Formação de conceitos probabilísticos através de observações contendo atributos discretos e contínuos

Ricardo Batista RebouçasJoão José Vasco Furtado

In real world applications, many entities can be represented by a combination of discrete and numeric attributes. The concept formation general problem in dealing with mixed-data scale environments is due to the use of different evaluation function for each attribute type. In this paper, we analyze this problem and propose a solution. The solution is based on taking into account the individual contribution of each attribute-oriented evaluation function for the overall evaluation function. Experiments measuring the quality of concepts generated from our approach have shown superior results when these concepts are generated from data with discrete and numeric attributes. Clique no link abaixo para buscar o texto completo deste trabalho na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD