A methodological approach for pattern recognition system using discriminant analysis and artificial neural networks


Abstract:

In this work it is presented a methodology for the development of a pattern recognition system using classification methods as discriminant analysis and artificial neural networks. In this methodology, the statistical analysis is contemplated, with the purpose of retaining the observations and the important characteristics that can produce an appropriate classification, and allows, as well, to detect outliers' observations, multicolinearity between variables, among other things.

Año de publicación:

2005

Keywords:

  • classification
  • artificial neural networks
  • pattern recognition
  • Discriminant analysis

Fuente:

scopusscopus

Tipo de documento:

Article

Estado:

Acceso restringido

Áreas de conocimiento:

  • Red neuronal artificial
  • Ciencias de la computación
  • Ciencias de la computación

Áreas temáticas:

  • Ciencias de la computación