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

Authors:
Anna Pérez-Méndez;Elizabeth Torres-Rivas;Francklin Rivas-Echeverría;Ronald Maldonado-Rodríguez
Affiliations:
Escuela de Estadística, Universidad de Los Andes, Mérida, Venezuela;Escuela de Estadística,Universidad de Los Andes, Mérida, Venezuela;Laboratorio de Sistemas Inteligentes, Universidad de Los Andes, Mérida, Venezuela;Bioenergetic Laboratory. University of Geneva, Switzerland
Venue:
NN'05 Proceedings of the 6th WSEAS international conference on Neural networks
Year:
2005

Citing 1
Cited 1

Neural network design

Neural network design

Pisum sativum classification based on a methodological approach for pattern recognition using discriminant analysis and neural networks

NN'05 Proceedings of the 6th WSEAS international conference on Neural networks

Quantified Score

Hi-index	0.00

Visualization

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.