APLICABILIDADE DE MEMÓRIA LÓGICA COMO FERRAMENTA COADJUVANTE NO DIAGNÓSTICO DAS DOENÇAS GENÉTICAS

Abstract

This study has involved the interaction among knowledge in very distinctive areas, or else: informatics, engineering e genetics, emphasizing the building of a taking decision backing system methodology. The aim of this study has been the development of a tool to help in the diagnosis of chromosomal aberrations, presenting like tutorial model the Turner Syndrome. So to do that there have been used classification techniques based in decision trees, probabilistic networks (Naïve Bayes, TAN e BAN) and neural MLP network (from English, Multi- Layer Perception) and training algorithm by error retro propagation. There has been chosen an algorithm and a tool able to propagate evidence and develop efficient inference techniques able to originate appropriate techniques to combine the expert knowledge with defined data in a databank. We have come to a conclusion about the best solution to work out the shown problem in this study that was the Naïve Bayes model, because this one presented the greatest accuracy. The decision - ID3, TAN e BAN tree models presented solutions to the indicated problem, but those were not as much satisfactory as the Naïve Bayes. However, the neural network did not promote a satisfactory solution.