%0 Journal Article
%T An Artificial Neural Network Model for Neonatal Disease Diagnosis
%A Dilip Roy Chowdhury
%A Mridula Chatterjee & R. K. Samanta
%J International Journal of Artificial Intelligence and Expert Systems
%D 2011
%I Computer Science Journals
%X The significance of disease diagnosis by artificial intelligence is not obscure now a day. Theincreasing demand of Artificial Neural Network application for predicting the disease shows betterperformance in the field of medical decision making. This paper represents the use of artificialneural networks in predicting neonatal disease diagnosis. The proposed technique involvestraining a Multi Layer Perceptron with a BP learning algorithm to recognize a pattern for thediagnosing and prediction of neonatal diseases. A comparative study of using different trainingalgorithm of MLP, Quick Propagation, Conjugate Gradient Descent, shows the higher predictionaccuracy. The Backpropogation algorithm was used to train the ANN architecture and the samehas been tested for the various categories of neonatal disease. About 94 cases of different signand symptoms parameter have been tested in this model. This study exhibits ANN basedprediction of neonatal disease and improves the diagnosis accuracy of 75% with higher stability.
%K Artificial Intelligence
%K Multi Layer Perceptron
%K Neural Network
%K Neonate
%U http://cscjournals.org/csc/manuscript/Journals/IJAE/volume2/Issue3/IJAE-57.pdf