Selection Important Symptoms for Medical Datasets

Selection of optimal features is an important area of research in medical data mining systems. In this research we introduce an efficient procedure ¿feature subset selection, feature ranking and classification, called as Principle Component Analysis based on JK method for the improvement of detection accuracy and optimal feature subset selection. The proposed method adjusts a parameter named ¿variance coverage¿ and builds the model with the value at which maximum classification accuracy is obtained. This facilitates the selection of a compact set of superior features, remarkably at a very low cost. The extensive experimental comparison of the proposed method and other methods using three different classifiers (Naïve Bayes (NB), multi-layer perceptron (MLP) and J48 decision tree) and 6 different medical data sets can confirm that the proposed (PCA-JK) strategy yields promising results on feature selection and classification accuracy for medical data mining field of research.