Minimal rule-based classifiers using PCA on pima-indians-diabetes-dataset

Abstract

Diabetes mellitus has been a very complex and chronic lifelong disease. Hence, it has been identified as a clinically highly significant disease which further attracted the healthcare industry to define most relevant clinical directories and also to apply efficient automated pre-diagnoses and further care. Rule-based classifier technique has proven its strength in diabetes diagnosis when used the computational methods. There has been a considerable development in the classifier’s performance, to classify the disease, in the past decades by which they were highly recommended. In this paper, a classifier is proposed based on minimum rules which further uses Principal Component Analysis (PCA). To apply these techniques Pima Indians diabetes dataset is used from the UCI Machine Learning Repository. Set of experiments were conducted on the data set with PCA to evaluate the performance among the decision tree, Naïve Bayes, and Support Vector Machine.