An enhanced model for diabetes prediction using improved firefly feature selection and hybrid random forest algorithm

Abstract

Diabetes is a chronic disease that causes numerous amount of death each year. Untreated diabetes disturbs the proper functionality of other organs in human body. Hence early detection is a significant process to have a healthy life style. Usually the performance of the classification is affected due to the existence of high dimensionality in medical data.In this study a system model is proposed on Pima dataset to enhance the classification accuracy by eliminating the irrelevant features. Therefore it is important to choose a suitable feature selection approach that provides the better accuracy in disease prediction compared to prior study.Hencenovel techniquesImprovedFirefly(IFF)and hybrid Random forest algorithmis proposed for feature selection and classification. The present study provides a better result with 96.3% accuracy.The efficiency of the present studyis compared with the prior classification approaches.