An efficient method for high performance prediction mechanism for diabetes using enhanced Firefly algorithm and Map-Reduce

Abstract

Algorithms in Data mining are utilized to predict unrefined data into useful conventional information. This conservative information plays a vital role in the Health care industry. In this study we focus on the functionalities of diabetes prediction. In diabetes data we have the problem of data imbalance in predicting the accuracy. The Proposed tailored Firefly Algorithm along with Map reduce is used to augment the efficacy and precision of prediction. Comparison of Different bench mark algorithms with our new Extended Fire Fly is done and variety of classification methods are used with moto to increase the effectiveness. The new method helps to maximize the prediction of accuracy and reduces the time. The PIMA Indian Diabetic Dataset from UCI machine learning repository is utilized for our experiment results. Different metrics are used in order to prove the effectiveness.