DIABETES DATA ANALYSIS USING MAPREDUCE AND CLASSIFICATION TECHNIQUES

Abstract

Data mining techniques can be applied to extract valuable knowledge from data repositories, e.g. through clustering, classification or association rule mining. Mapreduce is a programming technique which is suitable for analyzing large data sets that otherwise cannot fit in your computer's memory. The research hopes to propose a quicker and more efficient technique of diagnosing the disease, leading to timely treatment of the patients. After mapreduce the classification techniques such as KNN and SVM are applied. The performance of classification techniques are analyzed and interpreted.