Predicting Diabetes Risk Using an Improved Apriori Algorithm

Abstract

The data mining is able to analyze data and recover the valuable insights from the data. These insights are used for serving in different applications. In this context different data mining algorithms has been developed among them frequent pattern mining has an essential role. In this paper, the frequent pattern mining technique has been implemented for analyzing the diabetic risk. In this context, the popular diabetic dataset has been obtained. Then, the preprocessing has been done on dataset for cleaning the dataset. Next, an encoding process has been developed to transform the dataset. This transform dataset is an effort to deal with the continuous values using the frequent pattern algorithm. Further a modified apriori algorithm has been employed to understand and establish the relationships between diabetic attributes. The experiments have been carried out and theexperimental performance of the improved apriori algorithms has been measured. Additionally a comparison has also been performed with three popular frequent pattern mining algorithms. According, to the performance, we found that the proposed apriori algorithm is efficient and accurate algorithm to predict the diabetic risk.