A Refined Continuous Ant Colony Optimization Based FP-Growth Association Rule Technique on Type 2 Diabetes

Abstract

In recent years, Diabetes mellitus almost tops the list of chronic diseases worldwide among the major public health challenges. Diagnosing diabetes at the preliminary stage is undoubtedly challenging as it involves varying complexities and inter relation and dependence on several factors that affect it directly or indirectly. Due to large number of diabetic patients in recent years, desperate measures have to be devised and developed to facilitate medical diagnostic decision support systems that help doctors, researchers and medical practitioners during and after the process of diagnosing Diabetes. In this paper, the Association Rule Mining and Enhanced FP-Growth Algorithm has been used as a reference to propose a new algorithm that is basically has similar functionalities as that of the Ant Colony Optimization algorithm and one that improvises association rule mining results. The Refined Continuous Ant Colony Optimization or CACO deploys a meta-heuristic approach and has been devised and enthused by actual ant colonies behavior along with the sustained continuous domains. Preliminarily association rules so produced by the Enhanced FP-Growth algorithm are deployed thereafter which rules from weakest set are found on the basis of threshold value and then further used by the Ant Colony algorithm so that association rules are reduced and a better quality of rules are discovered as a result of the efforts. The study as well the research presented here aims at reducing database scanning by optimizing as well by improving the quality of rules that are produced for CACO.