AN EFFICIENT APPROACH FOR DETECTION OF HEART ATTACK USING NOBLE ANT COLONY OPTIMIZATION CONCEPT OF DATA MINING

The goal of data mining is to extract knowledge from large amounts of data. Data Mining is an interdisciplinary field that focuses on machine learning, statistics and databases. In this article, we highlight a new framework that uses a combination of data extraction and ant colony optimization to collect heart disease such as early heart attacks to protect them and reduce mortality rates. This study focused on the formulation and implementation of an improved and reliable model for the diagnosis of heart attack disease with a sophisticated approach to data extraction, the Ant Colony Optimization technique. To do this, we first took the generated support, which will be used as the symptom weight, which will be the initial value of the pheromone. There are many types of heart disease that can be considered here Congenital Heart Disease Congestive Heart Failure Coronary Heart Disease. Based on the identified risk, we identify the maximum value of the pheromone; the maximum value of the pheromone is the addition of weight and risk level. The next step of the ant is to find the maximum value of the pheromone, as the sensitive ant movements and the ratio of the symptoms will change. With this approach, the number of fragments can be managed via the ACO parameter. Then we find the precision and the memory. With this approach we want to achieve higher recognition accuracy