Green Computing Process and its Optimization Using Machine Learning Algorithm in Healthcare Sector

Abstract

Handling the information is crucial task in healthcare sector; the data mining techniques will be right choice to address the complex problems. The hybridized optimization techniques in big data analytics consider the important part of the healthcare network communication issues in decision making approach of patient information. This article focused on heart disease data mining and relevant issues since the heart diseases are considered as a reason for causing deaths just as for males and females all over the world. So, people need to be conscious of possible aspects of heart disease. Even though genetics has a part, some of the standards of living practiced are the fundamental reasons for the heart disease. The heart diseases are classified by classical techniques with 13 risk factors and helpful variables. The introduced approach delivers a new computing hybrid modeling scheme for detect the heart diseases. This study represents, various existing methods making decisions for cardio vascular risks depends on the artificial neural networks (ANN). This ANN based methods generally anticipated that Heart Failure attributes having same risk involvement to the heart failure diagnosis. In this article the strategy of an effective recognition method is analyzed for analyzing the failure related to heart diseases using a hybridized approach of K-Nearest Neighbor clustering and Spiral optimization in the classification of the cardio vascular risks. The hybridized KNN technique is matched with some data mining techniques like Support vector Machine (SVM), Convolutional Neural Networks (CNN), and Artificial Neural Networks (ANN). The experimental results of this work achieved optimized improved results significantly than other machine learning techniques. The illustrative results exposed that the hybrid scheme stated effectually classify heart disease in the way of computing optimized prediction of heart diseases. Overall the proposed algorithm evidence 5% of enhancement in prediction of heart diseases with comparison of other existing machine learning techniques.