Assessment of the Heart Disease Using Soft Computing Methodology

Abstract

The techniques behind Data mining play a significant task in health care field. The techniques are mainly involved in prediction-based computing. A wide variety of algorithms are available in data mining. Data mining has many modern data analysis techniques like classification and prediction which may be utilized for this purpose. Classification is a data mining approach that allocates items in a group to target categories or classes. It also may be used to label a target item into any one of the classes identified. Among many available classification techniques, clustering is one of the unsupervised machine learning approaches that could be used for creating clusters as features to enhance classification models. There are various clustering algorithms available like K-mean clustering, AGNES clustering, etc. For disease prediction system K-means algorithm is used among all techniques available in prediction system. K-Mean algorithm creates clusters and groups of data properly. Many researchers have worked in the data clustering field and various clustering techniques have been used by them. In this work at first, Knowledge-based data are created by using factor analysis. After that K-mean algorithm is used on the result of knowledge-based data and different number of cluster points are assumed, then we get the Euclidean distance function with the simple matching dissimilarity measure. Once the cluster was formed, another method was used to forecast the resultant values of the data in the cluster. The proposed approach was tested on heart disease dataset and found efficient in this domain.