ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

THE STATE OF THE ART CARDIAC ILLNESS PREDICTION USING NOVEL DATA MINING TECHNIQUE

Journal: International Journal of Engineering Sciences & Research Technology (IJESRT) (Vol.7, No. 2)

Publication Date:

Authors : ; ;

Page : 725-739

Keywords : Data Mining; CHARM; Clustering; C5.0; K-Means; Medical Data; Classification;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Data Mining is an analytic process designed to find out data in search of harmonious patterns and methodical relationships between variables, and then to validate the extractive by applying the detected patterns to new subsets of data. The data mining is defined as the procedure of extracting information from enormous sets of data. In other words, we can say that data mining is mining knowledge from data. Afore, the scope of data mining has thoroughly been reviewed and surveyed by many researchers pertaining to the domain of healthcare industry which is an active interdisciplinary area of research. Actually, the task of knowledge extraction from the healthcare industry in medical data is a challenging effort and it is a very complex task. The present scenario in healthcare industry heart illness is a term that assigns to a huge number of health care circumstances related to heart. These medical situations relate to the unexpected health situation that straight control the cardiac. In healthcare industry data mining techniques like association rule mining, regression, classification, clustering is implemented to analyze the different kinds of cardiac based issue. Data mining techniques have the capabilities to explore hidden patterns or relationships among the objects in the medical data. In this paper we are using CHARM, an efficient algorithm for mining all frequent closed item set. The data classification is based on CHARM algorithms which result in accuracy, the data are estimated using entropy based cross validations and partition techniques and the results are compared. Subsequently, C5 algorithm is used as the training algorithm to show the rank of cardiac illness with the decision tree. The cardiac illness database is clustered using the K-means clustering algorithm, which will alienate the data appropriate to heart attackfrom the database.

Last modified: 2018-02-28 21:01:13