This paper is published in Volume-3, Issue-2, 2017
Area
Big Data
Author
Subhapriya. P
Co-authors
R. Sujatha, K. Meghana
Org/Univ
Sri Manakula Vinayagar Engineering College, Puducherry, India
Pub. Date
29 March, 2017
Paper ID
V3I2-1255
Publisher
Keywords
Big Data, Data Mining, Random Forest Classifier, Healthcare, Knowledge Discovery in Database.

Citationsacebook

IEEE
Subhapriya. P, R. Sujatha, K. Meghana. Healthcare Prediction Analysis in Big Data using Random Forest Classifier, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Subhapriya. P, R. Sujatha, K. Meghana (2017). Healthcare Prediction Analysis in Big Data using Random Forest Classifier. International Journal of Advance Research, Ideas and Innovations in Technology, 3(2) www.IJARIIT.com.

MLA
Subhapriya. P, R. Sujatha, K. Meghana. "Healthcare Prediction Analysis in Big Data using Random Forest Classifier." International Journal of Advance Research, Ideas and Innovations in Technology 3.2 (2017). www.IJARIIT.com.

Abstract

An infrastructure build in the big data platform is reliable to challenge the commercial and not- commercial IT development communities of data streams in high dimensional data cluster modeling. The knowledge discovery in database (KDD) is alarmed by the development of methods and techniques for making use of data. The data size is generally growing from day to day. One of the most important steps of the KDD is the data mining which is the ability to extract useful knowledge hidden in this large amount of data. Both the data mining and healthcare industry have emerged some of reliable early detection systems and other various healthcare related systems from the clinical and diagnosis data. In this paper propose the enhanced data mining algorithm for healthcare application. It consists of three steps they are anomaly detection, clustering, and classification. In this classification algorithm use the random forest algorithm for accurately predict the patient result from a large amount of data. Finally, our experimental result shows our proposed method can achieve more accuracy result.
Paper PDF