Prediction of Diabetes using Ensemble Techniques
Prema N S1, Varshith V2, Yogeswar J3
1Prema N S, Department of Information Science and Engineering, Vidyavardhaka College of Engineering, Mysuru (Karnataka), India.
2Varshith V, Department of Information Science and Engineering, Vidyavardhaka College of Engineering, Mysuru (Karnataka), India.
3Yogeswar J, Department of Information Science and Engineering, Vidyavardhaka College of Engineering, Mysuru (Karnataka), India.
Manuscript received on 29 April 2019 | Revised Manuscript received on 11 May 2019 | Manuscript Published on 17 May 2019 | PP: 660-662 | Volume-7 Issue-6S4 April 2019 | Retrieval Number: F11360476S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In the recent decades, there has been a significant improvement in the quality and quantity of medical data that is produced by digital devices. This has led to inexpensive and easy production of data. Thus, there has been an increased advantage in the areas of Big Data and Machine Learning. In this paper, various machine learning algorithms are applied to predict diabetes, based on specific attributes. The performances of the algorithms are compared in terms of accuracy, voting based ensemble techniques is applied for the normalized pima diabetes data for which a highest accuracy is achieved.
Keywords: Diabetes, Ensemble Classifier, Voting Classifiers, SVM.
Scope of the Article: Regression and Prediction