Clustering Classification for Diabetic Patients using K-Means and M-Tree prediction model

Prateeksha Tomar¹ , Amit Kumar Manjhvar²

1. Dept. of CSE, Madhav Institute of Technology and Science, Gwalior, India.
2. Dept. of CSE, Madhav Institute of Technology and Science, Gwalior, India.

Correspondence should be addressed to: tomarprateeksha09@gmail.com.

Section:Research Paper, Product Type: Isroset-Journal
Vol.3 , Issue.6 , pp.48-53, Jun-2017

Online published on Jun 30, 2017

Copyright © Prateeksha Tomar, Amit Kumar Manjhvar . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

426 Views    284 Downloads    232 Downloads

Abstract :
Medicinal Data mining is the way in the direction of removing concealed examples from therapeutic data. This paper shows the advancement of a crossover model for ordering Pima Indian diabetic database (PIDD). The model comprises of two phases. In the primary stage, the K-means bunching is utilized to distinguish and take out erroneously grouped examples. The nonstop data is changed over to all out frame by rough width of the coveted interims, in light of the conclusion of restorative master. In the second stage an adjusted arrangement is finished utilizing M tree C4.5 by taking the accurately bunched event of first stage. Test comes about imply the fell K-means grouping and M tree C4.5 has upgraded arrangement precision of C4.5. Additionally administers produced utilizing fell C4.5 tree with clear cut data are less in numbers and simple to translate contrasted with principles created with C4.5 alone with persistent data. The proposed fell model with all out data got the arrangement precision of 93.33 % when contrasted with exactness of 73.62 % utilizing C4.5 alone for PIMA Indian diabetic dataset.

Key-Words / Index Term :
K-means clustering, Categorical data, rule based classification, M-tree, Pima Indian Diabetics

References :
[1] Polat K., Gunes S., Aslan A., “A cascade learning system for classification of diabetes disease: Generalized discriminant analysis and least square support vector machine. Expert Systems with Applications”, Expert systems with applications, Vol.34, Issue.1, pp. 214-221, 2008.
[2] B.M Patil, R.C Joshi, Durga Tosniwal, “Hybrid Prediction model for Type-2 Diabetic Patients, Expert System with Applications”, Expert systems with applications. , Vol.37, Issue.12, pp.8102-8108, 2010.
[3] J.R. Quinlan, “Induction of M Trees, Machine Learning”, Kluwer Academic Publishers, Boston, pp.81-106, 1986.
[4] J.Han, M. Kamber, “DataMining: Concepts and techniques”, Morgan Kauffman Publishers, San Francisco, pp.34-118, 2001.
[5] A. Shrivastava, S. Rajawat, "An Implementation of Hybrid Genetic Algorithm for Clustering based Data for Web Recommendation System", International Journal of Computer Sciences and Engineering, Vol.2, Issue.4, pp.6-11, 2014.
[6] Prateeksha tomar , Amit Kumar Manjhvar, “survey report On various decision tree classification algorithms using weka tool”, International journal of computer scienceandengineering,Vol.5, No. 3, pp.1-8, 2017.
[7] S. Joshi, F.U. Khan, N. Thakur, "Contrasting and Evaluating Different Clustering Algorithms: A Literature Review", International Journal of Computer Sciences and Engineering, Vol.2, Issue.4, pp.87-91, 2014.
[8] AG. Karegowda, MA. Jayaram, “Integrating M Tree and ANN for Categorization of Diabetics Data”, International Conference on Computer Aided Engineering, pp.9-15, India, 2007.
[9] K.Selvi, "Identify Heart Diseases Using Data Mining Techniques: an Overview", International Journal of Computer Sciences and Engineering, Vol.3, Issue.11, pp.180-187, 2015.
[10] P. Thangarajum B. Deepa, “A Case study on Perclusion and Discovery of Skin Melanoma Risk using Clustering Techniques”, International Journal of Advanced Research in Electronics and Communication Engineering (IJARECE), Volume 3, Issue 7, pp.76-82, 2014.
[11] Siti Farhanah, Bt Jaafar and Dannawaty, Mohd Ali, “Diabetes mellitus forecast using artificial neural networks”, Asian conference of paramedical research proceedings, Malaysia, pp.5-7, 2007.
[12] Karthika Jayprakash,Nidhi Kargathra, Pranay Jagtap,Suraj Shridhar and Archana Gupta, "Comparison of Classification Techniques for Heart Health Analysis System", International Journal of Computer Sciences and Engineering, Vol.4, Issue.2, pp.92-95, 2016.
[13] Priyanka, Sana Khan, Tulsi Kour, "Investigation on Smart Health Care Using Data Mining Methods", International Journal of Scientific Research in Computer Science and Engineering, Vol.4, Issue.2, pp.31-36, 2016.