Three-Fold Integrated Clutsering-Classification (TICC) Strategy for Diabetes Mellitus Prediction

Authors

  • Dr. V. Saravanan  Associate Professor & Head, PG and Research Department of Information Technology, Hindusthan College of Arts and Science, Coimbatore, Tamil Nadu, India
  • Monika Seles  M. Phil Research Scholar, Hindusthan College of Arts and Science, Coimbatore, Tamil Nadu, India

Keywords:

MLT, Diabetes Mellitus, Classification, Clustering

Abstract

MLT finds potentially useful patterns in the data. Three MLT deployed for the diabetes mellitus prediction is presented subsequently with a brief on proposed method, experimental set up, test results and performance comparison. The proposed classifiers are tested with the original dataset. The results are recorded first. Subsequently the dataset will be subject to cluster and the this will be the first fold of the proposed technique. In the expansion step the assigned cluster will be a separate instance in the dataset. This will be the second fold of the proposed technique. Classification will be deployed as the third fold of the proposed technique. This proposed three fold integrated clustering-classification technique for diabetes mellitus prediction significantly improves the performance of the diabetes mellitus prediction. After the proposed strategy is carried out, results are recorded and compared.

References

  1. Raj Anand, Vishnu Pratap Singh Kirar, Kavita Burse, " K-Fold Cross Validation and Classification Accuracy of PIMA Indian Diabetes Data Set Using Higher Order Neural Network and PCA ", IJSCE, Volume-2, Issue-6, January 2013, pp. 436-438, ISSN: 2231-2307.
  2. Y. Angeline Christobel, P.Sivaprakasam, "A New Classwise k Nearest Neighbor (CKNN) Method for the Classification of Diabetes Dataset", IJEAT, Volume-2, Issue-3, February 2013, pp. 396-400, ISSN: 2249 – 8958.
  3. Pujari A. K. et al. (2012). Improving Classification Accuracy by Using Feature Selection and Ensemble Model. International Journal of Soft Computing and Engineering (IJSCE). International Journal of Soft Computing and Engineering (IJSCE)Vol. 2,pp. 380-386.
  4. Han, J.,& Micheline, K. (2006). Data mining: Concepts and Techniques, Morgan Kaufmann .Publisher.
  5. UCI Repository of Machine Learning Databases, University of California at Irvine, Department of Computer Science. Available: http://www.ics.uci.edu/~mlearn/databases/thyroid -disease/newthyroid.data
  6. Bishop, C. M. (1995). Neural Networks for Pattern Recognition. Oxford University Press, New York.
  7. Bolli, G. (2006). Glucose variability and complications. Diabetes Care, 29(7):1707–1709.Box, G., Jenkins, G., and Reinsel, G. (2008). Time Series Analysis: Forecasting and Control. John Wiley, Hoboken, New Jersey, fourth edition.
  8. Burges, C. (1998). A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2(2):121–167.
  9. Cao, L. and Tay, F. (2003). Support vector machine with adaptive parameters in financial time series forecasting. IEEE Transactions on Neural Networks, 14(6):1506–1518.
  10. "Diagnosis & Classification of Diabetes Mellitus", Diabetes Care, Volume 37, Supplement 1, 2014, pp. S81-S90.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2017-08-31

Issue

Volume 2, Issue 4, July-August-2017

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Dr. V. Saravanan, Monika Seles, " Three-Fold Integrated Clutsering-Classification (TICC) Strategy for Diabetes Mellitus Prediction, IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 2, Issue 4, pp.700-708, July-August-2017.