Co- Disease Prediction using Multileyer Perceptron and Classification from Diabetic Medical Data Sets

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Artificial Neural Networks (ANN) techniques have the important concepts those can be used in the present scenario of the medical world. It has made the medical field to formulate easy steps to detect and predict the diseases like diabetes, thrombocytopenia, heart diseases, brain tumor, cancer etc. The classification methods available in the data mining theories and ANN gradually help to predict the data for the future analysis by building the classification models. In this paper, the results and the research work carried out on diabetic medical data using the artificial neural network algorithms like multilevel perception and its application over such data so as to predict the      diseases are discussed. The rules developed will be helpful to detect the co-disease in the diabetic patients and we have ranked them as per the final classifier for prediction. The proposed classification algorithm has accurately predicted the data with and without feature subset selection.



  • Keywords

    ANN, classification methods, final classifier ,co-disease and multilevel perceptron

  • References

      ] Hastie, Trevor. Tibshirani, Robert. Friedman, Jerome. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, New York, NY, 2009.

      [2] M.A.Jabbar, B.L.Deekshatulu, Priti Chandra,” anevolutionary algorithm for heart disease prediction,CCIS pp 378-389 Springer Verlag 2012.

      [3] M.Ambarasi et al,”Enhanced prediction of heart diseases with feature subset selection using genetic algorithm”IJEST Vol 2(10) pp 5370-5376(2010)

      [4] Symptoms of low bold sugar webMD from original on 18 june 2016,Retrieved 29 June 2016.

      [5] Rochester, N.; J.H. Holland; L.H. Habit; W.L. Duda (1956). "Tests on a cell assembly theory of the action of the brain, using a large digital computer". IRE Transactions on Information Theory. 2 (3): 80–93. doi:10.1109/TIT.1956.1056810

      [6] Ciresan, Dan; Giusti, Alessandro; Gambardella, Luca M.; Schmidhuber, Juergen (2012). Pereira, F.; Burges, C. J. C.; Bottou, L.; Weinberger, K. Q., eds. Advances in Neural Information Processing Systems 25 (PDF). Curran Associates, Inc. pp. 2843–2851.

      [7] Chen, Bo; Polatkan, Gungor (2011). "The Hierarchical Beta Process for Convolutional Factor Analysis and Deep Learning" (PDF). Machine Learning .

      [8] M.A.Jabbar, B.L.Deekshatulu, Priti Chandra,

      “Cluster based association rule mining for heart diseaseprediction, JATIT, Vol 32 no 2 October (2011).

      [9] Niti Guru, Anil Dahiya, Navin Rajpal, "Decision Support System for Heart Disease Diagnosis Using Neural Network", Delhi Business Review, Vol. 8, No. 1 (January - June 2007).

      [10] Definition and diagnosis of Diabetes Millitus and Intermediate Hyperglycemia, report of WHO/IDE,2006 P:21 ISBN 978-92-4- 159493-6

      [11] Sellappan Palaniappan, Rafiah Awang, "Intelligent Heart Disease Prediction System Using Data Mining Techniques", IJCSNS International Journal of Computer Science and Network Security, Vol.8 No.8, August 2008

      [12] Da, Y.; Xiurun, G. (July 2005). T. Villmann, ed. An improved PSO-based ANN with simulated annealing technique. New Aspects in Neurocomputing: 11th European Symposium on Artificial Neural Networks. Elsevier. doi:10.1016/j.neucom.2004.07.002Education and Counseling 53, 309–313.




Article ID: 20450
DOI: 10.14419/ijet.v7i4.6.20450

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.