Open Access Open Access  Restricted Access Subscription Access

Design and Performance Analysis of MLP NN Based Binary Classifier for Heart Diseases


Affiliations
1 P. G. Department of Applied Electronics, SGB Amravati University, Amravati- 444602 (M.S.), India
 

Experiments with the Switzerland heart disease database have concentrated on attempting to distinguish presence and absence. The classifiers based on various neural networks, namely, MLP, PCA, Jordan, GFF, Modular, RBF, SOFM, SVM NNs and conventional statistical techniques such as DA and CART are optimally designed, thoroughly examined and performance measures are compared in this study. With chosen optimal parameters of MLP NN, when it is trained and tested over cross validation (unseen data sets), the average (and best respectively) classification of 98±2.83 % (and 100%), 96.67±4.56% overall accuracy, sensitivity 96±5.48, specificity 100% are achieved which shows consistent performance than other NN and statistical models. The results obtained in this work show the potentiality of the MLP NN approach for heart diseases classification.

Keywords

Heart Disease, MLP Neural Network, Error Back Propagation Algorithm, Performance
User

  • Akhbardeh A, Junnila S, Koivuluoma M, Koivistoinen T and Varri A (2005) The heart disease diagnosing system based on force sensitive chair's measurement,
  • Bishop C (1997) Neural networks for pattern recognition. Oxford University Press, New York.
  • Bonow, Libby, Mann and Zipes (2006) Heart disease: a textbook of cardiovascular medicine, 8th edition, Saunders, Elsevier.
  • Bose NK and Liang P (2001) Neural network fundamentals with graphs, algorithms, and applications. Tata McGraw- Hill Publ. Company Ltd., New Delhi.
  • Hagan MT, Demuth HB and Beale MH (1997) Neural network design. PWS Publ., Boston, MA.
  • Haykin S (2007) Neural network: a comprehensive foundation. Pearson Prentice Hall, New Delhi.
  • Lippmann RP (1987) An introduction to computing with neural nets. IEEE ASSP Magazine. pp:4-22.
  • Mathers CD, Lopez A and Stein D (2004) Deaths and disease burden by cause: global burden of disease estimates by World Bank Country Groups.
  • MATLAB (2008) Neural networks toolbox users guide. The Math Works, Inc., Natick, MA.
  • Murphy PM and Aha DW (2004) UCI machine learning databases repository. Univ. of California Irvine C.A., Dept. of Info. & Computer Sci. ftp://ftp.ics.uci.edu/pub/ machine-learningdatabases/heart/
  • Neurosolution version 5.07 (2007) Neuro dimension. Gainesville Inc., Florida, (USA).
  • Principe J, Euliano N and Lefebvre C (1999) Neural and adaptive systems: fundamentals through simulations, John Wiley & Sons.
  • Reyneri LM (2003) Implementation issues of neuro- fuzzy hardware: going towards HW/SW co design. IEEE Trans. on Neural Networks. 14 (1), 176-194.
  • Tokan Fikret , Türker Nurhan and Yıldırım Tülay (2006) ROC analysis as a useful tool for performance evaluation of artificial neural networks. Lecture Notes in Computer Sci., Springer Berlin Publ., Heidelberg, ISSN 0302- 9743 (Print) 1611-3349 (Online), Vol. 4132/2006, Book Artificial Neural Networks– ICANN

Abstract Views: 421

PDF Views: 85




  • Design and Performance Analysis of MLP NN Based Binary Classifier for Heart Diseases

Abstract Views: 421  |  PDF Views: 85

Authors

Ranjana Raut
P. G. Department of Applied Electronics, SGB Amravati University, Amravati- 444602 (M.S.), India
S. V. Dudul
P. G. Department of Applied Electronics, SGB Amravati University, Amravati- 444602 (M.S.), India

Abstract


Experiments with the Switzerland heart disease database have concentrated on attempting to distinguish presence and absence. The classifiers based on various neural networks, namely, MLP, PCA, Jordan, GFF, Modular, RBF, SOFM, SVM NNs and conventional statistical techniques such as DA and CART are optimally designed, thoroughly examined and performance measures are compared in this study. With chosen optimal parameters of MLP NN, when it is trained and tested over cross validation (unseen data sets), the average (and best respectively) classification of 98±2.83 % (and 100%), 96.67±4.56% overall accuracy, sensitivity 96±5.48, specificity 100% are achieved which shows consistent performance than other NN and statistical models. The results obtained in this work show the potentiality of the MLP NN approach for heart diseases classification.

Keywords


Heart Disease, MLP Neural Network, Error Back Propagation Algorithm, Performance

References





DOI: https://doi.org/10.17485/ijst%2F2009%2Fv2i8%2F29508