Open Learning Society
Untitled Document
     
  User Name :
  Password :
   
     
Untitled Document
   
  Adaptive Neuro-Fuzzy Inference System for Heart  Disease diagnosis
     
    International Conference on Infomration System, Computer Engineering & Application ( ICISCEA 2011 )
    © 2011 by OLS Journal - ISSN No : 2091- 0266
    Number 1
    Year of Publication : December Issue , 2011
    Authors : A.V.Senthil Kumar
  -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
  Citation A.V.Senthil Kumar : Adaptive Neuro-Fuzzy Inference System for Heart  Disease diagnosis : OLS Journals Special Isssue onInfomration System, Computer Engineering & Application , 2011 , Published by : OLS Journals
  -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
  Abstract  
 

   This paper presents a novel approach using  Adaptive Neuro-Fuzzy Inference System(ANFIS) to  estimate heart disease. ANFIS determines the  incompleteness in decision made by human experts using  hybrid as learning mechanism. A hybrid neural network  training was applied to diagnosis the heart disease. This  mechanism presents five layer, each layer has its own  nodes. The data were obtained from the University of  California at Irvine (UCI) machine learning repository.  The proposed method is tested with Cleveland heart  disease dataset. The ANFIS approach is implemented  using MATLAB. The result of the proposed methods is  compared with earlier method using accuracy as metrics.  The proposed Adaptive Neuro-Fuzzy Inference System is  effectively “hand crafted” to achieve the desired  performance and also improves the accuracy to diagnosis  the heart disease.
  -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
  Keywords

:Neuro fuzzy ANFIS; hybrid neural network;  heart disease
  References :  
 
  1.  Roan, S.-M., Chiang, C.-C. & Fu, H.-C, “ Fuzzy RCE neural network,  fuzzy systems”, In Second IEEE international conference on 28 March–1  April 1993 (pp. 629–634), Vol. 1.
  2.  J.-S.R. Jang, “ANFIS: adaptive network-based fuzzy inference system,”  IEEE Trans. Sys. Man. Cybern., vol. 23, pp. 665–685, 1993.
  3.  B. Kosko, “Fuzzy systems as universal approximators,” IEEE Trans.  Comput., vol. 43, no. 11, pp. 1329–1333, Nov. 1994.
  4. Serpen, G., Jiang, H. & Allred, L. G. (1997). Performance analysis of  probabilistic potential function neural network classifier. In Proceedings of artificial neural networks in engineering conference (pp. 471– 476), Vol. 7.
  5. S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd  ed.Prentice Hall, 1999.
  6.  Mukhopadhyay, S., Tang, C., Huang, J., Yu, M., & Palakal, M. (2002). A comparative study of genetic sequence classification algorithms, neural networks for signal processing. In Proceedings of the 2002 12th IEEE workshop on 4–6 September 2002, (pp. 57–66).
  7. Tang, Y., Jin, B., Sun,Y. & Zhang, Y.-Q. (2004). Granular support vector  machines for medical binary classification problems. In IEEE symposium on  computational intelligence in bioinformatics and computational biology (pp. 73–78).
  8.  Wang, S. (2005). Classification with incomplete survey data: A Hopfield  neural network approach. Computers & Operations Research, 32, 2583, 1594
  9.  Loo, C. K. (2005). Accurate and reliable diagnosis and classification using  probabilistic ensemble simplified fuzzy ARTMAP. IEEE Transactions on  Knowledge and Data Engineering, 17(11), November 2005.
  10.   Humar Kahramanli, Novruz Allahverdi(2008). Design of a hybrid system  for the Diabetes and heart diseases. Expert system with applications 35(2008)  82-89
  11.  Min Liu, Mingyu dong and Cheng Wu(2010). A New ANFIS for  Parameter Prediction with Numeric and Categorical Inputs. IEEE Transaction  on Automation Science and Engineering Vol. & No. 3 July 2010.
  12.  M. Forouzanfar, H. R. Dajani, V. Z. Groza, M. Bolic, and S. Rajan,  “Adaptive neuro-fuzzy inference system for oscillometric blood pressure  estimation,” in Proc. IEEE Int. Workshop MeMeA, Ottawa, Canada, Apr./May 2010, pp. 125–129.
  13.  Marcelo de Carvalho Alves, Edson Ampélio Pozza , João de Cássia do  Bonfim Costa, Luiz Gonsaga de Carvalho , Luciana Sanches Alves (2011).  Adaptive neuro-fuzzy inference systems for epidemiological analysis of  soybean rust, Environmental Modelling & Software 26 (2011) 1089e1096
  14.  Mehdi Fasanghari, Gholam Ali Montazer,( 2010)” Design and implementation of fuzzy expert system for Tehran Stock Exchange portfolio  recommendation” Expert Systems with Applications 37 PP 6138–6147
     
© Copyright 2011 Open Learning Society– All Rights Reserved