Open Access Open Access  Restricted Access Subscription or Fee Access

Diagnose The Type II Diabetes Using Feed Forward Back Propagation Neural Networks

T. Jayalakshmi, Dr. A. Santhakumaran

Abstract


Diabetes mellitus is the most endocrine disease. This paper presents an optimum back propagation algorithm with analysis and its benefits for diagnosing the Type II diabetes. The Levenberg Marquadrt back propagation approach is used to analyze the convergence of back propagation with the following methods 1) selection of activation function to diagnose the diabetes mellitus 2) finding the optimal number of hidden layers to improve the performance of the system. The study has tested with 768 data, from that 268 are having diabetes. The performance of the proposed method is demonstrated by comparing the results of various activation functions in terms of accuracy and identifying the number of hidden layers in terms of minimum CPU time. It proves that 100% accuracy to be achieved when using specific combination of activation functions. Out of this hyperbolic tan sigmoid function with two hidden layer always produce accurate result with minimum number of epochs.

Keywords


Activation function, Back propagation neural networks, Diabetes mellitus, Levenberg Marquardt method.

Full Text:

PDF

References


Chengwei Li, Ruiqiang Hu, “Pid control based on BP neural network for the regulation of blood glucose level in diabetes”, IEEE 2007, pp.1168-1172.

H.M.Fonseca, A.I.Cabrera, J.I.Chairez, “Neuro tracking control for glucose-insulin interaction model”, IEEE 2nd ICEEE and XI conference on electrical engineering, Sep 7-9, 2005, pp.451-454.

Humberto M.Fonseca, Victor H.Oritz, Agustin I Cabrera, “Stochastic neural networks applied to dynamic glucose model for diabetes patients” IEEE 1st international conference on Electrical and Electronics Engineering, 2004, pp.522-525.

L.Zhou, X.Yang, “Use of neural network for land cover classification from remotely sensed imagery”, the international archives of the photogrammetry, remote sensing and spatial information sciences, Vol.XXXVII, part B7, 2008.

Md.Monirul Islam, Md.Shahjahan and K.Murase, “Exploring constructive algorithms with stopping criteria to produce accurate and diverse individual neural networks in an ensemble”, IEEE 2001, pp.1526-1531.

Mohamed Soltane, Mahamod Ismail, Zainol Abidin Abdul Rashid, “Artificial Neural Networks (ANN) Approach to PPG Signal Classification”, International journal of computing and information Sciences, Vol.2, No1, April 2004.

N.M.NAwi, M.R. Ransing, and R.S.Ransing, “An Improved Learning Algorithm based on the Conjugate Gradient Method for Back Prooagation Neural Networks”, Proc of World Academy of Science, Eng, and Technology, Vol 14, Aug 2006.

N.M.Nawi, R.S.Ransing, M.R.Ransing, “An improved conjugate gradient based learning algorithm for BP neural networks”, Int.Jouranl of computational intelligence, 2008.

D.Shanthi, Dr.G.Sahoo, Dr.N.Saravanan, “Input feature selection using Hybrid Neuro Genetic Approach in the diagnosis of stroke Disease” , IJCSNS, Vol 8, No 12, Dec 2008

Shibendra pobi and Lawrence O.Hall, “Predicting juvenile diabetes from clinical test results”, IEEE international joint conference on neural networks, Jul16-21, 2006,pp.2159-2165.

Siti Farhnah, Bt Jaafar and Darmawaty Mohd Ali, “Diabetes mellitus forcast using neural network”, IEEE Asian conference on sensors and the international conference on new techniques in biomedical research, Sep 5-7, 2005, pp.135-139.

Syed Muhammed Aquil Burbey, Tahseen Ahmed Jilani, Cemel Ardil, “Levenberg Marquadrt Algorithm for Karachi Stock Exchange Share Rates Forecasting”, Proc of World Academy of Science, Engineering and Technology, Jan 2005, pp.171-175.

Suman Ahmmed, Khondaker Abdllah-Al-Mamun, Monirul Islam, “A novel Algorithm for Designing Three Layered Artificial Neural Networks”, Int Journal of Soft computing, 2(3), 450-458, 2007.

R.Sivakumar, “ Neural Network based Diabetic Retinopathy Calssification Using Phase spectral Periodicity components”, ICGST-BIME Journal, Vol 7, Issue 1, May 2007.

V.P.Plagianakos, D.G.Sotiropoulos, M.N.Vrahatis, “An Improved Backpropagation Method with Adaptive Learning Rate”, Computational Mathematics &Informatics, University of Patras, Technical Report No.TR98-02.

Zhi-Hua Zhou, Yuan Jiang Jiang, “Medical diagnosis with C4.5 rule preceded by artificial neural network ensemble”, IEEE Trans on information technology in biomedicine, Vol 7, No.1 March 2003, pp.37-42.

Z.Zainuddin, N. Mahat, and Y. Abu Hassan, “Improving the Convergence of the Back propagation Algorithm Using Local Adaptive Techniques”, Proc of World Academy of Science, Eng, and Technology, Vol 1, Jan 2005.


Refbacks

  • There are currently no refbacks.