Numerical solution of nonlinear singular initial value problems of Emden-Fowler type using Chebyshev Neural Network method

In this investigation, a new algorithm has been proposed to solve singular initial value problems of Emden-Fowler type equations. Approximate solutions of these types of equations have been obtained by applying Chebyshev Neural Network (ChNN) model for the first time. The Emden-Fowler type equations are singular in nature. Here, we have considered single layer Chebyshev Neural Network model to overcome the difficulty of singularity. The computations become efficient because the procedure does not need to have hidden layer. A feed forward neural network model with error back propagation principle is used for modifying the network parameters and to minimize the computed error function. We have compared analytical and numerical solutions of linear and nonlinear Emden-Fowler equations respectively with the approximate solutions obtained by proposed ChNN method. Their good agreements and less CPU time in computations than the traditional artificial neural network (ANN) show the efficiency of the present methodology.

[1]  Abdul-Majid Wazwaz,et al.  A new algorithm for solving differential equations of Lane-Emden type , 2001, Appl. Math. Comput..

[2]  M. Buscema,et al.  Introduction to artificial neural networks. , 2007, European journal of gastroenterology & hepatology.

[3]  Huseyin Demir,et al.  Numerical Solution of a Class of Nonlinear Emden-Fowler Equations by Using Differential Transform Method , 2009 .

[4]  J C Patra,et al.  Chebyshev Neural Network-Based Model for Dual-Junction Solar Cells , 2011, IEEE Transactions on Energy Conversion.

[5]  Ben Muatjetjeja,et al.  Conservation laws for a generalized coupled bidimensional Lane-Emden system , 2013, Commun. Nonlinear Sci. Numer. Simul..

[6]  Dan Givoli,et al.  Neural network time series forecasting of finite-element mesh adaptation , 2005, Neurocomputing.

[7]  Dimitris G. Papageorgiou,et al.  Neural-network methods for boundary value problems with irregular boundaries , 2000, IEEE Trans. Neural Networks Learn. Syst..

[8]  Ben Muatjetjeja,et al.  Exact solutions of the generalized Lane–Emden equations of the first and second kind , 2011 .

[9]  Abdul-Majid Wazwaz,et al.  Adomian decomposition method for a reliable treatment of the Emden-Fowler equation , 2005, Appl. Math. Comput..

[10]  Takasi Kusano,et al.  Asymptotic behavior of positive solutions of sublinear differential equations of Emden-Fowler type , 2011, Comput. Math. Appl..

[11]  Mohsen Hayati,et al.  Multilayer perceptron neural networks with novel unsupervised training method for numerical solution of the partial differential equations , 2009, Appl. Soft Comput..

[12]  Martti Juhola,et al.  Intelligent sensors using computationally efficient Chebyshev neural networks , 2008 .

[13]  S. Karimi Vanani,et al.  On the numerical solution of differential equations of Lane-Emden type , 2010, Comput. Math. Appl..

[14]  D. Parisi,et al.  Solving differential equations with unsupervised neural networks , 2003 .

[15]  Nam Mai-Duy,et al.  Numerical solution of differential equations using multiquadric radial basis function networks , 2001, Neural Networks.

[16]  Juan I. Ramos,et al.  Linearization techniques for singular initial-value problems of ordinary differential equations , 2005, Appl. Math. Comput..

[17]  Md. Sazzad Hossien Chowdhury,et al.  Solutions of Emden-Fowler equations by homotopy-perturbation method , 2009 .

[18]  Mohd. Salmi Md. Noorani,et al.  Homotopy analysis method for singular IVPs of Emden–Fowler type , 2009 .

[19]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[20]  K. S. Govinder,et al.  Integrability analysis of the Emden-Fowler equation , 2007 .

[21]  O. P. Singh,et al.  An analytic algorithm of Lane-Emden type equations arising in astrophysics using modified Homotopy analysis method , 2009, Comput. Phys. Commun..

[22]  S. A. Hoda On Neural Network Methods for Mixed Boundary Value Problems , 2011 .

[23]  Ali H. Bhrawy,et al.  A Jacobi–Gauss collocation method for solving nonlinear Lane–Emden type equations , 2012 .

[24]  B. K. Datta RETRACTED ARTICLE: Analytic solution to the Lane-Emden equation , 1996 .

[25]  M. Dehghan,et al.  Approximate solution of a differential equation arising in astrophysics using the variational iteration method , 2008 .

[26]  Alaeddin Malek,et al.  Numerical solution for high order differential equations using a hybrid neural network - Optimization method , 2006, Appl. Math. Comput..

[27]  Lucie P. Aarts,et al.  Neural Network Method for Solving Partial Differential Equations , 2001, Neural Processing Letters.

[28]  Manoj Kumar,et al.  Multilayer perceptrons and radial basis function neural network methods for the solution of differential equations: A survey , 2011, Comput. Math. Appl..

[29]  Andrew J. Meade,et al.  Solution of nonlinear ordinary differential equations by feedforward neural networks , 1994 .

[30]  R. Fowler FURTHER STUDIES OF EMDEN'S AND SIMILAR DIFFERENTIAL EQUATIONS , 1931 .

[31]  J. Abdul Samath,et al.  Solution of matrix Riccati differential equation for nonlinear singular system using neural networks , 2010 .

[32]  H. J. Lane On the theoretical temperature of the Sun, under the hypothesis of a gaseous mass maintaining its volume by its internal heat, and depending on the laws of gases as known to terrestrial experiment , 1870, American Journal of Science and Arts.

[33]  Hadi Sadoghi Yazdi,et al.  Unsupervised kernel least mean square algorithm for solving ordinary differential equations , 2011, Neurocomputing.

[34]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[35]  Kevin Stanley McFall,et al.  Artificial Neural Network Method for Solution of Boundary Value Problems With Exact Satisfaction of Arbitrary Boundary Conditions , 2009, IEEE Transactions on Neural Networks.

[36]  Andrew J. Meade,et al.  The numerical solution of linear ordinary differential equations by feedforward neural networks , 1994 .

[37]  Tsu-Tian Lee,et al.  The Chebyshev-polynomials-based unified model neural networks for function approximation , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[38]  I. Hashim,et al.  Solutions of a class of singular second-order IVPs by homotopy-perturbation method , 2007 .

[39]  Indra Narayan Kar,et al.  On-line system identification of complex systems using Chebyshev neural networks , 2007, Appl. Soft Comput..

[40]  Siwei Luo,et al.  Numerical solution of elliptic partial differential equation using radial basis function neural networks , 2003, Neural Networks.

[41]  Snehashish Chakraverty,et al.  Regression-based neural network training for the solution of ordinary differential equations , 2013, Int. J. Math. Model. Numer. Optimisation.

[42]  Abdul-Majid Wazwaz,et al.  The modified decomposition method for analytic treatment of differential equations , 2006, Appl. Math. Comput..

[43]  Fazal M. Mahomed,et al.  Solution of generalized emden-fowler equations with two symmetries , 1994 .

[44]  Dimitrios I. Fotiadis,et al.  Artificial neural networks for solving ordinary and partial differential equations , 1997, IEEE Trans. Neural Networks.

[45]  Alex ChiChung Kot,et al.  Nonlinear dynamic system identification using Chebyshev functional link artificial neural networks , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[46]  Shijun Liao,et al.  A new analytic algorithm of Lane-Emden type equations , 2003, Appl. Math. Comput..

[47]  H. Davis Introduction to Nonlinear Differential and Integral Equations , 1964 .

[48]  Wan-De Weng,et al.  A channel equalizer using reduced decision feedback Chebyshev functional link artificial neural networks , 2007, Inf. Sci..