Abstract
In this paper, fuzzy neural network (FNN) can be trained with crisp and fuzzy data. The work of this paper is an expansion of the research of fuzzy linear Fredholm integro-differential equations. In this work, we interpret a fuzzy integro-differential equations. In this paper, a novel hybrid method based on FNN and Newton–Cotes methods with positive coefficient for the solution of system of fuzzy linear Fredholm integro-differential equations of the second kind with fuzzy initial values is presented. The problem formulation of the proposed UA is quite straightforward. To obtain the “best-approximated” solution of system of fuzzy linear Fredholm integro-differential equations, the adjustable parameters of PFNN are systematically adjusted by using the learning algorithm. Within this paper, the fuzzy neural network model is used to obtain an estimate for the fuzzy parameters in a statistical sense. Based on the extension principle, a simple algorithm from the cost function of the fuzzy neural network is proposed, in order to find the approximate parameters. We propose a learning algorithm from the cost function for adjusting of fuzzy weights. Here neural network is considered as a part of a larger field called neural computing or soft computing. Finally, we illustrate our approach by some numerical examples.
Similar content being viewed by others
References
Abbasbandy S, Babolian E, Alavi M (2007) Numerical method for solving linear Fredholm fuzzy integral equations of the second kind. Chaos Solitons Fractals 31:138–146
Abbasbandy S, Otadi M (2006) Numerical solution of fuzzy polynomials by fuzzy neural network. Appl Math Comput 181:1084–1089
Abbasbandy S, Otadi M, Mosleh M (2008) Numerical solution of a system of fuzzy polynomials by fuzzy neural network. Inf Sci 178:1948–1960
Alefeld G, Herzberger J (1983) Introduction to interval computations. Academic Press, New York
Allahviranloo T, Ahmady E, Ahmady N (2008) Nth-order fuzzy linear differential eqations. Inf Sci 178:1309–1324
Allahviranloo T, Ahmady N, Ahmady E (2007) Numerical solution of fuzzy differential eqations by predictor-corrector method. Inf Sci 177:1633–1647
Atkinson KE (1987) An introduction to numerical analysis. Wiley, New York
Babolian E, Goghary HS, Abbasbandy S (2005) Numerical solution of linear Fredholm fuzzy integral equations of the second kind by Adomian method. Appl Math Comput 161:733–744
Bede B, Rudas IJ, Bencsik AL (2007) First order linear fuzzy differential eqations under generalized differentiability. Inf Sci 177:1648–1662
Bernard JF (1988) Use of rule-based system for process control. IEEE Control Syst Mag 8:3–13
Buckley JJ, Hayashi Y (1994) Can fuzzy neural nets approximate continuous fuzzy functions? Fuzzy Sets Syst 61:43–51
Buckley JJ, Hayashi Y (1994) Fuzzy neural networks. Fuzzy Sets Syst 66:1–13
Buckley JJ, Feuring T (2000) Fuzzy differential equations. Fuzzy Sets Syst 110:69–77
Chang SL, Zadeh LA (1972) On fuzzy mapping and control. IEEE Trans Syst Man Cybemet 2:30–34
Chen YC, Teng CC (1995) A model reference control structure using a fuzzy neural network. Fuzzy Sets Syst 73:291–312
Dubey G, Kumar Sh (2016) Improvement in the numerical method for integrating weight function of pre-cracked specimen. Eng Fract Mech 154:83–91
Dubois D, Prade H (1978) Operations on fuzzy numbers. J Syst Sci 9:613–626
Dubois D, Prade H (1982) Towards fuzzy differential calculus: part 3, differentiation. Fuzzy Sets Syst 8:225–233
Effati S, Pakdaman M (2010) Artificial neural network approach for solving fuzzy differential equations. Inf Sci 180:1434–1457
Fei W (2007) Existence and uniqueness of solution for fuzzy random differential equations with non-lipschitz coefficients. Inf Sci 177:4329–4337
Friedman M, Ma M, Kandel A (1999) Numerical solutions of fuzzy differential and integral equations. Fuzzy Sets Syst 106:35–48
Goetschel R, Voxman W (1986) Elementary fuzzy calculus. Fuzzy Sets Syst 18:31–43
Hayashi Y, Buckley JJ, Czogala E (1992) Fuzzy neural network with fuzzy signals and weights. Int J Intell Syst 8:527–537
Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall, New Jersey
Hochstadt H (1973) Integral equations. Wiley, New York
Hornick K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366
Ishibuchi H, Fujioka R, Tanaka H (1992) An architecture of neural networks for input vectors of fuzzy numbers. In: Proceedings of IEEE international conference on fuzzy systems, pp 1293–1300
Ishibuchi H, Kwon K, Tanaka H (1995) A learning algorithm of fuzzy neural networks with triangular fuzzy weights. Fuzzy Sets Syst 71:277–293
Ishibuchi H, Morioka K, Turksen IB (1995) Learning by fuzzified neural networks. Int J Approx Reason 13:327–358
Ishibuchi H, Nii M (2001) Numerical analysis of the learning of fuzzified neural networks from fuzzy if-then rules. Fuzzy Sets Syst 120:281–307
Ishibuchi H, Okada H, Tanaka H (1993) Fuzzy neural networks with fuzzy weights and fuzzy biases. In: Proceedings of ICNN 93, San Francisco, pp 1650–1655
Ishibuchi H, Tanaka H, Okada H (1993) Fuzzy neural networks with fuzzy weights and fuzzy biases. In: Proceedings of 1993 IEEE international conferences on neural networks, pp 1650–1655
Jin C, Ding J (2016) Solving Fredholm integral equations via a piecewise linear maximum entropy method. J Comput Appl Math 304:130–137
Kaleva O (1987) Fuzzy differential equations. Fuzzy Sets Syst 24:301–317
Khanna T (1990) Foundations of neural networks. Addison-Wesly, Reading
Klir GJ, Clair US, Yuan B (1997) Fuzzy set theory: foundations and applications. Prentice-Hall Inc., Upper Saddle River
Krishnamraju PV, Buckley JJ, Relly KD, Hayashi Y (1994) Genetic learning algorithms for fuzzy neural nets. In: Proceedings of IEEE international conference on fuzzy systems, pp 1969–1974
Lagaris IE, Likas A (1998) Artificial neural networks for solving ordinary and partial differential equations. IEEE Trans Neural Netw 9(5):987–1000
Lapedes A, Farber R (1988) How neural nets work? In: Anderson DZ (ed) Neural information processing systems. AIP, Melvillepp, pp 442–456
Leng G, Prasad G, McGinnity TM (2004) An on-line algorithm for creating self-organizing fuzzy neural networks. Neural Netw 17:1477–1493
Lin D, Wang X (2010) Observer-based decentralized fuzzy neural sliding mode control for interconnected unknown chaotic systems via network structure adaptation. Fuzzy Sets Syst 161:2066–2080
Lin D, Wang X (2011) Self-organizing adaptive fuzzy neural control for the synchronization of uncertain chaotic systems with random-varying parameters. Neurocomputing 74:2241–2249
Lin D, Wang X, Nian F, Zhang Y (2010) Dynamic fuzzy neural networks modeling and adaptive backstepping tracking control of uncertain chaotic systems. Neurocomputing 73:2873–2881
Lippmann RP (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4(2):4–22
Malek A, Shekari Beidokhti R (2006) Numerical solution for high order differential equations using a hybrid neural network-optimization method. Appl Math Comput 183:260–271
Mizukoshi MT, Barros LC, Chalco-Cano Y, Romn-Flores H, Bassanezi RC (2007) Fuzzy differential equations and the extention principle. Inf Sci 177:3627–3635
Mosleh M (2013) Fuzzy neural network for solving a system of fuzzy differential equations. Appl Soft Comput 13:3597–3607
Mosleh M (2014) Numerical solution of fuzzy linear Fredholm integro-differential equation by fuzzy neural network. Iran J Fuzzy Syst Iran J Fuzzy Syst 11:91–112
Mosleh M, Otadi M (2015) Numerical solutions of nonlinear fuzzy Fredholm integro-differential equations of the second kind. Iran J Fuzzy Syst 12:117–127
Mosleh M, Allahviranloo T, Otadi M (2012) Evaluation of fully fuzzy regression models by fuzzy neural network. Neural Comput Appl 21:105–112
Mosleh M, Otadi M (2012) Simulation and evaluation of fuzzy differential equations by fuzzy neural network. Appl Soft Comput 12:2817–2827
Mosleh M, Otadi M (2012) Minimal solution of fuzzy linear system of differential equations. Neural Comput Appl 21:329–336
Mosleh M, Otadi M, Abbasbandy S (2010) Evaluation of fuzzy regression models by fuzzy neural network. J Comput Appl Math 234:825–834
Mosleh M, Otadi M, Abbasbandy S (2011) Fuzzy polynomial regression with fuzzy neural networks. Appl Math Model 35:5400–5412
Otadi M (2014) Fully fuzzy polynomial regression with fuzzy neural networks. Neurocomputing 142:486–493
Otadi M, Mosleh M (2011) Simulation and evaluation of dual fully fuzzy linear systems by fuzzy neural network. Appl Math Model 35:5026–5039
Otadi M, Mosleh M (2016) Simulation and evaluation of interval-valued fuzzy linear Fredholm integral equations with interval-valued fuzzy neural network. Neurocomputing 205:519–528
Otadi M, Mosleh M, Abbasbandy S (2011) Numerical solution of fully fuzzy linear systems by fuzzy neural network. Soft Comput 15:1513–1522
Papaschinopoulos G, Stefanidou G, Efraimidis P (2007) Existence, uniquencess and asymptotic behavior of the solutions of a fuzzy differential equation with piecewise constant argument. Inf Sci 177:3855–3870
Picton P (2000) Neural networks, 2nd edn. Palgrave, Great Britain
Puri ML, Ralescu DA (1983) Differentials of fuzzy functions. J Math Anal Appl 91:552–558
Rodriguez-Lopez R (2008) Comparison results for fuzzy differential eqations. Inf Sci 178:1756–1779
Seikkala S (1987) On the fuzzy initial value problem. Fuzzy Sets Syst 24:319–330
Schalkoff RJ (1997) Artificial neural networks. McGraw-Hill, New York
Stanley J (1990) Introduction to neural networks. Scientific software, Pasadena, CA
Tung WL, Quek C (2002) A generic self-organizing fuzzy neural network. IEEE Trans Neural Netw 13:1075–1086
Wang X, Zhao J (2010) Cryptanalysis on a parallel keyed hash function based on chaotic neural network. Neurocomputing 73:3224–3228
Xingyuan W, Bing X, Huaguang Z (2010) A multi-ary number communication system based on hyperchaotic system of 6th-order cellular neural network. Commun Nonlinear Sci Numer Simul 15:124–133
Zadeh LA (1975) The concept of a liguistic variable and its application to approximate reasoning: parts 1–3. Inf Sci 8:199–249, 301–357; 9 (1975) 43–80
Zadeh LA (2008) Is there a need for fuzzy logic? Inf Sci 178:2751–2779
Zhang HG, Liu DR (2006) Fuzzy modeling and fuzzy control. Birhauser, Boston
Zhang HG, Quan YB (2001) Modeling, identification, and control of a class of nonlinear systems. IEEE Trans Fuzzy Syst 9:349–354
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
This work was supported by the Islamic Azad University Firoozkooh of Iran.
Appendices
Appendix 1
Definition 6.1
([21, 22]). Let \(f:[a,b]\longrightarrow E^1\), for each partition \(p=\{t_0,t_1,\ldots , t_n\}\) of [a, b] and for arbitrary \(\xi _i\in [t_{i-1},t_i],1\le i\le n\) suppose
The definite integral of f(t) over [a, b] is
provided that this limit exists in the metric D.
If the fuzzy function f(t) is continuous in the metric D, its definite integral exists [22] and also
Definition 6.2
Let \(u,v\in E^1\). If there exists \(w\in E^1\) such that \(u=v+w\) then w is called the H-difference of u, v and it is denoted by \(u-v.\)
Definition 6.3
A function \(f:(a,b)\longrightarrow E^1\) is called H-differentiable at \({\hat{t}}\in (a,b)\) if, for \(h>0\) sufficiently small, there exist the H-differences \(f({\hat{t}}+h)-f({\hat{t}}),f({\hat{t}})-f({\hat{t}}-h),\) and an element \(f^{\prime }({\hat{t}})\in E^1\) such that:
Then, \(f^{\prime }({\hat{t}})\) is called the fuzzy derivative of f at \({\hat{t}}.\)
Appendix 2: Derivation of a learning algorithm in PFNN
Let us denote the fuzzy connection weights \(V_{pj},\ p=1,\ldots ,n,\ j=1,\ldots ,m\) to the output unit by its parameter values as \(V_{pj}=(v_{pj}^{(1)},\ldots ,v_{pj}^{(q)},\ldots ,v_{pj}^{(r)})\). The amount of modification of each parameter value for problem (16) is written as [28]
where t indexes the number of adjustments, \(\eta\) is a learning rate (positive real number) and \(\alpha\) is a momentum term constant (positive real number).
Thus, our problem is to calculate the derivative \(\frac{\partial e_{ikh}}{\partial v_{pj}^{(q)}}\). Let us rewrite \(\frac{\partial e_{ikh}}{\partial v_{pj}^{(q)}}\) as follows:
In this formulation, \(\frac{\partial [V_{ij}]_h^{L}}{\partial v_{ij}^{(q)}}\) and \(\frac{\partial [V_{ij}]_h^{U}}{\partial v_{ij}^{(q)}}\) are easily calculated from the membership function of the fuzzy connection weight \(V_{ij}\).
On the other hand, the derivatives \(\frac{\partial e_{ikh}}{\partial [V_{ij}]_h^L}\) and \(\frac{\partial e_{ikh}}{\partial [V_{ij}]_h^U}\) are independent of the shape of the fuzzy connection weight. They can be calculated from the cost function \(e_{ikh}\) using the input–output relation of our fuzzy neural network for the h-level sets. When we use the cost function with the weighting scheme in (29), \(\frac{\partial e_{ikh}}{\partial [V_{pj}]_h^L}\) and \(\frac{\partial e_{ikh}}{\partial [V_{pj}]_h^U},\) are calculated as follows:
[Calculation of \(\frac{\partial e_{ikh}}{\partial [V_{pj}]_h^L}\)]
If \(i=p\) then we have
where
otherwise
[Calculation of \(\frac{\partial e_{ikh}}{\partial [V_{pj}]_h^U}\)]
If \(i=p\) then we have
where
otherwise
In our PFNN, the connection weights and biases to the hidden units are real numbers. The nonfuzzy connection weight \(w_{pj}\) to the jth hidden unit is updated in the same manner as the parameter values of the fuzzy connection weight \(V_{pj}\) as follows:
The derivative \(\frac{\partial e_{ikh}}{\partial w_{pj}}\) can be calculated from the cost function \(e_{ikh}\) using the input–output relation of our PFNN for the h-level sets. When we use the cost function with the weighting scheme, \(\frac{\partial e_{ikh}}{\partial w_{pj}}\) for \(i=p\) is calculated as follows:
where
The nonfuzzy \(w_{pj}\) for \(i\ne p\) and nonfuzzy biases to the hidden units are updated in the same manner as above.
Rights and permissions
About this article
Cite this article
Mosleh, M., Otadi, M. Simulation and evaluation of system of fuzzy linear Fredholm integro-differential equations with fuzzy neural network. Neural Comput & Applic 31, 3481–3491 (2019). https://doi.org/10.1007/s00521-017-3267-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-017-3267-2