{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T05:48:18Z","timestamp":1678427298661},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T00:00:00Z","timestamp":1678320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"In this study, we investigate a new neural network method to solve Volterra and Fredholm integral equations based on the sine-cosine basis function and extreme learning machine (ELM) algorithm. Considering the ELM algorithm, sine-cosine basis functions, and several classes of integral equations, the improved model is designed. The novel neural network model consists of an input layer, a hidden layer, and an output layer, in which the hidden layer is eliminated by utilizing the sine-cosine basis function. Meanwhile, by using the characteristics of the ELM algorithm that the hidden layer biases and the input weights of the input and hidden layers are fully automatically implemented without iterative tuning, we can greatly reduce the model complexity and improve the calculation speed. Furthermore, the problem of finding network parameters is converted into solving a set of linear equations. One advantage of this method is that not only we can obtain good numerical solutions for the first- and second-kind Volterra integral equations but also we can obtain acceptable solutions for the first- and second-kind Fredholm integral equations and Volterra\u2013Fredholm integral equations. Another advantage is that the improved algorithm provides the approximate solution of several kinds of linear integral equations in closed form (i.e., continuous and differentiable). Thus, we can obtain the solution at any point. Several numerical experiments are performed to solve various types of integral equations for illustrating the reliability and efficiency of the proposed method. Experimental results verify that the proposed method can achieve a very high accuracy and strong generalization ability.<\/jats:p>","DOI":"10.3389\/fncom.2023.1120516","type":"journal-article","created":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T04:46:11Z","timestamp":1678337171000},"update-policy":"http:\/\/dx.doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Approximate solutions to several classes of Volterra and Fredholm integral equations using the neural network algorithm based on the sine-cosine basis function and extreme learning machine"],"prefix":"10.3389","volume":"17","author":[{"given":"Yanfei","family":"Lu","sequence":"first","affiliation":[]},{"given":"Shiqing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Futian","family":"Weng","sequence":"additional","affiliation":[]},{"given":"Hongli","family":"Sun","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,3,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/S0096-3003(00)00118-1","article-title":"Fredholm-Volterra integral equation of the first kind and contact problem","volume":"125","author":"Abdou","year":"2002","journal-title":"Appl. Math. Comput"},{"key":"B2","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1134\/S0965542522010055","article-title":"Collocation-variational approaches to the solution to volterra integral equations of the first kind","volume":"62","author":"Bulatov","year":"2022","journal-title":"Comput. Math. Math. Phys"},{"key":"B3","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MIS.2013.140","article-title":"Extreme learning machine: trends and controversies","volume":"28","author":"Cambria","year":"2013","journal-title":"IEEE Intell. Syst"},{"key":"B4","doi-asserted-by":"publisher","first-page":"103757","DOI":"10.1016\/j.dsp.2022.103757","article-title":"Numerical solving for generalized Black-Scholes-Merton model with neural finite element method","volume":"131","author":"Chen","year":"2022","journal-title":"Digit. Signal Process"},{"key":"B5","doi-asserted-by":"publisher","first-page":"876","DOI":"10.3390\/sym12060876","article-title":"Solution of ruin probability for continuous time model based on block trigonometric exponential neural network","volume":"12","author":"Chen","year":"2020","journal-title":"Symmetry"},{"key":"B6","doi-asserted-by":"publisher","first-page":"103003","DOI":"10.1016\/j.dsp.2021.103003","article-title":"Numerical solving of the generalized Black-Scholes differential equation using Laguerre neural network","volume":"112","author":"Chen","year":"2021","journal-title":"Digit. Signal Process"},{"key":"B7","doi-asserted-by":"publisher","first-page":"3283","DOI":"10.1016\/j.apm.2011.10.005","article-title":"Numerical solution of Volterra-Fredholm integral equations by moving least square method and Chebyshev polynomials","volume":"36","author":"Dastjerdi","year":"2012","journal-title":"Appl. Math. Model"},{"key":"B8","doi-asserted-by":"publisher","first-page":"114360","DOI":"10.1016\/j.cam.2022.114360","article-title":"Meshless procedure for highly oscillatory kernel based one-dimensional volterra integral equations","volume":"413","author":"Din","year":"2022","journal-title":"J. Comput. Appl. Math"},{"key":"B9","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1007\/s00521-010-0489-y","article-title":"A neural network approach for solving Fredholm integral equations of the second kind","volume":"21","author":"Effati","year":"2012","journal-title":"Neural Comput. Appl"},{"key":"B10","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1134\/S0965542522020075","article-title":"On numerical solution of one class of integral equations of the third kind","volume":"62","author":"Gabbasov","year":"2022","journal-title":"Comput. Math. Math. Phys"},{"key":"B11","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1016\/j.amc.2005.05.034","article-title":"Numerical solution of the second kind integral equations using radial basis function networks","volume":"174","author":"Golbabai","year":"2006","journal-title":"Appl. Math. Comput"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1651","DOI":"10.1016\/j.camwa.2009.03.038","article-title":"Solving a system of nonlinear integral equations by an RBF network","volume":"57","author":"Golbabai","year":"2009","journal-title":"Comput. Math. Appl"},{"key":"B13","doi-asserted-by":"publisher","first-page":"11404","DOI":"10.1016\/j.amc.2012.05.028","article-title":"LS-SVR-based solving Volterra integral equations","volume":"218","author":"Guo","year":"2012","journal-title":"Appl. Math. Comput"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1004988","DOI":"10.3389\/fncom.2022.1004988","article-title":"Global Average Pooling convolutional neural network with novel NNLU activation function and HYBRID parallelism","volume":"16","author":"Habib","year":"2022","journal-title":"Front. Comput. Neurosci"},{"key":"B15","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s00521-011-0604-8","article-title":"Multivariate numerical approximation using constructive L2(R) RBF neural network","volume":"21","author":"Hou","year":"2012","journal-title":"Neural Comput. Appl"},{"key":"B16","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1007\/s10489-016-0882-z","article-title":"A new hybrid constructive neural network method for impacting and its application on tungsten rice prediction","volume":"47","author":"Hou","year":"2017","journal-title":"Appl. Intell"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1007\/s11704-018-8095-8","article-title":"Forecasting time series with optimal neural networks using multi-objective optimization algorithm based on AICc","volume":"12","author":"Hou","year":"2018","journal-title":"Front. Comput. Sci"},{"key":"B18","doi-asserted-by":"publisher","first-page":"3056","DOI":"10.1016\/j.neucom.2007.02.009","article-title":"Letters: Convex incremental extreme learning machine","volume":"70","author":"Huang","year":"2007","journal-title":"Neurocomputing"},{"key":"B19","doi-asserted-by":"publisher","first-page":"3460","DOI":"10.1016\/j.neucom.2007.10.008","article-title":"Enhanced random search based incremental extreme learning machine","volume":"71","author":"Huang","year":"2008","journal-title":"Neurocomputing"},{"key":"B20","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1109\/TNN.2006.875977","article-title":"Universal approximation using incremental constructive feedforward networks with random hidden nodes","volume":"17","author":"Huang","year":"","journal-title":"IEEE Trans. Neural Netw"},{"key":"B21","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1109\/TSMCB.2011.2168604","article-title":"Extreme learning machine for regression and multiclass classification","volume":"42","author":"Huang","year":"2012","journal-title":"IEEE Trans. Syst. Man Cybern. B Cybern"},{"key":"B22","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","article-title":"Extreme learning machine: theory and applications","volume":"70","author":"Huang","year":"","journal-title":"Neurocomputing"},{"key":"B23","doi-asserted-by":"publisher","first-page":"4283","DOI":"10.1016\/j.cam.2011.03.029","article-title":"Numerical solution of linear Volterra integral equations of the second kind with sharp gradients","volume":"235","author":"Isaacson","year":"2011","journal-title":"J. Comput. Appl. Math"},{"key":"B24","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.asoc.2014.10.036","article-title":"Artificial neural networks based modeling for solving Volterra integral equations system","volume":"27","author":"Jafarian","year":"2015","journal-title":"Appl. Soft. Comput"},{"key":"B25","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/s00521-015-2104-8","article-title":"Artificial neural network approach for a class of fractional ordinary differential equation","volume":"28","author":"Jafarian","year":"2017","journal-title":"Neural Comput. Appl"},{"key":"B26","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1504\/IJMMNO.2013.056531","article-title":"Feedback neural network method for solving linear Volterra integral equations of the second kind","volume":"4","author":"Jafarian","year":"","journal-title":"Int. J. Math. Model. Numer. Optim"},{"key":"B27","first-page":"53","article-title":"Using feed-back neural network method for solving linear Fredholm integral equations of the second kind","volume":"2","author":"Jafarian","year":"","journal-title":"J. Hyperstruct"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1054421","DOI":"10.3389\/fncom.2022.1054421","article-title":"Disrupted visual input unveils the computational details of artificial neural networks for face perception","volume":"16","author":"Li","year":"2022","journal-title":"Front. Comput. Neurosci"},{"key":"B29","doi-asserted-by":"publisher","first-page":"B962","DOI":"10.1137\/15M1022562","article-title":"Numerical solution of the neural field equation in the two-dimensional case","volume":"37","author":"Lima","year":"2015","journal-title":"SIAM J. Sci. Comput"},{"key":"B30","doi-asserted-by":"publisher","first-page":"102634","DOI":"10.1016\/j.dsp.2019.102634","article-title":"Solving the ruin probabilities of some risk models with Legendre neural network algorithm","volume":"99","author":"Lu","year":"2020","journal-title":"Digit. Signal Process"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2781","DOI":"10.1108\/EC-11-2021-0683","article-title":"Numerical solution for high-order ordinary differential equations using H-ELM algorithm","volume":"39","author":"Lu","year":"2022","journal-title":"Eng. Comput"},{"key":"B32","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.neucom.2021.01.012","article-title":"A novel improved trigonometric neural network algorithm for solving price-dividend functions of continuous time one-dimensional asset-pricing models","volume":"435","author":"Ma","year":"2021","journal-title":"Neurocomputing"},{"key":"B33","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1016\/j.amc.2003.11.036","article-title":"Using rationalized Haar wavelet for solving linear integral equations","volume":"160","author":"Maleknejad","year":"2005","journal-title":"Appl. Math. Comput"},{"key":"B34","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.amc.2014.08.085","article-title":"Chebyshev neural network based model for solving Lane-Emden type equations","volume":"247","author":"Mall","year":"2014","journal-title":"Appl. Math. Comput"},{"key":"B35","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.asoc.2015.10.069","article-title":"Application of Legendre neural network for solving ordinary differential equations","volume":"43","author":"Mall","year":"2016","journal-title":"Appl. Soft. Comput"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1707","DOI":"10.1016\/j.amc.2007.02.058","article-title":"Numerical solution of some classes of integral equations using Bernstein polynomials","volume":"190","author":"Mandal","year":"2007","journal-title":"Appl. Math. Comput"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1491","DOI":"10.1016\/j.camwa.2009.11.004","article-title":"An expansion-iterative method for numerically solving Volterra integral equation of the first kind","volume":"59","author":"Masouri","year":"2010","journal-title":"Comput. Math. Appl"},{"key":"B38","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1016\/j.amc.2015.10.035","article-title":"Application of Fibonacci collocation method for solving Volterra-Fredholm integral equations","volume":"273","author":"Mirzaee","year":"2016","journal-title":"Appl. Math. Comput"},{"key":"B39","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.cam.2014.09.030","article-title":"Numerical solution of Volterra-Fredholm integral equations using Legendre collocation method","volume":"278","author":"Nemati","year":"2015","journal-title":"J. Comput. Appl. Math"},{"key":"B40","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.amc.2016.07.021","article-title":"Solving differential equations of fractional order using an optimization technique based on training artificial neural network","volume":"293","author":"Pakdaman","year":"2017","journal-title":"Appl. Math. Comput"},{"key":"B41","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1016\/S0096-3003(02)00497-6","article-title":"Numerical solution of the integral equations of the first kind","volume":"145","author":"Rashed","year":"2003","journal-title":"Appl. Math. Comput"},{"key":"B42","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1016\/j.cam.2006.08.036","article-title":"Solution of Voltera integral equation by the Sinc-collection method","volume":"206","author":"Rashidinia","year":"2007","journal-title":"J. Comput. Appl. Math"},{"key":"B43","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1080\/00207160.2017.1291932","article-title":"A new artificial neural network structure for solving high-order linear fractional differential equations","volume":"95","author":"Rostami","year":"2018","journal-title":"Int. J. Comput. Math"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1536","DOI":"10.1016\/j.camwa.2012.03.043","article-title":"Solving Volterra integral equations of the second kind by wavelet-Galerkin scheme","volume":"63","author":"Saberi-Nadjafi","year":"2012","journal-title":"Comput. Math. Appl"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1007\/s11063-018-9911-8","article-title":"Solving partial differential equation based on bernstein neural network and extreme learning machine algorithm","volume":"50","author":"Sun","year":"2019","journal-title":"Neural Process. Lett"},{"key":"B46","doi-asserted-by":"publisher","first-page":"125828","DOI":"10.1016\/j.jmaa.2021.125828","article-title":"Bernstein operator method for approximate solution of singularly perturbed volterra integral equations","volume":"507","author":"Usta","year":"2022","journal-title":"J. Math. Anal. Appl"},{"key":"B47","doi-asserted-by":"publisher","first-page":"10434","DOI":"10.1016\/j.amc.2013.04.017","article-title":"Lagrange collocation method for solving Volterra-Fredholm integral equations","volume":"219","author":"Wang","year":"2013","journal-title":"Appl. Math. Comput"},{"key":"B48","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.cam.2013.09.050","article-title":"Taylor collocation method and convergence analysis for the Volterra-Fredholm integral equations","volume":"260","author":"Wang","year":"2014","journal-title":"J. Comput. Appl. Math"},{"key":"B49","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1109\/TNNLS.2016.2636834","article-title":"Kernel-based multilayer extreme learning machines for representation learning","volume":"29","author":"Wong","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13662-018-1927-x","article-title":"A novel improved extreme learning machine algorithm in solving ordinary differential equations by Legendre neural network methods","volume":"469","author":"Yang","year":"2018","journal-title":"Adv. Diff. Equat"},{"key":"B51","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1007\/s00500-019-03944-1","article-title":"Neural network algorithm based on Legendre improved extreme learning machine for solving elliptic partial differential equations","volume":"24","author":"Yang","year":"2020","journal-title":"Soft Comput"},{"key":"B52","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.neucom.2018.08.020","article-title":"Numerical solution for ruin probability of continuous time model based on neural network algorithm","volume":"331","author":"Zhou","year":"2019","journal-title":"Neurocomputing"},{"key":"B53","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1016\/j.chaos.2017.06.030","article-title":"Solving fractional differential equations of variable-order involving operators with Mittag-Leffler kernel using artificial neural networks","volume":"103","author":"Zuniga-Aguilar","year":"2017","journal-title":"Chaos Solitons Fractals"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1120516\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T04:46:14Z","timestamp":1678337174000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1120516\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,9]]},"references-count":53,"alternative-id":["10.3389\/fncom.2023.1120516"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2023.1120516","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,9]]}}}