{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T07:32:34Z","timestamp":1767857554460,"version":"3.49.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T00:00:00Z","timestamp":1643760000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T00:00:00Z","timestamp":1643760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"national natural science foundation of china","doi-asserted-by":"publisher","award":["61463019"],"award-info":[{"award-number":["61463019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"natural science foundation of hunan province","doi-asserted-by":"publisher","award":["2019JJ40062"],"award-info":[{"award-number":["2019JJ40062"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Foundation of Education Bureau of Hunan Province","award":["20C0565"],"award-info":[{"award-number":["20C0565"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2022,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>As a special case of general fuzzy numbers, the polygonal fuzzy number can describe a fuzzy object by means of an ordered representation of finite real numbers. Different from general fuzzy numbers, the polygonal fuzzy numbers overcome the shortcoming of complex operations based on Zadeh\u2019s traditional expansion principle, and can maintain the closeness of arithmetic operation. Hence, it is feasible to use a polygonal fuzzy number to approximate a general fuzzy number. First, an extension theorem of continuous functions on a real compact set is given according to open set construction theorem. Then using Weierstrass approximation theorem and ordered representation of the polygonal fuzzy numbers, the convergence of a single hidden layer feedforward polygonal fuzzy neural network is proved. Secondly, the gradient vector of the approximation error function and the optimization parameter vector of the network are given by using the ordered representation of polygonal fuzzy numbers, and then the gradient descent algorithm is used to train the optimal parameters of the polygonal fuzzy neural network iteratively. Finally, two simulation examples are given to verify the approximation ability of the network. Simulation result shows that the proposed network and the gradient descent algorithm are effective, and the single hidden layer feedforward network have good abilities in learning and generalization.<\/jats:p>","DOI":"10.1007\/s40747-022-00655-3","type":"journal-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T03:02:41Z","timestamp":1643770961000},"page":"2383-2404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Convergence and gradient algorithm of a class of neural networks based on the polygonal fuzzy numbers representation"],"prefix":"10.1007","volume":"8","author":[{"given":"Gang","family":"Sun","sequence":"first","affiliation":[]},{"given":"Mingxin","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4756-7544","authenticated-orcid":false,"given":"Xiaoping","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,2]]},"reference":[{"issue":"1","key":"655_CR1","first-page":"1","volume":"24","author":"TP Chen","year":"1994","unstructured":"Chen TP (1994) Neural network and its approximation problem in system identification. Sci China (Series A) 24(1):1\u20137","journal-title":"Sci China (Series A)"},{"issue":"8","key":"655_CR2","first-page":"906","volume":"26","author":"FL Cao","year":"2003","unstructured":"Cao FL, Xu ZB, Liang JY (2003) Approximation of polynomial functions by neural network: construction of network and algorithm of approximation. Chin J Comput 26(8):906\u2013912","journal-title":"Chin J Comput"},{"issue":"2","key":"655_CR3","first-page":"385","volume":"50","author":"FL Cao","year":"2007","unstructured":"Cao FL, Zhang YQ, Zhang WG (2007) Neural networks with single hidden layer and the best polynomial approximation. Acta Math Sinica 50(2):385\u2013392","journal-title":"Acta Math Sinica"},{"issue":"3","key":"655_CR4","first-page":"334","volume":"18","author":"TF Xie","year":"2008","unstructured":"Xie TF, Cao FL (2008) On the construction of interpolating neural networks. Prog Nat Sci 18(3):334\u2013340","journal-title":"Prog Nat Sci"},{"issue":"5","key":"655_CR5","first-page":"670","volume":"29","author":"SY Xu","year":"2009","unstructured":"Xu SY, Cao FL (2009) Estimation of error for interpolation neural networks in distance spaces. J Syst Sci Math Sci 29(5):670\u2013676","journal-title":"J Syst Sci Math Sci"},{"key":"655_CR6","volume-title":"Neural networks and fuzzy systems: a dynamical systems approach to intelligence","author":"B Kosko","year":"1992","unstructured":"Kosko B (1992) Neural networks and fuzzy systems: a dynamical systems approach to intelligence. Prentice-Hall, Englewood Cliffs"},{"key":"655_CR7","doi-asserted-by":"crossref","unstructured":"Kosko B (1992) Fuzzy systems as universal approximators. In: Proceedings of IEEE international conference on fuzzy systems, pp 1153\u20131162","DOI":"10.1109\/FUZZY.1992.258720"},{"issue":"5","key":"655_CR8","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1109\/72.159070","volume":"3","author":"LX Wang","year":"1992","unstructured":"Wang LX, Mendel JM (1992) Fuzzy basis functions, universal approximation, and orthogonal least-squares learning. Trans Neural Netw 3(5):807\u2013814","journal-title":"Trans Neural Netw"},{"key":"655_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0165-0114(94)90297-6","volume":"66","author":"JJ Buckley","year":"1994","unstructured":"Buckley JJ, Hayashi Y (1994) Fuzzy neural networks: a survey. Fuzzy Sets Syst 66:1\u201313","journal-title":"Fuzzy Sets Syst"},{"issue":"1","key":"655_CR10","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/0165-0114(94)90283-6","volume":"61","author":"JJ Buckley","year":"1994","unstructured":"Buckley JJ, Hayashi Y (1994) Can fuzzy neural nets approximate continuous fuzzy functions? Fuzzy Sets Syst 61(1):43\u201351","journal-title":"Fuzzy Sets Syst"},{"key":"655_CR11","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/0165-0114(93)90503-A","volume":"58","author":"JJ Buckley","year":"1999","unstructured":"Buckley JJ, Hayashi Y (1999) Can neural nets be universal approximators for fuzzy functions? Fuzzy Sets Syst 58:273\u2013278","journal-title":"Fuzzy Sets Syst"},{"issue":"2","key":"655_CR12","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0165-0114(97)00125-5","volume":"102","author":"T Feuring","year":"1999","unstructured":"Feuring T, Lippe WM (1999) The fuzzy neural network approximation lemma. Fuzzy Sets Syst 102(2):227\u2013237","journal-title":"Fuzzy Sets Syst"},{"issue":"2","key":"655_CR13","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/S0165-0114(98)00433-3","volume":"119","author":"PY Liu","year":"2001","unstructured":"Liu PY (2001) Universal approximation of continuous analyses fuzzy valued functions by multi-layer regular fuzzy neural networks. Fuzzy Sets Syst 119(2):303\u2013311","journal-title":"Fuzzy Sets Syst"},{"issue":"2","key":"655_CR14","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/j.fss.2004.02.013","volume":"150","author":"PY Liu","year":"2005","unstructured":"Liu PY, Li HX (2005) Approximation analysis of feedforward regular fuzzy neural network with two hidden layers. Fuzzy Sets Syst 150(2):373\u2013396","journal-title":"Fuzzy Sets Syst"},{"issue":"1","key":"655_CR15","first-page":"76","volume":"32","author":"PY Liu","year":"2002","unstructured":"Liu PY (2002) A new fuzzy neural network and its approximation capability. Sci China (Series E) 32(1):76\u201386","journal-title":"Sci China (Series E)"},{"issue":"11","key":"655_CR16","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1007\/s11432-011-4364-y","volume":"54","author":"GJ Wang","year":"2011","unstructured":"Wang GJ, Li XP (2011) Universal approximation of polygonal fuzzy neural networks in sense of K-integral norms. Sci China Inf Sci 54(11):2307\u20132323","journal-title":"Sci China Inf Sci"},{"issue":"1","key":"655_CR17","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.fss.2012.04.003","volume":"209","author":"AD Baez-Sanchez","year":"2012","unstructured":"Baez-Sanchez AD, Moretti AC, Rojas-Medar MA (2012) Polygonal fuzzy sets and numbers. Fuzzy Sets Syst 209(1):54\u201365","journal-title":"Fuzzy Sets Syst"},{"issue":"4","key":"655_CR18","doi-asserted-by":"publisher","first-page":"357","DOI":"10.14311\/NNW.2014.24.021","volume":"24","author":"GJ Wang","year":"2014","unstructured":"Wang GJ, Li XP (2014) Construction of the polygonal fuzzy neural network and its approximation based on K-integral norm. Neural Netw World 24(4):357\u2013376","journal-title":"Neural Netw World"},{"issue":"1","key":"655_CR19","first-page":"39","volume":"29","author":"FX Zhao","year":"2006","unstructured":"Zhao FX, Li HX (2006) Universal approximation of regular fuzzy neural networks to Sugeno-integrable functions. Acta Math Appl Sin 29(1):39\u201345","journal-title":"Acta Math Appl Sin"},{"issue":"10","key":"655_CR20","first-page":"2079","volume":"40","author":"Y He","year":"2012","unstructured":"He Y, Wang GJ (2012) The conjugate gradient algorithm of the polygonal fuzzy neural networks. Acta Electron Sin 40(10):2079\u20132084","journal-title":"Acta Electron Sin"},{"key":"655_CR21","unstructured":"Sui XL, Wang GJ (2012) Influence of perturbations of training pattern pairs on stability of polygonal fuzzy neural network. Pattern Recogn Artif Intell 26(6):928\u2013936"},{"issue":"5","key":"655_CR22","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1007\/s13042-013-0224-y","volume":"5","author":"YQ Yang","year":"2014","unstructured":"Yang YQ, Wang GJ, Yang Y (2014) Parameters optimization of polygonal fuzzy neural networks based on GA-BP hybrid algorithm. Int J Mach Learn Cybern 5(5):815\u2013822","journal-title":"Int J Mach Learn Cybern"},{"issue":"3","key":"655_CR23","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s13042-015-0391-0","volume":"7","author":"XP Li","year":"2016","unstructured":"Li XP, Li D (2016) The structure and realization of a polygonal fuzzy neural network. Int J Mach Learn Cybern 7(3):375\u2013389","journal-title":"Int J Mach Learn Cybern"},{"issue":"10","key":"655_CR24","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1007\/s00521-016-2600-5","volume":"29","author":"GJ Wang","year":"2018","unstructured":"Wang GJ, Suo CF (2018) The isolation layered optimization algorithm of MIMO polygonal fuzzy neural network. Neural Comput Appl 29(10):721\u2013731","journal-title":"Neural Comput Appl"},{"issue":"1","key":"655_CR25","doi-asserted-by":"publisher","first-page":"1477","DOI":"10.3233\/JIFS-182882","volume":"37","author":"GJ Wang","year":"2019","unstructured":"Wang GJ, Gao JS (2019) Parallel conjugate gradient-particle swarm optimization and the parameters design based on the polygonal fuzzy neural network. J Intell Fuzzy Syst 37(1):1477\u20131489","journal-title":"J Intell Fuzzy Syst"},{"issue":"2","key":"655_CR26","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1002\/int.22316","volume":"36","author":"GJ Wang","year":"2021","unstructured":"Wang GJ, Chen X, Sun G (2021) Design and optimization of TS firefly algorithm based on nonhomogeneous linear polygonal T-S fuzzy system. Int J Intell Syst 36(2):691\u2013714","journal-title":"Int J Intell Syst"},{"key":"655_CR27","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.ins.2016.12.024","volume":"382","author":"H Wang","year":"2017","unstructured":"Wang H, Wang W, Zhou X et al (2017) Firefly algorithm with neighborhood attraction. Inf Sci 382:374\u2013387","journal-title":"Inf Sci"},{"issue":"17","key":"655_CR28","doi-asserted-by":"publisher","first-page":"5091","DOI":"10.1007\/s00500-016-2104-3","volume":"21","author":"H Wang","year":"2017","unstructured":"Wang H, Zhou X, Sun H et al (2017) Firefly algorithm with adaptive control parameters. Soft Comput 21(17):5091\u20135102","journal-title":"Soft Comput"},{"issue":"6","key":"655_CR29","first-page":"538","volume":"30","author":"RY Li","year":"2017","unstructured":"Li RY, Chen QQ, Chen SY (2017) Dynamic search firefly algorithm based on improved attraction. Pattern Recogn Artif Intell 30(6):538\u2013548","journal-title":"Pattern Recogn Artif Intell"},{"key":"655_CR30","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.neucom.2017.02.040","volume":"240","author":"LF He","year":"2017","unstructured":"He LF, Huang SW (2017) Modified firefly algorithm based multilevel thresholding for color image segmentation. Neurocomputing 240:152\u2013174","journal-title":"Neurocomputing"},{"issue":"1","key":"655_CR31","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.cie.2012.09.015","volume":"64","author":"H Garg","year":"2013","unstructured":"Garg H, Sharma SP (2013) Multi-objective reliability-redundancy allocation problem using particle swarm optimization. Comput Ind Eng 64(1):247\u2013255","journal-title":"Comput Ind Eng"},{"issue":"2","key":"655_CR32","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.isatra.2012.09.010","volume":"52","author":"H Garg","year":"2013","unstructured":"Garg H (2013) Performance analysis of complex repairable industrial systems using PSO and fuzzy confidence interval based lambda-tau methodology. ISA Trans 52(2):171\u2013183","journal-title":"ISA Trans"},{"key":"655_CR33","first-page":"292","volume":"274","author":"H Garg","year":"2016","unstructured":"Garg H (2016) A hybrid PSO-GA algorithm for constrained optimization problems. Appl Math Comput 274:292\u2013305","journal-title":"Appl Math Comput"},{"key":"655_CR34","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1016\/j.asoc.2015.10.027","volume":"38","author":"F Gaxiola","year":"2016","unstructured":"Gaxiola F, Melin P, Valdez F et al (2016) Optimization of type-2 fuzzy weights in backpropagation learning for neural networks using GAs and PSO. Appl Soft Comput 38:860\u2013871","journal-title":"Appl Soft Comput"},{"issue":"114","key":"655_CR35","first-page":"1","volume":"8","author":"F Gaxiola","year":"2017","unstructured":"Gaxiola F, Melin P, Valdez F et al (2017) Comparison of T-norms and S-onrms for interval type-2 fuzzy numbers in weight adjustment for neural networks. Information 8(114):1\u201321","journal-title":"Information"},{"key":"655_CR36","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.ins.2015.07.020","volume":"325","author":"F Gaxiola","year":"2015","unstructured":"Gaxiola F, Melin P, Valdez F et al (2015) Generalized type-2 fuzzy weight adjustment for backpropagation neural networks in time series prediction. Inf Sci 325:159\u2013174","journal-title":"Inf Sci"},{"issue":"14","key":"655_CR37","first-page":"1","volume":"8","author":"F Gaxiola","year":"2019","unstructured":"Gaxiola F, Melin P, Valdez F et al (2019) PSO with dynamic adaptation of parameters for optimization in neural networks with interval type-2 fuzzy numbers weights. Axioms 8(14):1\u201321","journal-title":"Axioms"},{"key":"655_CR38","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s00521-016-2446-x","volume":"29","author":"S Agrawal","year":"2018","unstructured":"Agrawal S, Agrawal J, Kaur S et al (2018) A comparative study of fuzzy PSO and fuzzy SVD-based RBF neural network for multi-label classification. Neural Comput Appl 29:245\u2013256","journal-title":"Neural Comput Appl"},{"key":"655_CR39","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1007\/s40815-018-0534-z","volume":"21","author":"SS Pal","year":"2019","unstructured":"Pal SS, Kar S (2019) A hybridized forecasting method based on weight adjustment of neural network using generalized type-2 fuzzy set. Int J Fuzzy Syst 21:308\u2013320","journal-title":"Int J Fuzzy Syst"},{"key":"655_CR40","doi-asserted-by":"publisher","first-page":"8691","DOI":"10.1007\/s00521-019-04372-w","volume":"32","author":"AA Khater","year":"2020","unstructured":"Khater AA, El-Nagar AM, El-Bardini M et al (2020) Online learning based on adaptive learning rate for a class of recurrent fuzzy neural network. Neural Comput Appl 32:8691\u20138710","journal-title":"Neural Comput Appl"},{"key":"655_CR41","doi-asserted-by":"publisher","first-page":"5089","DOI":"10.1007\/s00521-020-05276-w","volume":"33","author":"H Ding","year":"2021","unstructured":"Ding H, Li W, Qiao J (2021) A self-organizing recurrent fuzzy neural network based on multivariate time series analysis. Neural Comput Appl 33:5089\u20135109","journal-title":"Neural Comput Appl"},{"key":"655_CR42","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.fss.2019.02.010","volume":"368","author":"JG Hsieh","year":"2019","unstructured":"Hsieh JG, Jeng JH, Lin YL et al (2019) Single index fuzzy neural networks using locally weighted polynomial regression. Fuzzy Sets Syst 368:82\u2013100","journal-title":"Fuzzy Sets Syst"},{"key":"655_CR43","doi-asserted-by":"crossref","unstructured":"Wang GJ, Xiao WM, Tao YJ (2021) Interpolation neural network constructed by the step path and its approximation performance. Clust Comput 24(2):1397\u20131411","DOI":"10.1007\/s10586-020-03197-w"},{"key":"655_CR44","volume-title":"Metric spaces of fuzzy sets","author":"P Diamond","year":"1994","unstructured":"Diamond P, Kloeden P (1994) Metric spaces of fuzzy sets. World Scientific Press, Singapore"},{"key":"655_CR45","unstructured":"Wang GJ (2017) Polygonal fuzzy neural network and fuzzy system approximation. Science Press, Beijing"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-022-00655-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-022-00655-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-022-00655-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T23:09:12Z","timestamp":1666566552000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-022-00655-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,2]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["655"],"URL":"https:\/\/doi.org\/10.1007\/s40747-022-00655-3","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,2]]},"assertion":[{"value":"5 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}