Design of progressive fuzzy polynomial neural networks through gated recurrent unit structure and correlation/probabilistic selection strategies

Basit Öğe Kaydı
dc.authoridWang, Zheng/0000-0003-2160-8608
dc.authoridWANG, ZHEN/0000-0003-3927-0115
dc.contributor.authorWang, Zhen
dc.contributor.authorOh, Sung-Kwun
dc.contributor.authorWang, Zheng
dc.contributor.authorFu, Zunwei
dc.contributor.authorPedrycz, Witold
dc.contributor.authorYoon, Jin Hee
dc.date.accessioned2024-05-19T14:46:19Z
dc.date.available2024-05-19T14:46:19Z
dc.date.issued2023
dc.departmentİstinye Üniversitesien_US
dc.description.abstractThis study focuses on two critical design aspects of a progressive fuzzy polynomial neural network (PFPNN): the influence of the gated recurrent unit (GRU) structure and the implementation of fitness-based candidate neuron selection (FCNS) through two probabilistic strategies. The primary objectives are to enhance modeling accuracy and to reduce the computational load associated with nonlinear regression tasks. Compared with the existing fuzzy rule-based modeling architecture, the proposed dynamic model consists of the GRU structure and the hybrid fuzzy polynomial architecture. In the initial two layers of the PFPNN, we introduce three types of polynomial and fuzzy rules into the GRU neurons (GNs) and fuzzy polynomial neurons (FPNs), which can effectively reveal potential complex relationships in the data space. The synergy of the FCNS strategies and the l2 regularization learning method is to design a progressive regression model adept at melding the GRU structure with a self-organizing architecture. The proposed GRU structure and polynomial-based neurons significantly improve the modeling accuracy for time-series datasets. The rational utilization of FCNS strategies can reinforce the network structure and discover the potential performance of neurons of the network. Furthermore, the inclusion of l2 norm regularization provides additional stability to the proposed model and mitigates the overfitting issue commonly encountered in many existing learning methods. We validated the proposed neural networks using six time-series, four machine learning, and two real-world datasets. The PFPNN outperformed other models in the comparison studies in 83.3% of the datasets, emphasizing its superiority in terms of developing a stable deep structure from diverse candidate neurons and reducing computational overhead. (c) 2023 Elsevier B.V. All rights reserved.en_US
dc.description.sponsorshipNational Research Foundation of Korea (NRF) - Korea Government (MSIT) [NRF-2020R1A2C1A01011131, NRF-2022R1I1A1A01071671]; Basic Science Research Program through the National Research Foundation of Korea (NRF) - Ministry of Education; [NRF-2021R1F1A1056102]en_US
dc.description.sponsorshipThis work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea Government (MSIT) (NRF-2021R1F1A1056102 and NRF-2020R1A2C1A01011131) and by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (grant number: NRF-2022R1I1A1A01071671) .en_US
dc.identifier.doi10.1016/j.fss.2023.108656
dc.identifier.issn0165-0114
dc.identifier.issn1872-6801
dc.identifier.scopus2-s2.0-85166485645en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org10.1016/j.fss.2023.108656
dc.identifier.urihttps://hdl.handle.net/20.500.12713/5494
dc.identifier.volume470en_US
dc.identifier.wosWOS:001058105600001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.ispartofFuzzy Sets and Systemsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectProgressive Fuzzy Polynomial Neural Network (Pfpnn)en_US
dc.subjectGated Recurrent Unit (Gru) Structureen_US
dc.subjectFuzzy Polynomial Neurons/Polynomial Neuronsen_US
dc.subjectCorrelation Selection/Probabilistic Selectionen_US
dc.subjectL2 Norm Regularizationen_US
dc.titleDesign of progressive fuzzy polynomial neural networks through gated recurrent unit structure and correlation/probabilistic selection strategiesen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu