Fuzzy clustering-based neural network based on linear fitting residual-driven weighted fuzzy clustering and convolutional regularization strategy

Basit Öğe Kaydı
dc.authoridYANG, Dachun/0000-0001-9024-3345
dc.authorwosidYANG, Dachun/ISV-0041-2023
dc.contributor.authorBu, Fan
dc.contributor.authorZhang, Congcong
dc.contributor.authorKim, Eun-Hu
dc.contributor.authorYang, Dachun
dc.contributor.authorFu, Zunwei
dc.contributor.authorPedrycz, Witold
dc.date.accessioned2024-05-19T14:39:12Z
dc.date.available2024-05-19T14:39:12Z
dc.date.issued2024
dc.departmentİstinye Üniversitesien_US
dc.description.abstractIn this study, a reinforced Fuzzy Clustering-based Neural Network (FCNN) is introduced as an augmented FCNN architecture to address regression issues. It is widely recognized that regardless of the design method and rules employed by a fuzzy model, the determination of fuzzy sets remains a crucial aspect. FCNN and its improved variants utilize conventional fuzzy clustering algorithms to partition the feature space into fuzzy sets. However, this approach tends to disregard the distinctions inherent in data patterns. Although FCNN is a nonlinear model in relation to the input variables, it is a linear model with respect to the parameters that need to be estimated. Inspired by this, our method incorporates a pre-training phase where we utilize sample residuals from a linear regression algorithm to measure differences between data patterns. These differences are subsequently integrated into the fuzzy partition, yielding more refined fuzzy sets. To combat overfitting that can degrade the model's predictive capability, we introduce a convolutional L2 regularization strategy that integrates the convolution operator from harmonic analysis into the construction of L2 regularization. Compared to conventional L2 regularization, this convolutional regularization strategy is more effective in improving the regularity of the design matrix, thereby reducing the variation between coefficients and enhancing the model's generalization ability. The efficacy of the presented method is substantiated by experimental studies conducted on both synthetic and real-world datasets.en_US
dc.description.sponsorshipNational Natural Science Foundation of China [12201279, 12371093]; Natural Science Foundation of Shandong, China [ZR2022QF072]; Shandong Excellent Young Scientists Fund Program (Overseas) [2023HWYQ-098]; Taishan Young Scholar Experts Project [tsqn202211243]; Fundamental Research Funds for the Central Universities [2233300008]en_US
dc.description.sponsorshipThis work was partially supported by the National Natural Science Foundation of China (Grant Nos. 12201279, 12371093) , the Natural Science Foundation of Shandong, China (Grant No. ZR2022QF072) , the Shandong Excellent Young Scientists Fund Program (Overseas) (Grant No. 2023HWYQ-098) , the Taishan Young Scholar Experts Project (Grant No. tsqn202211243) , and the Fundamental Research Funds for the Central Universities (Grant No. 2233300008) .en_US
dc.identifier.doi10.1016/j.asoc.2024.111403
dc.identifier.issn1568-4946
dc.identifier.issn1872-9681
dc.identifier.scopus2-s2.0-85185564199en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org10.1016/j.asoc.2024.111403
dc.identifier.urihttps://hdl.handle.net/20.500.12713/4724
dc.identifier.volume154en_US
dc.identifier.wosWOS:001192208000001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.ispartofApplied Soft Computingen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectAugmented Fcnnen_US
dc.subjectPre-Training With Linear Regressionen_US
dc.subjectWeighted Fuzzy Clusteringen_US
dc.subjectConvolutional Regularization Strategyen_US
dc.titleFuzzy clustering-based neural network based on linear fitting residual-driven weighted fuzzy clustering and convolutional regularization strategyen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu