Design of hierarchical neural networks using deep LSTM and self-organizing dynamical fuzzy-neural network architecture

Basit Öğe Kaydı
dc.authorscopusidWitold Pedrycz / 58861905800
dc.authorwosidWitold Pedrycz / HJZ-2779-2023
dc.contributor.authorZhou, Kun
dc.contributor.authorOh, Sung-Kwun
dc.contributor.authorQiu, Jianlong
dc.contributor.authorPedrycz, Witold
dc.contributor.authorSeo, Kisung
dc.contributor.authorYoon, Jin Hee
dc.date.accessioned2025-04-18T08:48:53Z
dc.date.available2025-04-18T08:48:53Z
dc.date.issued2024
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractTime series forecasting is an essential and challenging task, especially for large-scale time-series (LSTS) forecasting, which plays a crucial role in many real-world applications. Due to the instability of time series data and the randomness (noise) of their characteristics, it is difficult for polynomial neural network (PNN) and its modifications to achieve accurate and stable time series prediction. In this study, we propose a novel structure of hierarchical neural networks (HNN) realized by long short-term memory (LSTM), two classes of self-organizing dynamical fuzzy neural network architectures of fuzzy rule-based polynomial neurons (FPNs) and polynomial neurons constructed by variant generation of nodes as well as layers of networks. The proposed HNN combines the deep learning method with the PNN method for the first time and extends it to time series prediction as a modification of PNN. LSTM extracts the temporal dependencies present in each time series and enables the model to learn its representation. FPNs are designed to capture the complex nonlinear patterns present in the data space by utilizing fuzzy C-means (FCM) clustering and least-square-error-based learning of polynomial functions. The self-organizing hierarchical network architecture generated by the Elitism-based Roulette Wheel Selection strategy ensures that candidate neurons exhibit sufficient fitting ability while enriching the diversity of heterogeneous neurons, addressing the issue of multicollinearity and providing opportunities to select better prediction neurons. In addition, L-2-norm regularization is applied to mitigate the overfitting problem. Experiments are conducted on nine real-world LSTS datasets including three practical applications. The results show that the proposed model exhibits high prediction performance, outperforming many state-of-the-art models.
dc.description.sponsorshipNational Research Foundation of Korea
dc.identifier.citationZhou, K., Oh, S. K., Qiu, J., Pedrycz, W., Seo, K., & Yoon, J. H. (2024). Design of Hierarchical Neural Networks Using Deep LSTM and Self-organizing Dynamical Fuzzy-Neural Network Architecture. IEEE Transactions on Fuzzy Systems.
dc.identifier.doi10.1109/TFUZZ.2024.3361856
dc.identifier.endpage2929
dc.identifier.issn1063-6706
dc.identifier.issn1941-0034
dc.identifier.issue5
dc.identifier.scopus2-s2.0-85185389762
dc.identifier.scopusqualityQ1
dc.identifier.startpage2915
dc.identifier.urihttp://dx.doi.org/10.1109/TFUZZ.2024.3361856
dc.identifier.urihttps://hdl.handle.net/20.500.12713/6616
dc.identifier.volume32
dc.identifier.wosWOS:001214545400036
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorPedrycz, Witold
dc.institutionauthoridWitold Pedrycz / 0000-0002-9335-9930
dc.language.isoen
dc.publisherIEEE-inst electrical electronics engineers
dc.relation.ispartofIEEE transactions on fuzzy systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectTime Series Analysis
dc.subjectNeurons
dc.subjectFuzzy Neural Networks
dc.subjectPredictive Models
dc.subjectComputer Architecture
dc.subjectNeural Networks
dc.subjectAdaptation Models
dc.subjectElitism-Based Roulette Wheel Selection (ERWS)
dc.subjectFuzzy Polynomial Neurons/Polynomial Neuron (FPN/PN)
dc.subjectHierarchical Neural Networks (HNN)
dc.subjectLarge-Scale Time Series (LSTS) Prediction
dc.subjectLong Short-Term Memory (LSTM)
dc.titleDesign of hierarchical neural networks using deep LSTM and self-organizing dynamical fuzzy-neural network architecture
dc.typeArticle

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bilgisayar Mühendisliği Bölümü Makale Koleksiyonu