Design of hierarchical neural networks using deep LSTM and self-organizing dynamical fuzzy-neural network architecture
Küçük Resim Yok
Tarih
2024
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
IEEE-inst electrical electronics engineers
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Time 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.
Açıklama
Anahtar Kelimeler
Time Series Analysis, Neurons, Fuzzy Neural Networks, Predictive Models, Computer Architecture, Neural Networks, Adaptation Models, Elitism-Based Roulette Wheel Selection (ERWS), Fuzzy Polynomial Neurons/Polynomial Neuron (FPN/PN), Hierarchical Neural Networks (HNN), Large-Scale Time Series (LSTS) Prediction, Long Short-Term Memory (LSTM)
Kaynak
IEEE transactions on fuzzy systems
WoS Q Değeri
Q1
Scopus Q Değeri
Q1
Cilt
32
Sayı
5
Künye
Zhou, 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.
