A self-organizing deep network architecture designed based on LSTM network via elitism-driven roulette-wheel selection for time-series forecasting
dc.authorid | zhou, kun/0000-0002-3858-2072 | |
dc.contributor.author | Zhou, Kun | |
dc.contributor.author | Oh, Sung-Kwun | |
dc.contributor.author | Pedrycz, Witold | |
dc.contributor.author | Qiu, Jianlong | |
dc.contributor.author | Seo, Kisung | |
dc.date.accessioned | 2024-05-19T14:41:45Z | |
dc.date.available | 2024-05-19T14:41:45Z | |
dc.date.issued | 2024 | |
dc.department | İstinye Üniversitesi | en_US |
dc.description.abstract | In this study, we propose a new self-organizing deep network architecture of fuzzy polynomial neural networks (FPNN) based on Fuzzy rule-based Polynomial Neurons (FPNs) and a long short-term memory (LSTM) network to solve the task of time-series forecasting. In the existing regression model based on polynomial neural networks (PNN), it is difficult to achieve high quality performance when predicting time series data, because this model lacks the ability to extract temporal and spatial information. Therefore, we propose a new architecture consisting of one LSTM (temporal) layer and several fuzzy polynomial (spatial) layers to overcome the above-mentioned shortcomings of PNN and enhance its predictive ability to approximate the data. The temporal layer consists of LSTM neurons that have inherently strong modeling capabilities to learn sequential information. The spatial layers are composed of Rule-based Polynomial Neurons (FPNs) that can effectively reflect the complex nonlinear structure found in the input space and granulate it using of the Fuzzy C-Means (FCM) clustering method. An elitism-driven roulette-wheel selection (E_RWS) is used to select appropriate neurons. E_RWS not only ensures that the neuron with the strongest fitting ability is selected but also increases the diversity of candidate neurons. According to the experimental results, the proposed model has a high prediction performance and outperforms many state-of-the-art prediction methods when applied to the real-world time-series. | en_US |
dc.description.sponsorship | National Research Foundation of Korea (NRF) - Korea Government (MSIT) [61877033]; National Natural Science Foundation of China [ZR2019MF021, NRF-2021R1F1A1056102]; Natural Science Foundation of Shandong Province [RS-2023-00244355]; [NRF-2023K2A9A2A06060385]; [61833005] | en_US |
dc.description.sponsorship | This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea Government (MSIT) (NRF-2021R1F1A1056102, NRF-2023K2A9A2A06060385, and RS-2023-00244355), and also by the National Natural Science Foundation of China under Grant No. 61877033, 61833005, and also by Natural Science Foundation of Shandong Province under Grant No. ZR2019MF021. | en_US |
dc.identifier.doi | 10.1016/j.knosys.2024.111481 | |
dc.identifier.issn | 0950-7051 | |
dc.identifier.issn | 1872-7409 | |
dc.identifier.scopus | 2-s2.0-85186757078 | en_US |
dc.identifier.scopusquality | Q1 | en_US |
dc.identifier.uri | https://doi.org10.1016/j.knosys.2024.111481 | |
dc.identifier.uri | https://hdl.handle.net/20.500.12713/5155 | |
dc.identifier.volume | 289 | en_US |
dc.identifier.wos | WOS:001203075000001 | en_US |
dc.identifier.wosquality | N/A | en_US |
dc.indekslendigikaynak | Web of Science | en_US |
dc.indekslendigikaynak | Scopus | en_US |
dc.language.iso | en | en_US |
dc.publisher | Elsevier | en_US |
dc.relation.ispartof | Knowledge-Based Systems | en_US |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.snmz | 20240519_ka | en_US |
dc.subject | Fuzzy Polynomial Neural Networks (Fpnn) | en_US |
dc.subject | Long Short -Term Memory Network (Lstm) | en_US |
dc.subject | Fuzzy C-Means (Fcm) Clustering | en_US |
dc.subject | Elitism -Driven Roulette-Wheel Selection | en_US |
dc.subject | (E_Rws) | en_US |
dc.subject | Time -Series Forecasting | en_US |
dc.title | A self-organizing deep network architecture designed based on LSTM network via elitism-driven roulette-wheel selection for time-series forecasting | en_US |
dc.type | Article | en_US |