Home > Research > Publications & Outputs > MFRFNN

Links

Text available via DOI:

View graph of relations

MFRFNN: Multi-Functional Recurrent Fuzzy Neural Network for Chaotic Time Series Prediction

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

MFRFNN: Multi-Functional Recurrent Fuzzy Neural Network for Chaotic Time Series Prediction. / Nasiri, Hamid; Ebadzadeh, Mohammad Mehdi.
In: Neurocomputing, Vol. 507, 01.10.2022, p. 292-310.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Nasiri H, Ebadzadeh MM. MFRFNN: Multi-Functional Recurrent Fuzzy Neural Network for Chaotic Time Series Prediction. Neurocomputing. 2022 Oct 1;507:292-310. Epub 2022 Aug 12. doi: 10.1016/j.neucom.2022.08.032

Author

Nasiri, Hamid ; Ebadzadeh, Mohammad Mehdi. / MFRFNN : Multi-Functional Recurrent Fuzzy Neural Network for Chaotic Time Series Prediction. In: Neurocomputing. 2022 ; Vol. 507. pp. 292-310.

Bibtex

@article{3984079cf19a497fbfa4a7b4e3fa8de7,
title = "MFRFNN: Multi-Functional Recurrent Fuzzy Neural Network for Chaotic Time Series Prediction",
abstract = "Chaotic time series prediction, a challenging research topic in dynamic system modeling, has drawn great attention from researchers around the world. In recent years extensive researches have been done on developing chaotic time series prediction methods, and various models have been proposed. Among them, recurrent fuzzy neural networks (RFNNs) have shown significant potential in this area. Most of the proposed RFNNs learn a single function, but when dealing with chaotic time series, different outputs may be generated for a specific input based on the system's state. So, a network is required that can learn multiple functions simultaneously. Based on this concept, a novel multi-functional recurrent fuzzy neural network (MFRFNN) is proposed in this paper. MFRFNN consists of two fuzzy neural networks with Takagi-Sugeno-Kang fuzzy rules, one is used to produce the output, and the other to determine the system's state. There is a feedback loop between these two networks, which makes MFRFNN capable of learning and memorizing historical information of past observations. Employing the states allows the proposed network to learn multiple functions simultaneously. Moreover, a new learning algorithm, which employs the particle swarm optimization algorithm, is developed to train the networks{\textquoteright} weights. The effectiveness of MFRFNN is validated using the Lorenz and Rossler chaotic time series and four real-world datasets, including Box–Jenkins gas furnace, wind speed prediction, Google stock price prediction, and air quality index prediction. Based on the root mean square error, the proposed method shows a decrease of 35.12%,13.95%, and 49.62% from the second best methods in the Lorenz time series, Box–Jenkins gas furnace, and wind speed prediction dataset, respectively.",
keywords = "Chaotic time series, Neuro-fuzzy inference system, Prediction, Recurrent fuzzy neural network, Time series forecasting",
author = "Hamid Nasiri and Ebadzadeh, {Mohammad Mehdi}",
note = "Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",
year = "2022",
month = oct,
day = "1",
doi = "10.1016/j.neucom.2022.08.032",
language = "English",
volume = "507",
pages = "292--310",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - MFRFNN

T2 - Multi-Functional Recurrent Fuzzy Neural Network for Chaotic Time Series Prediction

AU - Nasiri, Hamid

AU - Ebadzadeh, Mohammad Mehdi

N1 - Publisher Copyright: © 2022 Elsevier B.V.

PY - 2022/10/1

Y1 - 2022/10/1

N2 - Chaotic time series prediction, a challenging research topic in dynamic system modeling, has drawn great attention from researchers around the world. In recent years extensive researches have been done on developing chaotic time series prediction methods, and various models have been proposed. Among them, recurrent fuzzy neural networks (RFNNs) have shown significant potential in this area. Most of the proposed RFNNs learn a single function, but when dealing with chaotic time series, different outputs may be generated for a specific input based on the system's state. So, a network is required that can learn multiple functions simultaneously. Based on this concept, a novel multi-functional recurrent fuzzy neural network (MFRFNN) is proposed in this paper. MFRFNN consists of two fuzzy neural networks with Takagi-Sugeno-Kang fuzzy rules, one is used to produce the output, and the other to determine the system's state. There is a feedback loop between these two networks, which makes MFRFNN capable of learning and memorizing historical information of past observations. Employing the states allows the proposed network to learn multiple functions simultaneously. Moreover, a new learning algorithm, which employs the particle swarm optimization algorithm, is developed to train the networks’ weights. The effectiveness of MFRFNN is validated using the Lorenz and Rossler chaotic time series and four real-world datasets, including Box–Jenkins gas furnace, wind speed prediction, Google stock price prediction, and air quality index prediction. Based on the root mean square error, the proposed method shows a decrease of 35.12%,13.95%, and 49.62% from the second best methods in the Lorenz time series, Box–Jenkins gas furnace, and wind speed prediction dataset, respectively.

AB - Chaotic time series prediction, a challenging research topic in dynamic system modeling, has drawn great attention from researchers around the world. In recent years extensive researches have been done on developing chaotic time series prediction methods, and various models have been proposed. Among them, recurrent fuzzy neural networks (RFNNs) have shown significant potential in this area. Most of the proposed RFNNs learn a single function, but when dealing with chaotic time series, different outputs may be generated for a specific input based on the system's state. So, a network is required that can learn multiple functions simultaneously. Based on this concept, a novel multi-functional recurrent fuzzy neural network (MFRFNN) is proposed in this paper. MFRFNN consists of two fuzzy neural networks with Takagi-Sugeno-Kang fuzzy rules, one is used to produce the output, and the other to determine the system's state. There is a feedback loop between these two networks, which makes MFRFNN capable of learning and memorizing historical information of past observations. Employing the states allows the proposed network to learn multiple functions simultaneously. Moreover, a new learning algorithm, which employs the particle swarm optimization algorithm, is developed to train the networks’ weights. The effectiveness of MFRFNN is validated using the Lorenz and Rossler chaotic time series and four real-world datasets, including Box–Jenkins gas furnace, wind speed prediction, Google stock price prediction, and air quality index prediction. Based on the root mean square error, the proposed method shows a decrease of 35.12%,13.95%, and 49.62% from the second best methods in the Lorenz time series, Box–Jenkins gas furnace, and wind speed prediction dataset, respectively.

KW - Chaotic time series

KW - Neuro-fuzzy inference system

KW - Prediction

KW - Recurrent fuzzy neural network

KW - Time series forecasting

U2 - 10.1016/j.neucom.2022.08.032

DO - 10.1016/j.neucom.2022.08.032

M3 - Journal article

AN - SCOPUS:85135819391

VL - 507

SP - 292

EP - 310

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -