In this paper an architecture based on the anatomical structure of the emotional network in the brain of mammalians is applied as a prediction model for chaotic time series studies. The architecture is called BELRFS, which stands for: Brain Emotional Learning-based Recurrent Fuzzy System. It adopts neuro-fuzzy adaptive networksto mimic the functionality of brain emotional learning. In particular, the model is investigated to predict space storms, since the phenomenon has been recognized as a threat to critical infrastructure in modern society. To evaluate the performance of BELRFS, three benchmark time series: Lorenz time series, sunspot number time series and Auroral Electrojet (AE) index. The obtained results of BELRFS are compared with Linear Neuro-Fuzzy (LNF) with the Locally Linear Model Tree algorithm (LoLiMoT). The results indicate that the suggested model outperforms most of data driven models in terms of prediction accuracy. Copyright © 2013 Inderscience Enterprises Ltd. ; Special Issue on Innovations of Intelligent Systems and Engineering; This paper is a revised and expanded version of a paper entitled ‘Neuro-fuzzy models, BELRFS and LoLiMoT, for prediction of chaotic time series’ presented at the INISTA’12, Trabzon, 2–4 July, 2012.
Chaotic Time Series Prediction Using Brain Emotional Learning Based Recurrent Fuzzy System (BELRFS)
2013-01-01
Scopus 2-s2.0-84892145721
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC: | 629 |
Predicting Chaotic Time Series Using Adaptive Wavelet-Fuzzy Inference System
British Library Conference Proceedings | 2005
|Unoccupied Parking Space Prediction of Chaotic Time Series
British Library Conference Proceedings | 2010
|Europäisches Patentamt | 2020
|