A new Neuro-Fuzzy Inference System with Dynamic Neurons (NFIS-DN) for system identification and time series forecasting

被引：18

作者：

Samanta, S. ^{[1
]}

Suresh, S. ^{[2
]}

Senthilnath, J. ^{[3
]}

Sundararajan, N. ^{[4
]}

机构：

[1] Nanyang Technol Univ, Interdisciplinary Grad Sch, ERI N, Singapore, Singapore

[2] Indian Inst Sci, Dept Aerosp Engn, Bengaluru, India

[3] ASTAR, Inst Infocomm Res, Singapore, Singapore

[4] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore

来源：

APPLIED SOFT COMPUTING | 2019年 / 82卷

关键词：

Dynamic neuron; Recurrent neural network; Fuzzy system; Self-regulated learning; Backpropagation; LEARNING ALGORITHM; PREDICTION; NETWORKS; CONTROLLER; MEMORY; MODEL;

D O I：

10.1016/j.asoc.2019.105567

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new Neuro-Fuzzy Inference System with Dynamic Neurons or NFIS-DN is presented here for discrete time dynamic system identification and time series forecasting problems. The proposed dynamic system based neuron, referred to as Dynamic Neuron (DN) is realized by a discrete-time nonlinear state-space model. The DN is designed such way, that the output considers only the effect of finite past instances, enabling the system with finite memory. The NFIS-DN model has five layers, and DNs are employed only in the layers handling crisp values. The antecedent and the consequent parameters of NFIS-DN are updated using a self-regulated backpropagation through time learning algorithm. The performance evaluation of NFIS-DN has been carried-out using benchmark problems in the areas of nonlinear system identification and time series forecasting. The results are compared with the state-of-the-art method on the neural fuzzy networks. The obtained results clearly suggest that the NFIS-DN performs significantly better while using a smaller or similar number of fuzzy rules. Finally the practical application of the NFIS-DN has been demonstrated using two real-world problems. (C) 2019 Elsevier B.V. All rights reserved.

引用

页数：11

共 57 条

[1] Evolutionary algorithm-based learning of fuzzy neural networks. Part 2: Recurrent fuzzy neural networks [J].

Aliev, R. A. ;

Guirimov, B. G. ;

Fazlollahi, Bijan ;

Aliev, R. R. .

FUZZY SETS AND SYSTEMS, 2009, 160 (17) :2553-2566

[2]

Angelov P, 2005, IEEE INT CONF FUZZY, P1068

[3] Autonomous Learning Multimodel Systems From Data Streams [J].

Angelov, Plamen P. ;

Gu, Xiaowei ;

Principe, Jose C. .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2018, 26 (04) :2213-2224

[4] An approach to Online identification of Takagi-Suigeno fuzzy models [J].

Angelov, PP ;

Filev, DP .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2004, 34 (01) :484-498

[5]

[Anonymous], HDB BRAIN THEORY NEU

[6]

Azoff E.M., 1994, Neural Network Time Series Forecasting of Financial Markets

[7] Meta-cognitive RBF Network and its Projection Based Learning algorithm for classification problems [J].

Babu, G. Sateesh ;

Suresh, S. .

APPLIED SOFT COMPUTING, 2013, 13 (01) :654-666

[8] An evolving recurrent interval type-2 intuitionistic fuzzy neural network for online learning and time series prediction [J].

Chao, Luo ;

Tan, Chenhao ;

Wang, Xingyuan ;

Zheng, Yuanjie .

APPLIED SOFT COMPUTING, 2019, 78 :150-163

[9] Data mining and wind power prediction: A literature review [J].

Colak, Ilhami ;

Sagiroglu, Seref ;

Yesilbudak, Mehmet .

RENEWABLE ENERGY, 2012, 46 :241-247

[10]

Cowder R.S., 1990, 1990 CONNECTIONIST M, P117

← 1 2 3 4 5 6 →