Cuckoo Search Based Optimization of Echo State Network for Time Series Prediction

Abubakar Bala; Idris Ismail; Rosdiazli Ibrahim

doi:10.1109/ICIAS.2018.8540609

Cuckoo Search Based Optimization of Echo State Network for Time Series Prediction

Abubakar Bala, Idris Ismail, Rosdiazli Ibrahim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

The Echo State Network (ESN) is a type of reservoir computing (RC) approach of artificial neural networks. The choice of its parameters and topology have become an optimization problem. This paper proposes a cuckoo search based optimization of three global parameters of the echo state network for time series prediction. The proposed technique is compared with the classical echo state network on the prediction of Mackey-Glass time series. It was found that the cuckoo search based method outperformed the classical ESN.

Original language	English
Title of host publication	International Conference on Intelligent and Advanced System, ICIAS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538672693
DOIs	https://doi.org/10.1109/ICIAS.2018.8540609
State	Published - 19 Nov 2018
Externally published	Yes

Publication series

Name	International Conference on Intelligent and Advanced System, ICIAS 2018

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Keywords

Artificial neural networks
Cuckoo search
Echo state network
Evolutionary algorithms
Lévy flight
Prediction

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Energy Engineering and Power Technology
Health Informatics

Access to Document

10.1109/ICIAS.2018.8540609

Cite this

Bala, A., Ismail, I., & Ibrahim, R. (2018). Cuckoo Search Based Optimization of Echo State Network for Time Series Prediction. In International Conference on Intelligent and Advanced System, ICIAS 2018 Article 8540609 (International Conference on Intelligent and Advanced System, ICIAS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIAS.2018.8540609

@inproceedings{42354e68a22843f3ab308a1a19e34ce1,

title = "Cuckoo Search Based Optimization of Echo State Network for Time Series Prediction",

abstract = "The Echo State Network (ESN) is a type of reservoir computing (RC) approach of artificial neural networks. The choice of its parameters and topology have become an optimization problem. This paper proposes a cuckoo search based optimization of three global parameters of the echo state network for time series prediction. The proposed technique is compared with the classical echo state network on the prediction of Mackey-Glass time series. It was found that the cuckoo search based method outperformed the classical ESN.",

keywords = "Artificial neural networks, Cuckoo search, Echo state network, Evolutionary algorithms, L{\'e}vy flight, Prediction",

author = "Abubakar Bala and Idris Ismail and Rosdiazli Ibrahim",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.",

year = "2018",

month = nov,

day = "19",

doi = "10.1109/ICIAS.2018.8540609",

language = "English",

series = "International Conference on Intelligent and Advanced System, ICIAS 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "International Conference on Intelligent and Advanced System, ICIAS 2018",

address = "United States",

}

Bala, A, Ismail, I & Ibrahim, R 2018, Cuckoo Search Based Optimization of Echo State Network for Time Series Prediction. in International Conference on Intelligent and Advanced System, ICIAS 2018., 8540609, International Conference on Intelligent and Advanced System, ICIAS 2018, Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/ICIAS.2018.8540609

Cuckoo Search Based Optimization of Echo State Network for Time Series Prediction. / Bala, Abubakar; Ismail, Idris; Ibrahim, Rosdiazli.
International Conference on Intelligent and Advanced System, ICIAS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8540609 (International Conference on Intelligent and Advanced System, ICIAS 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Cuckoo Search Based Optimization of Echo State Network for Time Series Prediction

AU - Bala, Abubakar

AU - Ismail, Idris

AU - Ibrahim, Rosdiazli

PY - 2018/11/19

Y1 - 2018/11/19

N2 - The Echo State Network (ESN) is a type of reservoir computing (RC) approach of artificial neural networks. The choice of its parameters and topology have become an optimization problem. This paper proposes a cuckoo search based optimization of three global parameters of the echo state network for time series prediction. The proposed technique is compared with the classical echo state network on the prediction of Mackey-Glass time series. It was found that the cuckoo search based method outperformed the classical ESN.

AB - The Echo State Network (ESN) is a type of reservoir computing (RC) approach of artificial neural networks. The choice of its parameters and topology have become an optimization problem. This paper proposes a cuckoo search based optimization of three global parameters of the echo state network for time series prediction. The proposed technique is compared with the classical echo state network on the prediction of Mackey-Glass time series. It was found that the cuckoo search based method outperformed the classical ESN.

KW - Artificial neural networks

KW - Cuckoo search

KW - Echo state network

KW - Evolutionary algorithms

KW - Lévy flight

KW - Prediction

UR - https://www.scopus.com/pages/publications/85055848481

U2 - 10.1109/ICIAS.2018.8540609

DO - 10.1109/ICIAS.2018.8540609

M3 - Conference contribution

AN - SCOPUS:85055848481

T3 - International Conference on Intelligent and Advanced System, ICIAS 2018

BT - International Conference on Intelligent and Advanced System, ICIAS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Cuckoo Search Based Optimization of Echo State Network for Time Series Prediction

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this