Home > Research > Publications & Outputs > An ARMA Type Pi-Sigma Artificial Neural Network...

Research

Links

Text available via DOI:

Keywords

View graph of relations

An ARMA Type Pi-Sigma Artificial Neural Network for Nonlinear Time Series Forecasting

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

An ARMA Type Pi-Sigma Artificial Neural Network for Nonlinear Time Series Forecasting. / Akdeniz, Esra; Egrioglu, Erol; Bas, Eren et al.
In: Journal of Artificial Intelligence and Soft Computing Research, Vol. 8, No. 2, 01.04.2018, p. 121-132.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Akdeniz, E, Egrioglu, E, Bas, E & Yolcu, U 2018, 'An ARMA Type Pi-Sigma Artificial Neural Network for Nonlinear Time Series Forecasting', Journal of Artificial Intelligence and Soft Computing Research, vol. 8, no. 2, pp. 121-132. https://doi.org/10.1515/jaiscr-2018-0009

APA

Akdeniz, E., Egrioglu, E., Bas, E., & Yolcu, U. (2018). An ARMA Type Pi-Sigma Artificial Neural Network for Nonlinear Time Series Forecasting. Journal of Artificial Intelligence and Soft Computing Research, 8(2), 121-132. https://doi.org/10.1515/jaiscr-2018-0009

Vancouver

Akdeniz E, Egrioglu E, Bas E, Yolcu U. An ARMA Type Pi-Sigma Artificial Neural Network for Nonlinear Time Series Forecasting. Journal of Artificial Intelligence and Soft Computing Research. 2018 Apr 1;8(2):121-132. Epub 2017 Nov 1. doi: 10.1515/jaiscr-2018-0009

Author

Akdeniz, Esra ; Egrioglu, Erol ; Bas, Eren et al. / An ARMA Type Pi-Sigma Artificial Neural Network for Nonlinear Time Series Forecasting. In: Journal of Artificial Intelligence and Soft Computing Research. 2018 ; Vol. 8, No. 2. pp. 121-132.

Bibtex

@article{03448bbe41ca402c86a39ce9005253f0,
title = "An ARMA Type Pi-Sigma Artificial Neural Network for Nonlinear Time Series Forecasting",
abstract = "Real-life time series have complex and non-linear structures. Artificial Neural Networks have been frequently used in the literature to analyze non-linear time series. High order artificial neural networks, in view of other artificial neural network types, are more adaptable to the data because of their expandable model order. In this paper, a new recurrent architecture for Pi-Sigma artificial neural networks is proposed. A learning algorithm based on particle swarm optimization is also used as a tool for the training of the proposed neural network. The proposed new high order artificial neural network is applied to three real life time series data and also a simulation study is performed for Istanbul Stock Exchange data set.",
keywords = "forecasting, High order artificial neural networks, Particle Swarm Optimization, pi-sigma neural network, recurrent neural network",
author = "Esra Akdeniz and Erol Egrioglu and Eren Bas and Ufuk Yolcu",
year = "2018",
month = apr,
day = "1",
doi = "10.1515/jaiscr-2018-0009",
language = "English",
volume = "8",
pages = "121--132",
journal = "Journal of Artificial Intelligence and Soft Computing Research",
issn = "2449-6499",
publisher = "De Gruyter Open Ltd.",
number = "2",

}

RIS

TY - JOUR

T1 - An ARMA Type Pi-Sigma Artificial Neural Network for Nonlinear Time Series Forecasting

AU - Akdeniz, Esra

AU - Egrioglu, Erol

AU - Bas, Eren

AU - Yolcu, Ufuk

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Real-life time series have complex and non-linear structures. Artificial Neural Networks have been frequently used in the literature to analyze non-linear time series. High order artificial neural networks, in view of other artificial neural network types, are more adaptable to the data because of their expandable model order. In this paper, a new recurrent architecture for Pi-Sigma artificial neural networks is proposed. A learning algorithm based on particle swarm optimization is also used as a tool for the training of the proposed neural network. The proposed new high order artificial neural network is applied to three real life time series data and also a simulation study is performed for Istanbul Stock Exchange data set.

AB - Real-life time series have complex and non-linear structures. Artificial Neural Networks have been frequently used in the literature to analyze non-linear time series. High order artificial neural networks, in view of other artificial neural network types, are more adaptable to the data because of their expandable model order. In this paper, a new recurrent architecture for Pi-Sigma artificial neural networks is proposed. A learning algorithm based on particle swarm optimization is also used as a tool for the training of the proposed neural network. The proposed new high order artificial neural network is applied to three real life time series data and also a simulation study is performed for Istanbul Stock Exchange data set.

KW - forecasting

KW - High order artificial neural networks

KW - Particle Swarm Optimization

KW - pi-sigma neural network

KW - recurrent neural network

U2 - 10.1515/jaiscr-2018-0009

DO - 10.1515/jaiscr-2018-0009

M3 - Journal article

AN - SCOPUS:85033450446

VL - 8

SP - 121

EP - 132

JO - Journal of Artificial Intelligence and Soft Computing Research

JF - Journal of Artificial Intelligence and Soft Computing Research

SN - 2449-6499

IS - 2

ER -