0
Research Papers

Time Series Forecasting With Orthogonal Endocrine Neural Network Based on Postsynaptic Potentials

[+] Author and Article Information
Miroslav Milovanović

Faculty of Electronic Engineering,
Department of Control Systems,
University of Niš,
Aleksandra Medvedeva 14,
Niš 18000, Republic of Serbia
e-mail: miroslav.b.milovanovic@elfak.ni.ac.rs

Dragan Antić

Professor
Faculty of Electronic Engineering,
Department of Control Systems,
University of Niš,
Aleksandra Medvedeva 14,
Niš 18000, Republic of Serbia
e-mail: dragan.antic@elfak.ni.ac.rs

Marko Milojković

Assistant Professor
Faculty of Electronic Engineering,
Department of Control Systems,
University of Niš,
Aleksandra Medvedeva 14,
Niš 18000, Republic of Serbia
e-mail: marko.milojkovic@elfak.ni.ac.rs

Saša S. Nikolić

Assistant Professor
Faculty of Electronic Engineering,
Department of Control Systems,
University of Niš,
Aleksandra Medvedeva 14,
Niš 18000, Republic of Serbia
e-mail: sasa.s.nikolic@elfak.ni.ac.rs

Miodrag Spasić

Faculty of Electronic Engineering,
Department of Control Systems,
University of Niš,
Aleksandra Medvedeva 14,
Niš 18000, Republic of Serbia
e-mail: miodrag.spasic@elfak.ni.ac.rs

Staniša Perić

Faculty of Electronic Engineering,
Department of Control Systems,
University of Niš,
Aleksandra Medvedeva 14,
Niš 18000, Republic of Serbia
e-mail: stanisa.peric@elfak.ni.ac.rs

Contributed by the Dynamic Systems Division of ASME for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received December 29, 2015; final manuscript received October 19, 2016; published online February 7, 2017. Assoc. Editor: Sergey Nersesov.

J. Dyn. Sys., Meas., Control 139(4), 041006 (Feb 07, 2017) (9 pages) Paper No: DS-15-1656; doi: 10.1115/1.4035090 History: Received December 29, 2015; Revised October 19, 2016

This paper presents a new type of endocrine neural network (ENN). ENN utilizes artificial glands which enable the network to be adaptive to external disturbances. Sensitivity is controlled by the hormone decay rate and the value of the sensitivity parameter. The network presented in this paper is improved by making the sensitivity parameter self-tuning and implementing orthogonal activation functions inside the network structure. Automatic tuning is performed on the basis of the biological principle of postsynaptic potentials by implementing inhibitory and excitatory glands inside the standard backpropagation learning algorithm of developed orthogonal ENN. These additional network functionalities enable extra sensitivity to external conditions and an additional network feature of activation sharpening. The network was tested on real-time series of experimental data with a purpose to forecast exchange rate of the three widely used international currencies.

FIGURES IN THIS ARTICLE
<>
Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Graphical representation of the binding process between hormones and a network layer

Grahic Jump Location
Fig. 2

Input layer neuron structure

Grahic Jump Location
Fig. 3

Hidden layer neuron structure

Grahic Jump Location
Fig. 4

Output layer neuron structure

Grahic Jump Location
Fig. 5

Generalized OENNPP topology

Grahic Jump Location
Fig. 6

A graphical comparison of GBP rate predictions using six neural network models

Grahic Jump Location
Fig. 7

A graphical comparison of JPY rate predictions using six neural network models

Grahic Jump Location
Fig. 8

A graphical comparison of EUR rate predictions using six neural network models

Grahic Jump Location
Fig. 9

OENNPP error minimization curves during training processes

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In