Comparison study of computational parameter values between LRN and NARX in identifying nonlinear systems

Research output: Contribution to journalArticle

Abstract

To determine the nonlinear autoregressive model with exogenous inputs (NARX) parameter values is not an easy task, even though NARX is reported to successfully identify nonlinear systems. Apart from the activation functions, number of layers, layer size, learning rate, and number of epochs, the number of delays at the input and at the feedback loop need to also be determined. The layer recurrent network (LRN) is seen to have the potential to outperform NARX. However, not many papers have reported on using the LRN to identify nonlinear systems. Therefore, it is the aim of this paper to investigate and analyze the parametric evaluation of the LRN and NARX in identifying 3 different types of nonlinear systems. From the 3 nonlinear systems, the satellite's attitude state space is more complex compared to the sigmoid and polynomial equations. To ensure an unbiased comparison, a general guideline is used to select the parameter values in an organized manner. The LRN and NARX performance is analyzed based on the training and architecture parameters, mean squared errors, and correlation coefficient values. The results show that the LRN outperformed NARX in training quality, needs equal or fewer parameters that need to be determined through heuristic processes and equal or lower number of epochs, and produced a smaller training error compared to NARX, especially when identifying the satellite's attitude. This indicates that the LRN has the capability of identifying a more complex and nonlinear system compared to NARX.

Original languageEnglish
Pages (from-to)1151-1165
Number of pages15
JournalTurkish Journal of Electrical Engineering and Computer Sciences
Volume21
Issue number4
DOIs
Publication statusPublished - 2013

Fingerprint

Nonlinear systems
Satellites
Large scale systems
Chemical activation
Polynomials
Feedback

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

@article{74a812b88e0444ae9297a0aa6811a680,
title = "Comparison study of computational parameter values between LRN and NARX in identifying nonlinear systems",
abstract = "To determine the nonlinear autoregressive model with exogenous inputs (NARX) parameter values is not an easy task, even though NARX is reported to successfully identify nonlinear systems. Apart from the activation functions, number of layers, layer size, learning rate, and number of epochs, the number of delays at the input and at the feedback loop need to also be determined. The layer recurrent network (LRN) is seen to have the potential to outperform NARX. However, not many papers have reported on using the LRN to identify nonlinear systems. Therefore, it is the aim of this paper to investigate and analyze the parametric evaluation of the LRN and NARX in identifying 3 different types of nonlinear systems. From the 3 nonlinear systems, the satellite's attitude state space is more complex compared to the sigmoid and polynomial equations. To ensure an unbiased comparison, a general guideline is used to select the parameter values in an organized manner. The LRN and NARX performance is analyzed based on the training and architecture parameters, mean squared errors, and correlation coefficient values. The results show that the LRN outperformed NARX in training quality, needs equal or fewer parameters that need to be determined through heuristic processes and equal or lower number of epochs, and produced a smaller training error compared to NARX, especially when identifying the satellite's attitude. This indicates that the LRN has the capability of identifying a more complex and nonlinear system compared to NARX.",
author = "Nordin, {Farah Hani} and Nagi, {Farrukh Hafiz} and {Zainul Abidin}, {Aidil Azwin}",
year = "2013",
doi = "10.3906/elk-1107-12",
language = "English",
volume = "21",
pages = "1151--1165",
journal = "Turkish Journal of Electrical Engineering and Computer Sciences",
issn = "1300-0632",
publisher = "Turkiye Klinikleri",
number = "4",

}

TY - JOUR

T1 - Comparison study of computational parameter values between LRN and NARX in identifying nonlinear systems

AU - Nordin, Farah Hani

AU - Nagi, Farrukh Hafiz

AU - Zainul Abidin, Aidil Azwin

PY - 2013

Y1 - 2013

N2 - To determine the nonlinear autoregressive model with exogenous inputs (NARX) parameter values is not an easy task, even though NARX is reported to successfully identify nonlinear systems. Apart from the activation functions, number of layers, layer size, learning rate, and number of epochs, the number of delays at the input and at the feedback loop need to also be determined. The layer recurrent network (LRN) is seen to have the potential to outperform NARX. However, not many papers have reported on using the LRN to identify nonlinear systems. Therefore, it is the aim of this paper to investigate and analyze the parametric evaluation of the LRN and NARX in identifying 3 different types of nonlinear systems. From the 3 nonlinear systems, the satellite's attitude state space is more complex compared to the sigmoid and polynomial equations. To ensure an unbiased comparison, a general guideline is used to select the parameter values in an organized manner. The LRN and NARX performance is analyzed based on the training and architecture parameters, mean squared errors, and correlation coefficient values. The results show that the LRN outperformed NARX in training quality, needs equal or fewer parameters that need to be determined through heuristic processes and equal or lower number of epochs, and produced a smaller training error compared to NARX, especially when identifying the satellite's attitude. This indicates that the LRN has the capability of identifying a more complex and nonlinear system compared to NARX.

AB - To determine the nonlinear autoregressive model with exogenous inputs (NARX) parameter values is not an easy task, even though NARX is reported to successfully identify nonlinear systems. Apart from the activation functions, number of layers, layer size, learning rate, and number of epochs, the number of delays at the input and at the feedback loop need to also be determined. The layer recurrent network (LRN) is seen to have the potential to outperform NARX. However, not many papers have reported on using the LRN to identify nonlinear systems. Therefore, it is the aim of this paper to investigate and analyze the parametric evaluation of the LRN and NARX in identifying 3 different types of nonlinear systems. From the 3 nonlinear systems, the satellite's attitude state space is more complex compared to the sigmoid and polynomial equations. To ensure an unbiased comparison, a general guideline is used to select the parameter values in an organized manner. The LRN and NARX performance is analyzed based on the training and architecture parameters, mean squared errors, and correlation coefficient values. The results show that the LRN outperformed NARX in training quality, needs equal or fewer parameters that need to be determined through heuristic processes and equal or lower number of epochs, and produced a smaller training error compared to NARX, especially when identifying the satellite's attitude. This indicates that the LRN has the capability of identifying a more complex and nonlinear system compared to NARX.

UR - http://www.scopus.com/inward/record.url?scp=84880109328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880109328&partnerID=8YFLogxK

U2 - 10.3906/elk-1107-12

DO - 10.3906/elk-1107-12

M3 - Article

AN - SCOPUS:84880109328

VL - 21

SP - 1151

EP - 1165

JO - Turkish Journal of Electrical Engineering and Computer Sciences

JF - Turkish Journal of Electrical Engineering and Computer Sciences

SN - 1300-0632

IS - 4

ER -