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

Simple item page
dc.citedby0
dc.contributor.authorNordin F.H.en_US
dc.contributor.authorNagi F.H.en_US
dc.contributor.authorZainul Abidin A.A.en_US
dc.contributor.authorid25930510500en_US
dc.contributor.authorid56272534200en_US
dc.contributor.authorid25824750400en_US
dc.date.accessioned2023-12-29T07:44:02Z
dc.date.available2023-12-29T07:44:02Z
dc.date.issued2013
dc.description.abstractTo 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. � T�bi?tak.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.3906/elk-1107-12
dc.identifier.epage1165
dc.identifier.issue4
dc.identifier.scopus2-s2.0-84880109328
dc.identifier.spage1151
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84880109328&doi=10.3906%2felk-1107-12&partnerID=40&md5=f72cc3b674699ced3cbb47f4c4057690
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/30021
dc.identifier.volume21
dc.pagecount14
dc.relation.ispartofAll Open Access; Bronze Open Access
dc.sourceScopus
dc.sourcetitleTurkish Journal of Electrical Engineering and Computer Sciences
dc.subjectLayer recurrent network
dc.subjectNonlinear autoregressive with exogenous inputs
dc.subjectNonlinear system identification
dc.subjectRecurrent neural network
dc.subjectComplex networks
dc.subjectIdentification (control systems)
dc.subjectNetwork layers
dc.subjectPolynomials
dc.subjectRecurrent neural networks
dc.subjectActivation functions
dc.subjectComputational parameters
dc.subjectCorrelation coefficient
dc.subjectInvestigate and analyze
dc.subjectNon-linear autoregressive with exogenous
dc.subjectNonlinear autoregressive model with exogenous input (NARX)
dc.subjectPolynomial equation
dc.subjectRecurrent networks
dc.subjectNonlinear systems
dc.titleComparison study of computational parameter values between LRN and NARX in identifying nonlinear systemsen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS