Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/20709

Title: Structure optimisation of input layer for feed-forward NARX neural network
Authors: Li, Zongyan
Best, Matt C.
Keywords: Optimisation
Correlation analysis
Neural network
Issue Date: 2016
Publisher: © Inderscience
Citation: LI, Z. and BEST, M.C., 2016. Structure optimisation of input layer for feed-forward NARX neural network. International Journal of Modelling, Identification and Control, 25 (3), pp. 217-226.
Abstract: This paper presents an optimization method for reducing the number of input channels and the complexity of the feed-forward NARX neural network (NN) without compromising the accuracy of the NN model. By utilizing the correlation analysis method, the most significant regressors are selected to form the input layer of the NN structure. Applications of vehicle handling and ride model identification are presented in this paper to demonstrate the optimization technique. The optimal input layer structure and the optimal number of neurons for the NN models are investigated and the results show that the optimised NN model requires significantly less coefficients and training time while maintains high simulation accuracy compared with that of the unoptimised model.
Description: This paper was accepted for publication in the journal International Journal of Modelling and the definitive published version is available at http://dx.doi.org/10.1504/IJMIC.2016.075814
Sponsor: This work was supported by Jaguar Land Rover and the UK-EPSRC grant EP/K014102/1 as part of the jointly funded Programme for Simulation Innovation.
Version: Accepted for publication
DOI: 10.1504/IJMIC.2016.075814
URI: https://dspace.lboro.ac.uk/2134/20709
Publisher Link: http://dx.doi.org/10.1504/IJMIC.2016.075814
ISSN: 1746-6172
Appears in Collections:Published Articles (Aeronautical and Automotive Engineering)

Files associated with this item:

File Description SizeFormat
author_final_version.pdfAccepted version315.44 kBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.