Surrey researchers Sign in
Pre-processing inputs for optimally-configured time-delay neural networks
Journal article   Open access  Peer reviewed

Pre-processing inputs for optimally-configured time-delay neural networks

T Taskaya-Temizel, MC Casey and K Ahmad
Electronics Letters, Vol.41(4), pp.198-200
17/02/2005

Abstract

SERIES ARIMA MODEL
A procedure for pre-processing non-stationary time series is proposed for modelling with a time-delay neural network (TDNN). The procedure stabilises the mean of the series and uses a fast Fourier transform to determine the TDNN input size. Results of applying this procedure on five well-known data sets are compared with existing hybrid neural network techniques, demonstrating improved prediction performance.
pdf
Pre-print66.08 kBDownloadView
TextSRIDA Open Access
url
http://dx.doi.org/10.1049/el:20058016View
Published (Version of record)
url
http://www.theiet.org/View

Metrics

267 File views/ downloads
23 Record Views

Details

Usage Policy