University of Surrey

Test tubes in the lab Research in the ATI Dance Research

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

Taskaya-Temizel, T, Casey, MC and Ahmad, K (2005) Pre-processing inputs for optimally-configured time-delay neural networks Electronics Letters, 41 (4). pp. 198-200.

Pre-print.pdf - Accepted version Manuscript
Available under License : See the attached licence file.

Download (67kB)
[img] Text (licence)

Download (1kB)


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.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Computing Science
Authors :
Taskaya-Temizel, T
Casey, MC
Ahmad, K
Date : 17 February 2005
DOI : 10.1049/el:20058016
Uncontrolled Keywords : SERIES, ARIMA, MODEL
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 22 Jun 2011 12:48
Last Modified : 31 Oct 2017 14:07

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800