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). 198 - 200. ISSN 0013-5194
|PDF - Accepted Version |
Available under License : See the attached licence file.
|Plain Text (licence)|
Official URL: http://dx.doi.org/10.1049/el:20058016
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.
|Uncontrolled Keywords:||SERIES, ARIMA, MODEL|
|Divisions:||Faculty of Engineering and Physical Sciences > Computing Science|
|Deposited By:||Symplectic Elements|
|Deposited On:||22 Jun 2011 13:48|
|Last Modified:||16 Feb 2013 16:04|
Repository Staff Only: item control page