Pre-processing inputs for optimally-configured time-delay neural networks
ELECTRONICS LETTERS, vol.41, no.4, pp.198-200, 2005 (SCI-Expanded, Scopus)
- Publication Type: Article / Article
- Volume: 41 Issue: 4
- Publication Date: 2005
- Doi Number: 10.1049/el:20058016
- Journal Name: ELECTRONICS LETTERS
- Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
- Page Numbers: pp.198-200
- Middle East Technical University Affiliated: No
Abstract
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.