USP Electronic Research Repository

Identification of minimal timespan problem for recurrent neural networks with application to cyclone wind - intensity prediction

Deo, Ratneel and Chandra, R. (2016) Identification of minimal timespan problem for recurrent neural networks with application to cyclone wind - intensity prediction. [Conference Proceedings]

[img]
Preview
PDF - Published Version
Download (563kB) | Preview

Abstract

Time series prediction relies on past data points to make robust predictions. The span of past data points is important for some applications since prediction will not be possible unless the minimal timespan of the data points is available. This is a problem for cyclone wind-intensity prediction, where prediction needs to be made as a cyclone is identified. This paper presents an empirical study on minimal timespan required for robust prediction using Elman recurrent neural networks. Two different training methods are evaluated for training Elman recurrent network that includes cooperative coevolution and backpropagation-though time. They are applied to the prediction of the wind intensity in cyclones that took place in the South Pacific over past few decades. The results show that a minimal timespan is an important factor that leads to the measure of robustness in prediction performance and strategies should be taken in cases when the minimal timespan is needed.

Item Type: Conference Proceedings
Additional Information: DOI: 10.1109/IJCNN.2016.7727239
Subjects: Q Science > Q Science (General)
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
Depositing User: Ratneel Deo
Date Deposited: 03 Jan 2017 04:23
Last Modified: 08 Jul 2019 23:01
URI: http://repository.usp.ac.fj/id/eprint/9549
UNSPECIFIED

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...