A wavelet neural network model for spatio-temporal image processing and modeling

Wei, Hua-Liang, Yifan, Zhao and Jiang, Richard (2015) A wavelet neural network model for spatio-temporal image processing and modeling. In: The 10th International Conference on Computer Science & Education, 22nd - 24th July 2015, Cambridge.

Full text not available from this repository.

Abstract

Spatio-temporal images are a class of complex dynamical systems that evolve over both space and time. Compared with pure temporal processes, the identification of spatio-temporal models from observed images is much more difficult and quite challenging. Starting with an assumption that there is no a priori information about the true model but only observed data are available, this work introduces a new type of wavelet network that utilizes the easy tractability and exploits the good properties of multiscale wavelet decompositions to represent the rules of the associated spatio-temporal evolutionary system. An application to a chemical reaction exhibiting a spatiotemporal evolutionary behaviour, is investigated to demonstrate the application of the proposed modeling and learning approaches.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Spatio-temporal systems, learning from data, system identification, wavelet neural networks
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Richard Jiang
Date Deposited:	17 Sep 2015 14:39
Last Modified:	12 Oct 2019 22:51
URI:	http://nrl.northumbria.ac.uk/id/eprint/23777

Downloads