A Particle filter based Neural Network Training Algorithm for the Modeling of North Atlantic Oscillation
Archana R, A Unnikrishnan and R Gopikakumari. Article: A Particle filter based Neural Network Training Algorithm for the Modeling of North Atlantic Oscillation. IJCA Proceedings on International Conference on Advanced Computing and Communication Techniques for High Performance Applications ICACCTHPA 2014(5):6-12, February 2015. Full text available. BibTeX
@article{key:article,
author = {Archana R and A Unnikrishnan and R. Gopikakumari},
title = {Article: A Particle filter based Neural Network Training Algorithm for the Modeling of North Atlantic Oscillation},
journal = {IJCA Proceedings on International Conference on Advanced Computing and Communication Techniques for High Performance Applications},
year = {2015},
volume = {ICACCTHPA 2014},
number = {5},
pages = {6-12},
month = {February},
note = {Full text available}
}
Abstract
Chaotic dynamical systems are present in the nature in various forms such as the weather, activities in human brain, variation in stock market, flows and turbulence. In order to get a detailed understanding of a system, the modeling and analysis of the system is to be done in an effective way. A recurrent neural network (RNN) structure has been designed for modeling the dynamical system. The neural network weights are estimated using the Particle Filter algorithm. There are various natural systems, which can be represented by chaotic dynamical systems. But closed form mathematical equations for such systems are not readily available for generating such time series. The North Atlantic oscillations are one such system which is modeled with the selected RNN model structure and Particle Filter algorithm. While the model faithfully reproduces the given time series, the phase plane generated unravels the dynamics of the system. The characterization of the natural chaotic systems is done in the time domain by Embedding Dimension, Phase plots and Lyapunov Exponents.
References
- Devany, " A first course in chaotic dynamical systems: theory and experiments", Persues publications, 1992 .
- S Chen, S A Billings, "Neural networks for nonlinear system modeling and identification", International journal of control, vol. 56, issue2, pp. 319-346, 1992.
- Simon Haykin, " Neural networks-A comprehensive foundation", 2nd edition, Pearson education, 1999.
- Puskorius G V, L A Feldkamp, "Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks
- A Bullineria, " Neural computations: Lecture 2", 2014.
- Puskorius G V, L A Feldkamp, "Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks",
- Si-Zhao, Quin Hong, Thomas J Mc Avoy "Comparison of four Neural network learning methods for dynamic system modeling", IEEE Transactions on neural networks, vol. 3, pp 192-198, 1992
- A. Doucet, A. M. Johansen, "A Tutorial on Particle Filtering and Smoothing?: Fifteen years later," Version 1. 1, 2008.
- Afonso, Manya. "Particle filter and extended kalman filter for nonlinear estimation: a comparative study. " IEEE Transactions on Signal Processing,pp1- 10, 2008.
- M. S. Arulampalam, S. Maskell, N. Gordon, T. Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Transaction on Signal Processing. , vol. 50, no. 2, pp. 174–188, 2002.
- Torma, Péter, and Csaba Szepesvári. "Combining local search, neural networks and particle filters to achieve fast and reliable contour tracking. " Proceedings of the IEEE International Symposium on Intelligent Signal Processing. 2003
- Q. Wen and P. Qicoiig, "An improved particle filter algorithm based on neural network,"IFIP International Federation for Information Processing, vol. 228, pp. 297–305, 2006.
- Takens F "On the numerical determination of dimension of an attractor", Springer Lecture notes on Mathematics, vol. 898 pp. 230-241, 1981
- Takens F "Detecting strange attractors in turbulence" Springer Lecture Notes in Mathematics", vol. 898, pp. 366–381, 1981
- P Hong, C Peterson. "Finding the embedding dimension and variable dependencies in time series", Neural Computation, vol. 6, no. 3, pp. 509-520, 1994
- Liangyue Cao, "Practical method for determining the minimum embedding dimension from a scalar time series", Physica D: Nonlinear Phenomena, vol. 1, no. 10, pp. 43-50, 1997
- J. C. Robinson, "Takens' embedding theorem for infinite-dimensional dynamical systems", Nonlinearity, vol2, pp. 1–10,1999
- Arun V. Holden, "Chaotic behavior in systems" -Manchester University Press, 1986
- Lennart Ljung, "System identification – Theory for the user" , Prentice Hall, 1987
- M. T. Rosenstein, J. J. Collins, C. J. De Luca, "A practical method for calculating largest Lyapunov exponents from small data sets", Physica D: Nonlinear Phenomina, vol. 65, no. 1, pp. 117-134, 1993
- M Bask, R Gencay, "Testing chaotic dynamics via Lyapunov exponents", Physica D, vol. 114, pp. 1–2, 1998
- R J Greatbatch, "The North Atlantic Oscillation," Stochastic Environmental Research and Risk assessment, no. 14, pp. 213-242, 2000
- Collette, Christophe, M. Ausloos. "Scaling analysis and evolution equation of the North Atlantic oscillation index fluctuations. " International journal of modern physics C 15. 10 , pp. 1353-1366, 2004
- E. P. Gerber, "A Dynamical and Statistical Understanding of the North Atlantic Oscillation and Annular Modes," Ph. D Thesis, Princeton University, 2006
- S. M. Osprey, U. Kingdom, M. H. P. Ambaum, and U. King-, "Evidence for the Chaotic Origin of Northern Annular Mode Variability", Geophysical Research letters, 2011.
- Archana R, A Unnikrishnan, R Gopikakumari, " Modelling of Venice lagoon time series with improved Kalman filter based neural networks", International journal for computer applications, Special issue ACCTHPCA, 2012
- Archana R, A Unnikrishnan, R Gopikakumari, "Computation of state space evolution of chaotic systems from time series of output, based on neural networks", International Journal for engineering research and development, vol. 2, Issue. 2, pp 49-56, 2012
- NAO data: Climatic Research Unit, University of East Anglia, http://www. cru. uea. ac. uk/cru/data/nao/nao. dat
- National Oceanic and Atmospheric Administration(NOAA), United State Department of Commerce, http://oceanservice. noaa. gov