Abstract
The problem of multimodel prediction of multivariate time series is considered. A fuzzy method for selection of the best model and combining of predictions is proposed in batch and recurrent forms. The method allows to estimate degrees of membership of the current state of a process to the modes described by different models.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Hansen, L.K., Salamon, P.: Neural network ensembles. IEEE Trans. on Pattern Analysis and Machine Intelligence 12, 993–1000 (1990)
Bishop, C.M.: Neural Networks for Pattern Recognition, p. 482. Clarendon Press, Oxford (1995)
Sharkey, A.J.C.: On combining artificial neural nets. Connect. Sci. 8(3,4), 299–313 (1996)
Opitz, D.W., Shavlik, J.W.: Actively searching for an effective neural network ensemble. Connect. Sci. 8(3,4), 337–353 (1996)
Hashem, S.: Optimal linear combination of neural networks. Neural Networks 10(4), 599–614 (1997)
Ye., B., Pliss, O.P., Popov, I., S.: An Optimal Algorithm for Combining Multivariate Forecasts in Hybrid Systems. In: Proc. 7th Int. Conf. on Knowledge-based intelligent information and engineering systems (KES 2003), Oxford, UK, September 3 - 5, Part II, pp. 967–972 (2003)
Bodyanskiy Ye., V., Pliss, I.P., Solovyeva, T.V.: Adaptive Generalized Forecasting of Multivariate Random Sequences. Doklady AN USSR. 9, 73–75 (1989) (In Russian)
Ye, B.: Recurrent neural network detecting changes in the properties of nonlinear stochastic sequences. Automation and Remote Control 1(7), 1113–1124 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bodyanskiy, Y., Popov, S. (2004). Fuzzy Selection Mechanism for Multimodel Prediction. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2004. Lecture Notes in Computer Science(), vol 3214. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30133-2_101
Download citation
DOI: https://doi.org/10.1007/978-3-540-30133-2_101
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23206-3
Online ISBN: 978-3-540-30133-2
eBook Packages: Springer Book Archive