SciELO - Scientific Electronic Library Online

 
 número48Merging Deductive and Abductive Knowledge Bases: An Argumentation Context ApproachSupply Chain Management by Means of Simulation índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

Links relacionados

  • No hay artículos similaresSimilares en SciELO

Compartir


Polibits

versión On-line ISSN 1870-9044

Polibits  no.48 México jul./dic. 2013

 

Multiscale RBF Neural Network for Forecasting of Monthly Hake Catches off Southern Chile

 

Nibaldo Rodriguez1, Lida Barba2 and Jose Miguel Rubio L.3

 

1 School of Computer Engineering at the Pontificia Universidad Catolica de Valparaiso, Av. Brasil 2241, Chile (e-mail: nibaldo.rodriguez@ucv.cl).

2 School of Computer Engineering at the Universidad Nacional de Chimborazo, Av. Antonio Jose de Sucre, Km 1.5, Ecuador.

3 School of Computer Engineering at the Pontificia Universidad Catolica de Valparaiso, Av. Brasil 2241, Chile.

 

Manuscript received on August 2, 2013.
Accepted for publication on September 30, 2013.

 

Abstract

We present a forecasting strategy based on stationary wavelet transform combined with radial basis function (RBF) neural network to improve the accuracy of 3-month-ahead hake catches forecasting of the fisheries industry in the central southern Chile. The general idea of the proposed forecasting model is to decompose the raw data set into an annual cycle component and an inter-annual component by using 3-levels stationary wavelet decomposition. The components are independently predicted using an autoregressive RBF neural network model. The RBF neural network model is composed of linear and nonlinear weights, which are estimates using the separable nonlinear least squares method. Consequently, the proposed forecaster is the co-addition of two predicted components. We demonstrate the utility of the proposed model on hake catches data set for monthly periods from 1963 to 2008. Experimental results on hake catches data show that the autoregressive RBF neural network model is effective for 3-month-ahead forecasting.

Key words: Neural network, forecasting, nonlinear least squares.

  

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Acknowledgment

This research was partially supported by the Chilean National Science Fund through the project Fondecyt-Regular 1131105 and by the VRIEA of the Pontificia Universidad Católica de Valparaíso.

 

References

[1] k. I. Stergiou and E. d. Christou, "Modelling and forecasting annual fisheries catches: comparison of regression, univariate and multivariate time series," Fisheries Research, vol. 25, pp. 105-138, 1996.         [ Links ]

[2] k. I. Stergiou, "Prediction of the mullidae fishery in the eastern mediterranean 24 months in advance," Fisheries Research, vol. 9, issues 1, pp. 67-74, 1990.         [ Links ]

[3] J. C. Gutierrez-Estrada, C. Silva, E. Yañez, N. Rodriguez, and I. Pulido-Calvo, "Monthly catch forecasting of anchovy engraulis ringens in the north area of Chile: Non-linear univariate approach," Fisheries Research, vol. 86, pp. 188-200, 2007.         [ Links ]

[4] J. Gutierrez-Estrada, E. Yañez, I. Pulido, C. Silva, f. Plaza, and C. Borquez, "Pacific sardine (sardinops sagax, jenyns 1842) landings prediction: A neural network ecosystemic approach," Fisheries Research, vol. 100, pp. 116-125, 2009.         [ Links ]

[5] E. Yañez, F. Plaza, J. Gutierrez, N. Rodriguez, M. Barbieri, I. Pulido, and C. Borquez, "Anchovy (engraulis ringens) and sardine (sardinops sagax) abundance forecast of northern Chile: A multivariate ecosystemic neural network approach," Progress in Oceanography, vol. 87, pp. 242-250, 2010.         [ Links ]

[6] o. Kisi, "Stream flow forecasting using neuro-wavelet technique," Hydrological Processes, vol. 22, issues 20, pp. 4142-4152, 2008.         [ Links ]

[7] F. K. Nima A., "Day ahead price forecasting of electricity markets by a mixed data model and hybrid forecast method," International Journal of Electrical Power & Energy Systems, vol. 30, issue 9, pp. 533-546, 2008.         [ Links ]

[8] Z. Bai-Ling, C. Richard, M. Jabri, D. Dersch, and B. Flower, "Multires-olution forecasting for futures trading using wavelet decompositions," IEEE Transaction on neural networks, vol. 12, pp. 765-775, 2001.         [ Links ]

[9] R. R. Coifman and D. L. Donoho, "Translation-invariant de-noising," in Lecture Notes in Statistics: Wavelets and Statistics. Springer-Verlag, 1995.         [ Links ]

[10] G. Nason and B. Silverman, "The stationary wavelet transform and some statistical applications." in In: Lecture Notes in Statistics: Wavelets and Statistics, 1995.         [ Links ]

[11] J. Pesquet, H. Krim, and H. Carfantan, "Time-invariant orthonormal wavelet representations," IEEE transactions on signal processing, vol. 44, pp. 1964-1970, 1996.         [ Links ]

[12] D. B. Percival and A. T. Walden, Wavelet Methods for Time Series Analysis, C. U. Press, Ed. Cambridge, England, 2000.         [ Links ]

[13] D. Serre, Matrices: theory and applications, Springer, Ed. New York, 2002.         [ Links ]

[14] D. Marquardt, "An algorithm for least-squares estimation of nonlinear parameters," Journal of the Society for Industrial and Applied Mathematics, vol. 11(2), pp. 431-441, 1963.         [ Links ]

Creative Commons License Todo el contenido de esta revista, excepto dónde está identificado, está bajo una Licencia Creative Commons