Advertisement

Boosting for real and functional samples: an application to an environmental problem

  • B. M. Fernández de CastroEmail author
  • W. González Manteiga
Original Paper

Abstract

In this paper, boosting techniques are given in order to forecast SO2 levels near a power plant. We use boosting with neural networks to forecast real values of SO2 concentration. Then, the data are considered as a time series of curves. Assuming a lag one dependence, the predictions are computed using the functional kernel and the linear autoregressive Hilbertian model. Boosting techniques are developed for those functional models. We compare results of functional boosting with different starting points and iterate models. We carry out the estimation, in real and functional cases, with the information given by a historical matrix, which is a subsample that emphasizes relevant SO2 values.

Keywords

Neural networks Functional data Boosting Air pollutant 

Notes

Acknowledgements

Financial support by MCyT Grant BFM2002-03213 (European FEDER support included), Dirección Xeral de I+D (Xunta de Galicia) Grant PGIDT03PXIC20702PN and ENDESA GENERACIÓN S.A. under Dirección Xeral de I+D (Xunta de Galicia) Grant PGIDIT03TAM08E.

References

  1. Angulo JM, González Manteiga W, Febrero Bande M, Alonso FJ (1998) Semi-parametric statistical approaches for space–time process prediction. Environ Ecol Stat 5:297–316CrossRefGoogle Scholar
  2. Besse P, Cardot H (1996) Spline approximation of the prediction of a first-order autoregressive functional process. Can J Stat 24:467–487CrossRefGoogle Scholar
  3. Besse P, Cardot H, Stephenson D (2000) Autoregressive forecasting of some functional climatic variations. Scand J Stat 27(4):673–687CrossRefGoogle Scholar
  4. Borra S, Di Ciaccio A (2002) Improving nonparametric regression methods by bagging and boosting. Comput Stat Data Anal 38:407–420CrossRefGoogle Scholar
  5. Bosq D (2000) Linear processes in function spaces. Springer, New YorkGoogle Scholar
  6. Bühlmann P, Yu B (2003) Boosting with L2-loss: regression and classification. JASA 98:324–339Google Scholar
  7. Damon J, Guillas S (2002) The inclusion of exogenous variables in functional autoregressive ozone forecasting. Environmetrics 13:759–774CrossRefGoogle Scholar
  8. Fernández de Castro BM, Prada Sánchez JM, González Manteiga W, Febrero Bande M, Bermúdez Cela JL, Hernández Fernández JJ (2003) Prediction of SO2 level using neural networks. J Air Waste Manage Assoc 53:532–538Google Scholar
  9. Fernández de Castro BM, Guillas S, González Mantenga W (2005) Functional samples and bootstrap for predicting sulfur dioxide levels. Technometrics 47:212–221CrossRefGoogle Scholar
  10. García Jurado I, González Manteiga W, Febrero Bande M, Prada Sánchez J, Cao R (1995) Predicting using Box-Jenkins, nonparametric and bootstrap techniques. Technometrics 37:303–310CrossRefGoogle Scholar
  11. Guillas S (2001) Rates of convergence of autocorrelation estimates for autoregressive Hilbertian processes. Stat Probab Lett 55:281–291CrossRefGoogle Scholar
  12. Guillas S (2002) Doubly stochastic Hilbertian processes. J Appl Prob 39:566–580CrossRefGoogle Scholar
  13. Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning: data mining, inference and prediction. Springer, New YorkGoogle Scholar
  14. Prada Sánchez JM, Febrero Bande M, Cotos Yánez T, González Manteiga W, Bermúdez Cela JL, Lucas Domínguez T (2000) Prediction of SO2 pollution incidents near a power station using partially linear models and a historical matrix of predictor-response vectors. Environmetrics 11:209–225CrossRefGoogle Scholar
  15. Ramsay JO, Silverman BW (2002) Applied functional data analysis: methods and case studies. Springer, New YorkGoogle Scholar
  16. Ripley BD (1996) Pattern recognition and neural networks. Cambridge University Press, CambridgeGoogle Scholar

Copyright information

© Springer-Verlag 2007

Authors and Affiliations

  • B. M. Fernández de Castro
    • 1
    Email author
  • W. González Manteiga
    • 2
  1. 1.Marketing Estratégico Caixa GaliciaA CoruñaSpain
  2. 2.Department of Statistics and Operation ResearchUniversity of Santiago de CompostelaSantiago de CompostelaSpain

Personalised recommendations