Advertisement

On Predictability of Atmospheric Pollution Time Series

  • Igor R. Krcmar
  • Danilo P. Mandic
  • Robert J. Foxall
Conference paper

Abstract

Atmospheric pollution is a health hazard. Thus, an accurate prediction of atmospheric pollution time series is almost a necessity nowdays. The existence of missing data further complicates this challenging problem. The cubic spline interpolation method is applied on the hourly measurements of nitrogen oxide (NO), nitrogen dioxide (NO 2), ozone (O 3), and dust partides (PM10). In order to asses predictability of an air pollution time series, a class of gradient-descent based neural adaptive filters is employed. Results indicate that, yet simple, this class of neural adaptive filters is a suitable solution.

Keywords

Iterate Function System Nitrogen Dioxide Time Series Prediction Nonlinear Time Series Normalize Little Mean Square 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    N. A. Gershenfeld and A. S. Weigend, “The future of time series: learning and understanding”, Proc. of the NATO Advanced Research Workshop on Comparative Time Series Analysis, pp. 1–70, 1992.Google Scholar
  2. [2]
    M. Casgaali and A. S. Weigend, “Exploring the continuum between deterministic and stochastic modeling”, Proc. of the NATO Advanced Research Workshop on Comparative Time Series Analysis, pp. 347–366, 1992.Google Scholar
  3. [3]
    S. Haykin, “Making sense of a eomplex world”, IEEE Signal Procssing Magazine, vol. 8, pp. 66–81, 1998.CrossRefGoogle Scholar
  4. [4]
    H. Kantz, “Noise reduction by local reeonstruction of the dynamics”, Proc. of the NATO Advanced Research Workshop on Comparative Time Series Analysis, pp. 475–490, 1992.Google Scholar
  5. [5]
    V. Tresp and R. Hofmann, “Nonlinear time-series prediction with missing and noisy data”, Neural Computation, vol. 10, pp. 731–747, 1998.CrossRefGoogle Scholar
  6. [6]
    M. Tanaka, “Identification of nonlinear systems with missing data using stochastie neural network”, Proceedings of the 35th Con/erence on Decision and Control, pp. 933–934, 1996.Google Scholar
  7. [7]
    P. Baldi, “Gradient descent learning algorithm overview: A general dynamical systems perspective”, IEEE Transactions on Neural Networks, vol. 6, no. 1, pp.182–195, 1995.CrossRefGoogle Scholar
  8. [8]
    D. P. Mandie and J. A. Chambers, “Global a symptotic stability of non linear relaxation equations realised through a recurrent perceptron”, Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP-99), vol. 2, pp. 1037–1040, 1999.Google Scholar
  9. [9]
    S. Haykin, Neural networks — A comprehensive foundation, Prentice Hall, 1994.Google Scholar
  10. [10]
    D. P. Mandie and J. A. Chambers, “Relationship between the slope of the activation function and the learning rate for the RNN”, Neural Computation, vol. 11, no. 5, pp. 1069–1077, 2000.CrossRefGoogle Scholar
  11. [11]
    D. P. Mandie, “NNGD algorithm for neural adaptive filters”, Electronic Letters, vol. 36, no. 9, pp. 845–846 2000.CrossRefGoogle Scholar
  12. [12]
    D. S. Mazel and W. N. Sirgany, “Synthesizing missing data points with iterated function systems”, IEEE Workshop on NNSP’ 92, pp. 583–586, 1992.Google Scholar
  13. [13]
    S. C. Douglas and A. Ciehocki, “On-line step-size selection for training of adaptive systems”, IEEE Signal Processing Magazine, vol.14, no. 6. pp. 45–46, 1997.CrossRefGoogle Scholar
  14. [14]
    S. C. Douglas, “A family of normalized LMS algorithms”, IEEE Signal Processing Letters, vol. 1, no. 3, pp. 49–51, 1994.CrossRefGoogle Scholar
  15. [15]
    R. J. Foxall, I. R. Kremar, and D. P. Mandie, “On nonlinear processing of air pollution data”, Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA-2001), 2001.Google Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • Igor R. Krcmar
    • 1
  • Danilo P. Mandic
    • 2
  • Robert J. Foxall
    • 2
  1. 1.Faculty of Electrical EngineeringUniversity of BanjalukaBanjalukaBH
  2. 2.School of Information SystemsUniversity of East AngliaNorwichUK

Personalised recommendations