A Comparison of PCA and GA Selected Features for Cloud Field Classification (original) (raw)

Abstract

In this work a back propagation neural network (BPNN) is used for the segmentation of Meteosat images covering the Iberian Peninsula. The images are segmented in the classes land (L), sea (S), fog (F), low clouds (CL), middle clouds (CM), high clouds (CH) and clouds with vertical growth (CV). The classification is performed from an initial set of several statistical textural features based on the gray level co-occurrence matrix (GLCM) proposed by Welch [1]. This initial set of features is made up of 144 parameters and to reduce its dimensionality two methods for feature selection have been studied and compared. The first one includes genetic algorithms (GA) and the second is based on principal component analysis (PCA). These methods are conceptually very different. While GA interacts with the neural network in the selection process, PCA only depends on the values of the initial set of features.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Welch, R.M., Kuo K. S., Sengupta S. K., and Chen D. W.: Cloud field classification based upon high spatial resolution textural feature (I): Gray-level cooccurrence matrix approach. J. Geophys. Res., vol. 93, (oct.1988) 12633–81.
    Google Scholar
  2. Lee J., Weger R. C., Sengupta S. K. And Welch R.M.: A Neural Network Approach to Cloud Classification. IEEE Transactions on Geoscience and Remote Sensing, vol. 28, no. 5, pp. 846–855, Sept. 1990.
    Article Google Scholar
  3. M. Macías, F.J. López, A. Serrano and A. Astillero: “A Comparative Study of two Neural Models for Cloud Screening of Iberian Peninsula Meteosat Images”, Lecture Notes in Computer Science 2085, Bio-inspired applications of connectionism, pp. 184–191, 2001.
    Google Scholar
  4. A. Astillero, A Serrano, M. Núñez, J.A. García, M. Macías and H.M. Gónzalez: “A Study of the evolution of the cloud cover over Cáceres (Spain) along 1997, estimated from Meteosat images”, Proceedings of the 2001 EUMETSAT Meteorological Satellite Data Users’ Conference, pp. 353–359, 2001
    Google Scholar
  5. Bankert, R. L et al.,: Cloud Classification of AVHRR Imagery in Maritime Regions Using a Probabilistic Neural Network. Journal of Applied. Meteorology, 33, (1994) 909–918.
    Article Google Scholar
  6. B. Tian, M. A. Shaikh, M R. Azimi, T. H. Vonder Haar, and D. Reinke, “An study of neural network-based cloud classification using textural and spectral features,” IEE trans. Neural Networks, vol. 10, pp. 138–151, 1999.
    Article Google Scholar
  7. B. Tian, M. R. Azimi, T. H. Vonder Haar, and D. Reinke, “Temporal Updating Scheme for Probabilistic Neural Network with Application to Satellite Cloud Classification,” IEEE trans. Neural Networks, Vol. 11, no. 4, pp. 903–918, Jul. 2000.
    Article Google Scholar
  8. R. M. Welch et al., “Polar cloud and surface classification using AVHRR imagery: An intercomparison of methods,” J. Appl. Meteorol., vol. 31, pp. 405–420, May 1992.
    Google Scholar
  9. N. Lamei et al., “Cloud-type discrimitation via multispectral textural analysis,” Opt. Eng., vol. 33, pp. 1303–1313, Apr. 1994.
    Google Scholar
  10. R. M. Haralick et al., “Textural features for image classification”, IEEE trans. Syst., Man, Cybern., vol. SMC-3, pp. 610–621, Mar. 1973.
    Google Scholar
  11. M. F. Augfieijin, “Performance evaluation of texture measures for ground cover identification in satellite images by means of a neural.network classifier,” IEEE trans. Geosc. Remote Sensing, vol. 33, pp. 616–625, May 1995.
    Google Scholar
  12. Doak J. An evaluatin of feature selection methods and their application to computer security (Technical Repor CSE-92-18). Davis, CA: University of California, Department of Computer Science.
    Google Scholar
  13. Aha, D. W., and Bankert, R. L.: A Comparative Evaluation of Sequential Feature Selection Algorithms. Artificial Intelligence and Statistics V., D. Fisher and J. H. Lenz, editors. Springer-Verlag, New York, 1996.
    Google Scholar
  14. Eng Hock Tay F. and Li Juan Cao, A comparative study of saliency analysis and genetic algorithm for feature selection in support vector machines”, Intelligent Data Analysis, vol. 5, no. 3, pp. 191–209, 2001.
    MATH Google Scholar
  15. A. Tettamanzi, M. Tomassini. Soft Computing. Integrating Evolutionary, Neural and Fuzzy Systems. Springer, 2001.
    Google Scholar
  16. F.Z._Brill, D.E. Brown and W.N. Martin. Fast genetic selection of features for neural network classifiers. IEEE Transactions on Neural Networks, 3(2): 324–328, 1992.
    Article Google Scholar
  17. M. Riedmiller, M., Braun, L.: A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm. In Proceedings of the IEEE International Conference on Neural Networks 1993 (ICNN 93), 1993.
    Google Scholar
  18. R. Bellman: “Adaptive Control Processes: A Guided Tour”. New Jersey, Princeton University Press.
    Google Scholar
  19. I. T. Jolliffe: Principal Component Analysis, Springer-Verlag, 271 pp., 1986.
    Google Scholar
  20. H. F. Kaiser: “The application of electronic computer to factor analysis”, Educ. Psycol. Meas., vol. 20, pp.141–151, 1960.
    Article Google Scholar
  21. H. F. Kaiser, “The Varimax criterion for analytic rotation in factor analysis”, Psychometrika, vol. 23, pp. 187–200, 1958.
    Article MATH Google Scholar
  22. D.E. Goldberg. Genetic Algorithms in Search, Optimization & Machine Learning. Addison Wesley, 1989.
    Google Scholar
  23. D. Levine. Users Guide to the PGAPack Parallel Genetic Algorithm Library. Research Report ANL-95/18. Argonne National Laboratory, 1996.
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. Departamento de Electrónica e Ingeniería Electromecánica, Universidad de Extremadura, Avda. de Elvas s/n, 06071, Badajoz, Spain
    Miguel Macías-Macías & Carlos J. García-Orellana
  2. Departamento de Física, Universidad de Extremadura, Avda. de Elvas s/n, 06071, Badajoz, Spain
    Horacio M. González-Velasco, Ramón Gallardo-Caballero & Antonio Serrano-Pérez

Authors

  1. Miguel Macías-Macías
  2. Carlos J. García-Orellana
  3. Horacio M. González-Velasco
  4. Ramón Gallardo-Caballero
  5. Antonio Serrano-Pérez

Editor information

Editors and Affiliations

  1. Telefónica Investigación y Desarrollo, Emilio Vargas 6, 28043, Madrid, Spain
    Francisco J. Garijo
  2. Dpto. Lenguajes y Sistemas Informáticos, Universidad de Sevilla, ETS Ingeniería Informática, 41012, Seville, Spain
    José C. Riquelme & Miguel Toro &

Rights and permissions

© 2002 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Macías-Macías, M., García-Orellana, C.J., González-Velasco, H.M., Gallardo-Caballero, R., Serrano-Pérez, A. (2002). A Comparison of PCA and GA Selected Features for Cloud Field Classification. In: Garijo, F.J., Riquelme, J.C., Toro, M. (eds) Advances in Artificial Intelligence — IBERAMIA 2002. IBERAMIA 2002. Lecture Notes in Computer Science(), vol 2527. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36131-6\_5

Download citation

Keywords

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.

Publish with us