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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
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.
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.
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.
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
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.
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.
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.
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.
N. Lamei et al., “Cloud-type discrimitation via multispectral textural analysis,” Opt. Eng., vol. 33, pp. 1303–1313, Apr. 1994.
R. M. Haralick et al., “Textural features for image classification”, IEEE trans. Syst., Man, Cybern., vol. SMC-3, pp. 610–621, Mar. 1973.
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.
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.
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.
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.
A. Tettamanzi, M. Tomassini. Soft Computing. Integrating Evolutionary, Neural and Fuzzy Systems. Springer, 2001.
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.
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.
R. Bellman: “Adaptive Control Processes: A Guided Tour”. New Jersey, Princeton University Press.
I. T. Jolliffe: Principal Component Analysis, Springer-Verlag, 271 pp., 1986.
H. F. Kaiser: “The application of electronic computer to factor analysis”, Educ. Psycol. Meas., vol. 20, pp.141–151, 1960.
H. F. Kaiser, “The Varimax criterion for analytic rotation in factor analysis”, Psychometrika, vol. 23, pp. 187–200, 1958.
D.E. Goldberg. Genetic Algorithms in Search, Optimization & Machine Learning. Addison Wesley, 1989.
D. Levine. Users Guide to the PGAPack Parallel Genetic Algorithm Library. Research Report ANL-95/18. Argonne National Laboratory, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 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
DOI: https://doi.org/10.1007/3-540-36131-6_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00131-7
Online ISBN: 978-3-540-36131-2
eBook Packages: Springer Book Archive