Genetic programming to extract features from the whole-sky camera for cloud type classification J. Huertas, J. Rodríguez-Benítez, D. Pozo, R. Aler, Inés M. Galván   2017/04/25

Abstract

In the automatic cloud classification problem it is very important to extract relevant features from the cloud images that can be used as inputs to the classifiers. Typically, sets of hand-designed features, based on the red, green, and blue channels, are used. For instance, spectral and textural, among other characteristics, are commonly extracted from cloud images. Genetic Programming is a powerful tool that has been used to automatically generate functions in a variety of problems. In this work, it is proposed to use Genetic Programming to automatically construct image features for cloud classification. Specifically, the constructed function aims to transform an image, pixel by pixel, and then computing the mean and the standard deviation of the transformed image. The performance of this method is measured against a set of expert-defined features. Experiments have been carried out on a database of whole-sky cloud images. Results show that the proposed method is able to achieve a similar accuracy as the 4 most important features from the expert feature-set.

Authors and affiliations

J. Huertas(1), J. Rodríguez-Benítez(2), D. Pozo(2), R. Aler(1), Inés M. Galván(1)
1. Computer Science Department EVANNAI, University of Carlos III Leganés (Spain)
2. Physics Department MATRAS, University of Jaén

Key word

Genetic Programming, Feature Extraction, Cloud classification, Whole-sky images

References

[1] Heinemann, D., Lorenz, E., & Girodo, M. (2006). Forecasting of solar radiation. Solar energy resource management for electricity generation from local level to global scale. Nova Science Publishers, New York.
[2] Pankiewicz, G. S. (1995). Pattern recognition techniques for the identification of cloud and cloud systems. Meteorological Applications, 2(3), 257-271.
[3] Pfister, G., McKenzie, R. L., Liley, J. B., Thomas, A., Forgan, B. W., & Long, C. N. (2003). Cloud coverage based on all-sky imaging and its impact on surface solar irradiance. Journal of Applied Meteorology, 42(10), 1421-1434.
[4] Calbo J., and J. Sabburg, 2008. Feature extraction from whole-sky ground-bases images for cloud-type recognition,” J. Atmos. Ocean. Technol., 25(1): 3–14, 2008.
[5] Heinle, A., A. Macke, A. Srivastav. 2010. Automatic cloud classification of whole sky images Atmos. Meas. Tech., 3 (2010), pp. 557–567
[6] Kazantzidis, A., Tzoumanikas, P., Bais, A. F., Fotopoulos, S., & Economou, G. (2012). Cloud detection and classification with the use of whole-sky ground-based images. Atmospheric Research, 113, 80-88.
[7] Taravat, A., Fabio Del Frate, Cristina Cornaro, and Stefania Vergari. 2015. Neural Networks and Support Vector Machine Algorithms for Automatic Cloud Classification of Whole-Sky Ground-Based Images. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, VOL. 12( 3), MARCH 2015.
[8] Koza, J. R. (1992). Genetic programming: on the programming of computers by means of natural selection (Vol. 1). MIT press.
[9] Tackett, W. A. (1993, June). Genetic Programming for Feature Discovery and Image Discrimination. In ICGA (pp. 303-311).
[10] Krawiec, K. (2002). Genetic programming-based construction of features for machine learning and knowledge discovery tasks. Genetic Programming and Evolvable Machines, 3(4), 329-343.
[11] Guo, H., Jack, L. B., & Nandi, A. K. (2005). Feature generation using genetic programming with application to fault classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 35(1), 89-99.
[12] Back, T. (1996). Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms. Oxford university press.
[13] Marquez, R., & Coimbra, C. F. (2013). Intra-hour DNI forecasting based on cloud tracking image analysis. Solar Energy, 91, 327-336.
[14] Kenji Kira and Larry A Rendell. The feature selection problem: Traditional methods and a new algorithm. In AAAI, pages 129-134, 1992.
[15] Igor Kononenko, Edvard _Simec, and Marko Robnik-_Sikonja. Overcoming the myopia of inductive learning algorithms with relieff. Applied Intelligence, 7(1):39-55, 1997.