A GA-Based Feature Selection Algorithm for Remote Sensing Images
We present a GA–based feature selection algorithm in which feature subsets are evaluated by means of a separability index. This index is based on a filter method, which allows to estimate statistical properties of the data, independently of the classifier used. More specifically, the defined index uses covariance matrices for evaluating how spread out the probability distributions of data are in a given n −dimensional space. The effectiveness of the approach has been tested on two satellite images and the results have been compared with those obtained without feature selection and with those obtained by using a previously developed GA–based feature selection algorithm.
KeywordsFeature Vector Feature Selection Spectral Band Feature Subset Multi Layer Perceptron
Unable to display preview. Download preview PDF.
- 1.Martin-Bautista, M., Vila, M.A.: A survey of genetic feature selection in mining issues. In: Proc. 1999 Congress on Evolutionary Computation (CEC 1999), pp. 1314–1321 (1999)Google Scholar
- 2.Puuronen, S., Tsymbal, A., Skrypnik, I.: Advanced local feature selection in medical diagnostics. In: Proc. 13th IEEE Symp. Computer-Based Medical Systems, pp. 25–30 (2000)Google Scholar
- 3.Hung, C., Fahsi, A., Tadesse, W., Coleman, T.: A comparative study of remotely sensed data classification using principal components analysis and divergence. In: Proc. IEEE Intl. Conf. Systems, Man, and Cybernetics, pp. 2444–2449 (1997)Google Scholar
- 11.De Stefano, C., Fontanella, F., Marrocco, C., Schirinzi, G.: A feature selection algorithm for class discrimination improvement. In: IEEE International Geoscience and Remote Sensing Symposium (2007)Google Scholar