Genetic feature selection combined with fuzzy kNN for hyperspectral satellite imagery

Abstract

For high-dimensional data, the appropriate selection of features has a significant effect on the cost and accuracy of an automated classifier. In this paper, a feature selection technique using genetic algorithms is applied, for classification the fuzzy approach is suggested. And the hard and fuzzy kNN classifications are compared. Experiments are conducted on AVIRIS data, and the results are evaluated in the paper.