For high-dimensional data, the appropriate selection of features has a sign
ificant effect on the cost and accuracy of an automated classifier. In this
paper, a feature selection technique using genetic algorithms is applied.
For classification, crisp and fuzzy k-nearest neighbor (kNN) classifiers ar
e compared. Composite fuzzy classifier architectures are investigated. Expe
riments are conducted on airborne visible/infrared imaging spectrometer (AV
IRIS) data, and the results are evaluated in the paper. (C) 2002 Elsevier S
cience B.V, All rights reserved.