Feature reduction for classification of multidimensional data

This paper addresses the problem of classifying multidimensional data with relatively few training samples available. Classification is often performed based on data from measurements or ratings of objects or events. These data are called features. It is sometimes difficult to determine if all features are necessary for the classifier, Since the number of training samples needed to design a classifier grows with the dimension of the features, a way to reduce the dimension of the features without losing ally essential information is needed. This paper presents a new method for Feature reduction, and compares it with some methods presented earlier in the literature. This new method is found to have a more stable and predictable performance than the other methods, (C) 2000 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights: reserved.