Abstract
The pattern recognition literature is replete with the use of principal component analysis in the interpretation and analysis of data. However, in the specific case of classification, especially of biomedical patterns, this pre-processing method, which transforms possibly correlated features into a new set of uncorrelated variables, must be used with caution since a principal component, which may account for significant variance in the data, is not necessarily discriminatory. To compensate for this deficiency, we present a novel classification method using an adaptive network of fuzzy logic connectives to select the most discriminatory principal components. We empirically demonstrate the effectiveness of this method using a benchmark combination of a conventional classifier and principal component analysis.