Radial basis functions applied to the classification of UV-visible spectra

This paper describes how to apply a neural network based in radial basis fu nctions (RBFs) to classify multivariate data. The classification strategy w as automatically implemented in a sequential injection analytical system. R BF neural network had some advantages over counterpropagation neural networ ks (CPNNs) when they are used in the same application: the classification e rror was reduced from 20% to 13%, the input variables (UV-visible spectra) did not have to be preprocessed and the training procedure was simpler. (C) 1999 Elsevier Science B.V. All rights reserved.