Use of artificial neural networks in capillary zone electrophoresis

The use of artificial neural networks (ANNs) for nonlinear modeling of symm etric and nonsymmetric peaks in capillary zone electrophoresis (CZE) and in optimization of CZE methods was studied. It was shown that ANNs can be use d to estimate peak parameters and in combination with experimental design c an be applied for efficient prediction of optimal separation conditions. Th e great advantage is that no use of the explicit model of the separation pr ocess and no knowledge of the physicochemical constants are needed. (C) 199 9 Elsevier Science B.V. All rights reserved.