Combining classification and regression approaches for the quantification of highly overlapping capillary electrophoresis peaks by using evolutionary sigmoidal and product unit neural networks

Abstract

This is a study of the potential of neural networks built by using different transfer functions (sigmoidal, product and sigmoidal-product units) designed by an evolutionary algorithm to quantify highly overlapping electrophoretic peaks. To test this approach, two aminoglycoside antibiotics, amikacin and paramomycin, were quantified from samples containing either only one component or mixtures of them though capillary zone electrophoresis (CZE) with laser-induced fluorescence (LIF) detection. The three models assayed used as input data the four-parameter Weibull curve associated with the profile of the electrophoretic peak and in some cases the class label for each sample estimated by cluster analysis. The combination of classification and regression approaches allowed the establishment of straightforward network topologies enabling the analytes to be quantified with great accuracy and precision. The best models for mixture samples were provided by product unit neural networks (PUNNs), 4:4:1 (14 weights) for both analytes, after discrimination by cluster analysis, allowing the analytes to be quantified with great accuracy: 8.2% for amikacin and 5.6% for paromomycin within the standard error of prediction for the generalization test, SEP G . For comparison, partial least square regression was also used for the resolution of these mixtures; it provided a minor accuracy: SEP G 11.8 and 15.7% for amikacin and paramomycin, respectively. The reduced dimensions of the neural networks models selected enabled the derivation of simple quantification equations to transform the input variables into the output variable. These equations can be more easily interpreted from a chemical point of view than those provided by other ANN models.

Validation of artificial neural networks to model the acoustic behaviour of induction motors

“…Further details of this algorithm could be found in [28]. The parameters of the evolutionary algorithm are shown in Table 6, whereas, the remaining values were obtained from [29].…”

Using machine learning methods to determine a typology of patients with HIV-HCV infection to be treated with antivirals

“…Finally, the minimum number of hidden nodes, the maximum number of hidden nodes in the initialisation phase and the maximum number of hidden nodes in the whole evolutionary process were set at 1, 2, and 4, respectively. All these values were selected following a 5-fold cross-validation on the training set, and the remaining values were obtained from Hervás-Martínez et al [42].…”

Recent advances in the analysis of antibiotics by CE and CEC

“…This study showed the potential of different artificial neural networks for the quantitation of overlapped peaks to predict the contribution of each component to the overall analytical signal. This allows an important reduction in analysis time since it avoids time consumption by finding optimal conditions for the suitable CZE resolution 54.…”