Application of artificial neural networks in multifactor optimization of selectivity in capillary electrophoresis

Citation
Qf. Li et al., Application of artificial neural networks in multifactor optimization of selectivity in capillary electrophoresis, ANAL LETTER, 33(11), 2000, pp. 2333-2347
Citations number
21
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Chemistry & Analysis","Spectroscopy /Instrumentation/Analytical Sciences
Journal title
ANALYTICAL LETTERS
ISSN journal
0003-2719 → ACNP
Volume
33
Issue
11
Year of publication
2000
Pages
2333 - 2347
Database
ISI
SICI code
0003-2719(2000)33:11<2333:AOANNI>2.0.ZU;2-B
Abstract
A methodology based on the coupling of experimental design and artificial n eural networks (ANNs) was proposed in the optimization of selectivity in ca pillary electrophoresis. The effect of the buffer composition, concentratio n, SDS concentration, ethanol percentage and the applied voltage on the sep aration of six choice solutes was examined by using orthogonal design. Feed forward-type neural networks with faster back propagation (BP) algorithm we re applied to model the separation process, and then optimization of the ex perimental conditions was carried out in the modeled neural network with 5- 7-1 structure, which had been confirmed to be able to provide the maximum p erformance. It was demonstrated that by combining ANN modeling with experim ental design, the number of experiments necessary to search and find optima l separation conditions can be reduced significantly. Because of its genera l validity, the new proposed approach can also be applied in other separati on conditions.