Neural networks in high-performance liquid chromatography optimization: Response surface modeling
| Autor: | P.M J Coenegracht, H.J Metting |
|---|---|
| Přispěvatelé: | Faculty of Science and Engineering |
| Jazyk: | angličtina |
| Rok vydání: | 1996 |
| Předmět: |
Chromatography
LOOM Artificial neural network Chemistry PHASE Organic Chemistry RECOGNITION Regression analysis General Medicine Overfitting Response surface modeling response surface modelling neural networks Biochemistry High-performance liquid chromatography Analytical Chemistry Lateral inhibition Linear regression Neural Networks Computer ALGORITHM computer optimization Chromatography High Pressure Liquid Mathematics computer.programming_language |
| Zdroj: | Journal of Chromatography, 728(1-2), 47-53. ELSEVIER SCIENCE BV |
| ISSN: | 0021-9673 |
| Popis: | The usefulness of artificial neural networks for response surface modeling in HPLC optimization is compared with (non-)linear regression methods. The number of hidden nodes is optimized by a lateral inhibition method. Overfitting is controlled by cross-validation using the leave one out method (LOOM). Data sets of linear and non-linear response surfaces (capacity factors) were taken from literature. The results show that neural networks offer promising possibilities in HPLC method development. The predictive results were better or comparable to those obtained with linear and non-linear regression models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect