[article]
| Titre : |
Design and optimization of antiperspirant formulations using the artificial neural networks and genetic algorithms |
| Type de document : |
texte imprimé |
| Auteurs : |
Kader Comlekci, Auteur ; M. Turkoglu, Auteur |
| Année de publication : |
2002 |
| Article en page(s) : |
p. 114-117 |
| Note générale : |
Bibliogr. |
| Langues : |
Anglais (eng) |
| Tags : |
Antiperspirant 'Artificial neural networks' 'Genetic algorithms' 'Mathematical modeling' |
| Index. décimale : |
668.5 Parfums et cosmétiques |
| Résumé : |
In this study, the effects of concentrations of stearyl alcohol (10, 20 and 30%), hydrogenated castor oil (1, 3 and 5%) and talc (1, 3 and 5%) on the properties of antiperspirant sticks were investigated. Thirty-one batches resulted from the experimental design. The artificial neural network methodology (ANN), genetic algorithms (GA) were used for data analysis and optimization. Breaking force and spreadability were measured as the responses. ANN and genetic models provided R2 values between 0.6474 and 0.9984 for the measured responses. When a set of validation experiments was analyzed, GA predictions of antiperspirant characteristics were much better than the ANN predictions. Optimization based on GA showed that using stearyl alcohol at 18 - 22% with talc at 2 - 4% and hudrogenated castor oil at 4 - 5% would produce the antiperspirant stick that leaves the least residue and is easy to apply, but not so easily broken. |
| Permalink : |
https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=10655 |
in IFSCC MAGAZINE > Vol. 5, N° 2 (04-05-06/2002) . - p. 114-117
[article]
|
Aller sur edunet
Accueil
Design and optimization of antiperspirant formulations using the artificial neural networks and genetic algorithms in IFSCC MAGAZINE, Vol. 5, N° 2 (04-05-06/2002)
