Naslov
Selection of optimal training methodology for development of artificial neural network retention model in ion chromatography

Autori
Cerjan Stefanović, Štefica ; Bolanča, Tomislav ; Ukić, Šime ; Rogošić, Marko ; Bašković, Marin

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
14th International Symposium on Separation Science, New Achievements in Chromatography, Book of Abstracts / Šegudović, Nikola - Zagreb : Hrvatsko društvo kemijskih inženjera i tehnologa (HDKI), 2008, 169-169

ISBN
978-953-6894-36-9

Skup
14th International Symposium on Separation Science, New Achievements in Chromatography

Mjesto i datum
Primošten, Hrvatska, 30.09.2008. - 03.10.2008

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
ion chromatography; optimal training methodology; artificial neural network; retention model

Sažetak
The chromatographic property, which has the major impact on the separation quality, is retention. If there is a business expectation to find reasonable separation conditions within a couple of days, then there are only a dozen or so experiments possible before time runs out. Therefore, it is still important to try to apply different methodologies in order to increase predictive ability of retention in overall optimization process. Different training algorithms, activation function, number of hidden layer neurons and number of experimental data points used for training set were optimized until minimum on error surface has been found.

Izvorni jezik
Engleski

Znanstvena područja
Kemija, Kemijsko inženjerstvo

POVEZANOST RADA