prikaz prve stranice dokumenta Use of Artificial Neural Networks for Retention Modelling in ion Chromatography
  Download
PDF 164.02 KB
Scientific paper - Original scientific paper
Use of Artificial Neural Networks for Retention Modelling in ion Chromatography
Croatica Chemica Acta, 75 (2002), 3; 713-725. urn:nbn:hr:239:241939
Srečnik, Goran; Debeljak, Željko; Cerjan-Stefanović, Štefica; Bolanča, Tomislav; Novič, Milko; Lazarić, Katica; Gumhalter-Lulić, Željka

Institutional repository: Repository UHC Osijek

Cite this document

Srečnik, G., Debeljak, Ž., Cerjan Stefanović, Š., Bolanča, T., Novič, M., Lazarić, K. & Gumhalter Lulić, Ž. (2002). Use of Artificial Neural Networks for Retention Modelling in ion Chromatography. Croatica Chemica Acta, 75. (3), 713-725. Retrieved from https://urn.nsk.hr/urn:nbn:hr:239:241939

Srečnik, Goran, et al. "Use of Artificial Neural Networks for Retention Modelling in ion Chromatography." Croatica Chemica Acta, vol. 75, no. 3, 2002, pp. 713-725. https://urn.nsk.hr/urn:nbn:hr:239:241939

Srečnik, Goran, Željko Debeljak, Štefica Cerjan Stefanović, Tomislav Bolanča, Milko Novič, Katica Lazarić and Željka Gumhalter Lulić. "Use of Artificial Neural Networks for Retention Modelling in ion Chromatography." Croatica Chemica Acta 75, no. 3 (2002): 713-725. https://urn.nsk.hr/urn:nbn:hr:239:241939

Srečnik, G., et al. (2002) 'Use of Artificial Neural Networks for Retention Modelling in ion Chromatography', Croatica Chemica Acta, 75(3), pp. 713-725. Available at: https://urn.nsk.hr/urn:nbn:hr:239:241939 (Accessed 09 November 2024)

Srečnik G, Debeljak Ž, Cerjan Stefanović Š, Bolanča T, Novič M, Lazarić K, and sur.. Use of Artificial Neural Networks for Retention Modelling in ion Chromatography. Croatica Chemica Acta [Internet]. 2002 [cited 2024 November 09];75(3):713-725. Available at: https://urn.nsk.hr/urn:nbn:hr:239:241939

G. Srečnik, et al., "Use of Artificial Neural Networks for Retention Modelling in ion Chromatography", Croatica Chemica Acta, vol. 75, no. 3, pp. 713-725, 2002. [Online]. Available at: https://urn.nsk.hr/urn:nbn:hr:239:241939. [Accessed: 09 November 2024]

Metadata
Title (english)Use of Artificial Neural Networks for Retention Modelling in ion Chromatography
Title (croatian)Uporaba umjetnih neuronskih mreža za retencijsko modeliranje u ionskoj kromatografiji
AuthorGoran Srečnik
AuthorŽeljko Debeljak
MBZ: 296571
AuthorŠtefica Cerjan-Stefanović
MBZ: 6631
AuthorTomislav Bolanča
MBZ: 233894
AuthorMilko Novič
AuthorKatica Lazarić
MBZ: 109354
AuthorŽeljka Gumhalter-Lulić
MBZ: 14865
Author's institution(Clinical hospital center Osijek)
Author's institutionUniversity of Zagreb
Faculty of Chemical Engineering and Technology
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Clinical Medical Sciences
Neurology
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Chemistry
Analytic Chemistry
Abstract (english)
The aim of this work was to develop an empirical model for retention of inorganic anions (fluoride, chloride, nitrite, sulphate, bromide, nitrate, and phosphate) in suppressed ion chromatography with hydroxide selective stationary phases using artificial neural networks. Three-layer feed-forward neural network trained with a Levenberg-Marquardt batch error back propagation algorithm has been used to model retention mechanisms of inorganic anions with respect to the mobile phase parameters. The number of hidden layer nodes of the neural network and the number of iteration steps were optimized in order to obtain the best possible retention model. This Study shows that an optimized artificial neural network is a very accurate and fast retention modelling tool to model various inherent linear and non-linear relationships of retention behaviour. This has been proven by developing the neural network retention model with average relative errors of 0.88% obtained using only 300 iteration steps.
Abstract (croatian)
Svrha rada je razvoj empirijskog modela za retencijsko modeliranje anorganskih aniona (fluorida, klorida, nitrita, sulfata, nitrata, bromida i fosfata) u suprimiranoj ionskoj kromatografiji s hidroksid-selektivnom stacionarnom fazom, i to uporabom umjetne neuronske mreže. Unaprijedna neuronska mreža s tri sloja, obučavana Levenberg-Marquardt-ovim algoritmom s povratnim rasprostiranjem pogreške te prilagodbom parametara mreže nakon prolaska čitavog skupa za obuku kroz mrežu, uporabljena je za modeliranje retencijskog mehanizma anorganskih aniona, s obzirom na parametre mobilne faze. Broj neurona u skrivenom sloju neuronske mreže i broj iteracijskih koraka optimiran je da bi se dobio što bolji retencijski model. Pokazano je da optimirana neuronska mreža omogućuje vrlo točan i brz postupak za modeliranje linearnih i nelinearnih ovisnosti te je primjenjiva za modeliranje retencije. To je dokazano razvijanjem modela retencije, uporabom neuronske mreže sa srednjom vrijednošću relativnih pogrešaka od 0,88%, uz korištenje 300 iteracijskih koraka.
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionPublished version
Journal titleCroatica Chemica Acta
Numberingvol. 75, no. 3, pp. 713-725
p-ISSN0011-1643
e-ISSN1334-417X
URN:NBNurn:nbn:hr:239:241939
Publication2002
Document URLhttps://hrcak.srce.hr/128123
Type of resourceText
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2020-05-14 10:15:08