Artificial neural networks in analysis of indinavir and its degradation products retention
Само за регистроване кориснике
2009
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Artificial neural networks (ANN) are biologically inspired computer programs designed to simulate the way in which the human brain processes the information. In the past few years, coupling of experimental design (ED) and ANN became useful tool in the method optimization. This paper presents the application of ED-ANN in analysis of chromatographic behavior of indinavir and its degradation products. According to preliminary study, full factorial design 2(4) was chosen to set input variables for network training. Experimental data (inputs) and results for retention factors from experiments (outputs) were used to train the ANN with aim to define correlation among variables. For networks training multi-layer perceptron (MLP) with back propagation (BP) algorithm was used. Network with the lowest root mean square (RMS) had 4-8-3 topology. Predicted data were in good agreement with experimental data (correlation was higher than 0.9713 for training set). Regression statistics confirmed good ab...ility of trained network to predict compounds retention.
Кључне речи:
Experimental design / Artificial neural networks / Liquid chromatography / Indinavir / Degradation productsИзвор:
Talanta, 2009, 78, 1, 107-112Издавач:
- Elsevier Science BV, Amsterdam
Финансирање / пројекти:
- Формулисање и Карактеризација сепарационих система за моделовање ретенционог понашања лековитих супстанција уз хемометријску евалуацију (RS-MESTD-MPN2006-2010-142077)
DOI: 10.1016/j.talanta.2008.10.066
ISSN: 0039-9140
PubMed: 19174211
WoS: 000263634700016
Scopus: 2-s2.0-58649105768
Институција/група
PharmacyTY - JOUR AU - Jančić-Stojanović, Biljana AU - Ivanović, D. AU - Malenović, Anđelija AU - Medenica, Mirjana PY - 2009 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/1247 AB - Artificial neural networks (ANN) are biologically inspired computer programs designed to simulate the way in which the human brain processes the information. In the past few years, coupling of experimental design (ED) and ANN became useful tool in the method optimization. This paper presents the application of ED-ANN in analysis of chromatographic behavior of indinavir and its degradation products. According to preliminary study, full factorial design 2(4) was chosen to set input variables for network training. Experimental data (inputs) and results for retention factors from experiments (outputs) were used to train the ANN with aim to define correlation among variables. For networks training multi-layer perceptron (MLP) with back propagation (BP) algorithm was used. Network with the lowest root mean square (RMS) had 4-8-3 topology. Predicted data were in good agreement with experimental data (correlation was higher than 0.9713 for training set). Regression statistics confirmed good ability of trained network to predict compounds retention. PB - Elsevier Science BV, Amsterdam T2 - Talanta T1 - Artificial neural networks in analysis of indinavir and its degradation products retention VL - 78 IS - 1 SP - 107 EP - 112 DO - 10.1016/j.talanta.2008.10.066 ER -
@article{ author = "Jančić-Stojanović, Biljana and Ivanović, D. and Malenović, Anđelija and Medenica, Mirjana", year = "2009", abstract = "Artificial neural networks (ANN) are biologically inspired computer programs designed to simulate the way in which the human brain processes the information. In the past few years, coupling of experimental design (ED) and ANN became useful tool in the method optimization. This paper presents the application of ED-ANN in analysis of chromatographic behavior of indinavir and its degradation products. According to preliminary study, full factorial design 2(4) was chosen to set input variables for network training. Experimental data (inputs) and results for retention factors from experiments (outputs) were used to train the ANN with aim to define correlation among variables. For networks training multi-layer perceptron (MLP) with back propagation (BP) algorithm was used. Network with the lowest root mean square (RMS) had 4-8-3 topology. Predicted data were in good agreement with experimental data (correlation was higher than 0.9713 for training set). Regression statistics confirmed good ability of trained network to predict compounds retention.", publisher = "Elsevier Science BV, Amsterdam", journal = "Talanta", title = "Artificial neural networks in analysis of indinavir and its degradation products retention", volume = "78", number = "1", pages = "107-112", doi = "10.1016/j.talanta.2008.10.066" }
Jančić-Stojanović, B., Ivanović, D., Malenović, A.,& Medenica, M.. (2009). Artificial neural networks in analysis of indinavir and its degradation products retention. in Talanta Elsevier Science BV, Amsterdam., 78(1), 107-112. https://doi.org/10.1016/j.talanta.2008.10.066
Jančić-Stojanović B, Ivanović D, Malenović A, Medenica M. Artificial neural networks in analysis of indinavir and its degradation products retention. in Talanta. 2009;78(1):107-112. doi:10.1016/j.talanta.2008.10.066 .
Jančić-Stojanović, Biljana, Ivanović, D., Malenović, Anđelija, Medenica, Mirjana, "Artificial neural networks in analysis of indinavir and its degradation products retention" in Talanta, 78, no. 1 (2009):107-112, https://doi.org/10.1016/j.talanta.2008.10.066 . .