Evaluation of Chemical Equilibrium Data with the Use of
Artificial Neural Networks

J 2002

Evaluation of Chemical Equilibrium Data with the Use of Artificial Neural Networks

HAVEL, Josef, Přemysl LUBAL a Marta FARKOVÁ

Základní údaje

Originální název

Evaluation of Chemical Equilibrium Data with the Use of Artificial Neural Networks

Autoři

HAVEL, Josef (203 Česká republika, garant), Přemysl LUBAL (203 Česká republika) a Marta FARKOVÁ (203 Česká republika)

Vydání

Polyhedron, Velká Británie, Elsevier Science Ltd. 2002, 0277-5387

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10406 Analytical chemistry

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Impakt faktor

Impact factor: 1.414

Kód RIV

RIV/00216224:14310/02:00007256

Organizační jednotka

Přírodovědecká fakulta

Klíčová slova anglicky

artificial neural networks; experimental design; stability constants; metal complexes; ion selective electrodes; metal-ligand equilibria

Štítky

artificial neural networks, experimental design, ion selective electrodes, metal complexes, metal-ligand equilibria, Stability Constants

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 25. 2. 2013 12:31, RNDr. Marta Farková, CSc.

Anotace

V originále

Multivariate calibration with experimental design (ED) and artificial neural networks (ANN) modeling can be used to estimate equilibria constants from any kind of protonation or metal-ligand equilibrium data like potentiometry, polarography, spectrophotometry, extraction, etc. The method was tested on evenly or randomly distributed experimental error-free data and data with random noise and the results show that even rather higher experimental errors do not influence significantly the prediction power and correctness of ANN prediction. ANN with appropriate ED can provide accurate prediction of stability constants with the relative errors in the range of 4% or smaller while the approach is very robust. Comparison with a hard model evaluation based on non-linear regression techniques shows excellent agreement. Proposed ANN method is of a general nature and, in principal, can be adopted to any analytical technique used in equilibria studies.

Návaznosti

MSM 143100011, záměr

Název: Struktura a vazebné poměry, vlastnosti a analýza syntetických a přírodních molekulových ansamblů

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Struktura a vazebné poměry, vlastnosti a analýza syntetických a přírodních molekulových ansamblů

Citovat

HAVEL, Josef, Přemysl LUBAL a Marta FARKOVÁ. Evaluation of Chemical Equilibrium Data with the Use of Artificial Neural Networks. Polyhedron. Velká Británie: Elsevier Science Ltd., 2002, roč. 21, 14-15, s. 1375-1384. ISSN 0277-5387.

@article{483374,
   author = {Havel, Josef and Lubal, Přemysl and Farková, Marta},
   article_location = {Velká Británie},
   article_number = {14-15},
   keywords = {artificial neural networks; experimental design; stability constants; metal complexes; ion selective electrodes; metal-ligand equilibria},
   language = {eng},
   issn = {0277-5387},
   journal = {Polyhedron},
   title = {Evaluation of Chemical Equilibrium Data with the Use of Artificial Neural Networks},
   volume = {21},
   year = {2002}
}

TY  - JOUR
ID  - 483374
AU  - Havel, Josef - Lubal, Přemysl - Farková, Marta
PY  - 2002
TI  - Evaluation of Chemical Equilibrium Data with the Use of Artificial Neural Networks
JF  - Polyhedron
VL  - 21
IS  - 14-15
SP  - 1375
EP  - 1375
PB  - Elsevier Science Ltd.
SN  - 02775387
KW  - artificial neural networks
KW  - experimental design
KW  - stability constants
KW  - metal complexes
KW  - ion selective electrodes
KW  - metal-ligand equilibria
N2  - Multivariate calibration with experimental design (ED) and artificial neural networks (ANN) modeling can be used to estimate equilibria constants from any kind of protonation or metal-ligand equilibrium data like potentiometry, polarography, spectrophotometry, extraction, etc. The method was tested on evenly or randomly distributed experimental error-free data and data with random noise and the results show that even rather higher experimental errors do not influence significantly the prediction power and correctness of ANN prediction. ANN with appropriate ED can provide accurate prediction of stability constants with the relative errors in the range of 4% or smaller while the approach is very robust. Comparison with a hard model evaluation based on non-linear regression techniques shows excellent agreement. Proposed ANN method is of a general nature and, in principal, can be adopted to any analytical technique used in equilibria studies.
ER  -

HAVEL, Josef, Přemysl LUBAL a Marta FARKOVÁ. Evaluation of Chemical Equilibrium Data with the Use of Artificial Neural Networks. \textit{Polyhedron}. Velká Británie: Elsevier Science Ltd., 2002, roč.~21, 14-15, s.~1375-1384. ISSN~0277-5387.

Podrobný výpis o publikaci