Evaluation of Equilibria with Use of Artificial Neural Networks
(ANN). II. ANN and Experimental Design as a Tool in
Electrochemical Data Evaluation for Fully Dynamic (Labile)
Metal Complexes

J 2001

Evaluation of Equilibria with Use of Artificial Neural Networks (ANN). II. ANN and Experimental Design as a Tool in Electrochemical Data Evaluation for Fully Dynamic (Labile) Metal Complexes

CUKROWSKI, Ignacy, Marta FARKOVÁ a Josef HAVEL

Základní údaje

Originální název

Evaluation of Equilibria with Use of Artificial Neural Networks (ANN). II. ANN and Experimental Design as a Tool in Electrochemical Data Evaluation for Fully Dynamic (Labile) Metal Complexes

Autoři

CUKROWSKI, Ignacy, Marta FARKOVÁ a Josef HAVEL

Vydání

Electroanalysis, Weinheim, WILEY-VCH Verlag GmbH, 2001, 1040-0397

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10405 Electrochemistry

Stát vydavatele

Německo

Utajení

není předmětem státního či obchodního tajemství

Impakt faktor

Impact factor: 1.702

Kód RIV

RIV/00216224:14310/01:00004475

Organizační jednotka

Přírodovědecká fakulta

UT WoS

000168001400005

Klíčová slova anglicky

Artificial neural networks / Experimental design / Stability constants / Polarography / Metal complexes / Ion selective electrodes / Metal-ligand equilibria

Změněno: 24. 10. 2001 12:02, RNDr. Marta Farková, CSc.

Anotace

V originále

A use of artificial neural networks (ANN) and various experimental designs (ED) for refinement of experimental data obtained in a polarographic metal-ligand equilibrium study of fully dynamic (labile) metal complexes was thoroughly examined. ANN were tested on evenly and randomly distributed experimental error-free and error-corrupted data. It was found that randomly distributed experimental data did not influence the prediction power of ANN. Numerous tests demonstrated that ANN with appropriate ED can provide accurate prediction in the stability constants with the absolute errors in the range of +- 0.05 log unit or smaller. ANNs were found exceptionally robust. Random experimental errors have not influence estimates in stability constants much even when errors in pH up to the value of +- 0.1 pH unit were introduced. A special procedure has been worked out that allows to minimise the influence of error-corrupted data even further; no significant difference was observed between results obtained on error-free and error-corrupted data. This procedure makes also possible to obtain a standard deviation in the calculated stability constants that is usually a difficult task when ANNs are used. The results obtained from ANN were compared with those obtained from a hard model based non-linear regression techniques. No significant difference in evaluated data from these two, soft and hard model based approaches, was found. The use of ANN described here for polarographic data is of general nature and, in principal, can be adopted to other analytical techniques commonly used in metal-ligand equilibrium 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

CUKROWSKI, Ignacy, Marta FARKOVÁ a Josef HAVEL. Evaluation of Equilibria with Use of Artificial Neural Networks (ANN). II. ANN and Experimental Design as a Tool in Electrochemical Data Evaluation for Fully Dynamic (Labile) Metal Complexes. Electroanalysis. Weinheim: WILEY-VCH Verlag GmbH, 2001, roč. 13, č. 4, s. 295-308. ISSN 1040-0397.

@article{370811,
   author = {Cukrowski, Ignacy and Farková, Marta and Havel, Josef},
   article_location = {Weinheim},
   article_number = {4},
   keywords = {Artificial neural networks / Experimental design / Stability constants / Polarography / Metal complexes / Ion selective electrodes / Metal-ligand equilibria},
   language = {eng},
   issn = {1040-0397},
   journal = {Electroanalysis},
   title = {Evaluation of Equilibria with Use of Artificial Neural Networks (ANN). II. ANN and Experimental Design as a Tool in Electrochemical Data Evaluation for Fully Dynamic (Labile) Metal Complexes},
   volume = {13},
   year = {2001}
}

TY  - JOUR
ID  - 370811
AU  - Cukrowski, Ignacy - Farková, Marta - Havel, Josef
PY  - 2001
TI  - Evaluation of Equilibria with Use of Artificial Neural Networks (ANN). II. ANN and Experimental Design as a Tool in Electrochemical Data Evaluation for Fully Dynamic (Labile) Metal Complexes
JF  - Electroanalysis
VL  - 13
IS  - 4
SP  - 295
EP  - 295
PB  - WILEY-VCH Verlag GmbH
SN  - 10400397
KW  - Artificial neural networks / Experimental design / Stability constants / Polarography / Metal complexes / Ion selective electrodes / Metal-ligand equilibria
N2  - A use of artificial neural networks (ANN) and various experimental designs (ED) for refinement of experimental data obtained in a polarographic metal-ligand equilibrium study of fully dynamic (labile) metal complexes was thoroughly examined. ANN were tested on evenly and randomly distributed experimental error-free and error-corrupted data. It was found that randomly distributed experimental data did not influence the prediction power of ANN. Numerous tests demonstrated that ANN with appropriate ED can provide accurate prediction in the stability constants with the absolute errors in the range of +- 0.05 log unit or smaller. ANNs were found exceptionally robust. Random experimental errors have not influence estimates in stability constants much even when errors in pH up to the value of +- 0.1 pH unit were introduced. A special procedure has been worked out that allows to minimise the influence of error-corrupted data even further; no significant difference was observed between results obtained on error-free and error-corrupted data. This procedure makes also possible to obtain a standard deviation in the calculated stability constants that is usually a difficult task when ANNs are used. The results obtained from ANN were compared with those obtained from a hard model based non-linear regression techniques. No significant difference in evaluated data from these two, soft and hard model based approaches, was found. The use of ANN described here for polarographic data is of general nature and, in principal, can be adopted to other analytical techniques commonly used in metal-ligand equilibrium studies.
ER  -

CUKROWSKI, Ignacy, Marta FARKOVÁ a Josef HAVEL. Evaluation of Equilibria with Use of Artificial Neural Networks (ANN). II. ANN and Experimental Design as a Tool in Electrochemical Data Evaluation for Fully Dynamic (Labile) Metal Complexes. \textit{Electroanalysis}. Weinheim: WILEY-VCH Verlag GmbH, 2001, roč.~13, č.~4, s.~295-308. ISSN~1040-0397.

Podrobný výpis o publikaci