Evaluation of calibration data in capillary electrophoresis
using artificial neural networks to increase precision of
analysis

J 2002

Evaluation of calibration data in capillary electrophoresis using artificial neural networks to increase precision of analysis

POLÁŠKOVÁ, Pavla, Gaston Guillermo BOCAZ BENEVENTI, Hua LI a Josef HAVEL

Základní údaje

Originální název

Evaluation of calibration data in capillary electrophoresis using artificial neural networks to increase precision of analysis

Autoři

POLÁŠKOVÁ, Pavla (203 Česká republika), Gaston Guillermo BOCAZ BENEVENTI (152 Chile), Hua LI (156 Čína) a Josef HAVEL (203 Česká republika, garant)

Vydání

JOURNAL OF CHROMATOGRAPHY A, AMSTERDAM, ELSEVIER SCIENCE BV, 2002, 0021-9673

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10406 Analytical chemistry

Stát vydavatele

Nizozemské království

Utajení

není předmětem státního či obchodního tajemství

Impakt faktor

Impact factor: 3.098

Kód RIV

RIV/00216224:14310/02:00007964

Organizační jednotka

Přírodovědecká fakulta

UT WoS

000179406700007

Klíčová slova anglicky

calibration data; capillary electrophoresis; artificial neural networks

Štítky

artificial neural networks, calibration data, Capillary electrophoresis

Změněno: 10. 3. 2003 13:45, prof. RNDr. Josef Havel, DrSc.

Anotace

V originále

Increase of precision in capillary electrophoresis can be achieved applying suitable markers and evaluating calibration curves and data analysis with artificial neural networks. They are able to account for errors in both x- and y-axes, nonlinear response of detector and non-linearity of calibration curves eventually. A comparison of the artificial neural networks approach with ordinary least-squares (OLS) and bivariate least-squares regression (BLS) was done. While OLS and BLS give similar results, the method proposed and tested in analysis of several pharmaceutical products yields lower prediction errors than traditional linear least-squares methods and the precision of analysis was found in the range 0.5-1.5% relative. (C) 2002 Elsevier Science B.V. All rights reserved.

Návaznosti

GA203/02/1103, projekt VaV

Název: Umělé neuronové sítě a plánování pokusů v analytické chemii, zejména v separačních metodách

Investor: Grantová agentura ČR, Umělé neuronové sítě a plánování pokusů v analytické chemii, zejména v separačních metodách

Citovat

POLÁŠKOVÁ, Pavla, Gaston Guillermo BOCAZ BENEVENTI, Hua LI a Josef HAVEL. Evaluation of calibration data in capillary electrophoresis using artificial neural networks to increase precision of analysis. JOURNAL OF CHROMATOGRAPHY A. AMSTERDAM: ELSEVIER SCIENCE BV, 2002, roč. 979, 1-2, s. 59-67, 8Increase. ISSN 0021-9673.

@article{485220,
   author = {Polášková, Pavla and Bocaz Beneventi, Gaston Guillermo and Li, Hua and Havel, Josef},
   article_location = {AMSTERDAM},
   article_number = {1-2},
   keywords = {calibration data; capillary electrophoresis; artificial neural networks},
   language = {eng},
   issn = {0021-9673},
   journal = {JOURNAL OF CHROMATOGRAPHY A},
   title = {Evaluation of calibration data in capillary electrophoresis using artificial neural networks to increase precision of analysis},
   volume = {979},
   year = {2002}
}

TY  - JOUR
ID  - 485220
AU  - Polášková, Pavla - Bocaz Beneventi, Gaston Guillermo - Li, Hua - Havel, Josef
PY  - 2002
TI  - Evaluation of calibration data in capillary electrophoresis using artificial neural networks to increase precision of analysis
JF  - JOURNAL OF CHROMATOGRAPHY A
VL  - 979
IS  - 1-2
SP  - 59-67
EP  - 59-67
PB  - ELSEVIER SCIENCE BV
SN  - 00219673
KW  - calibration data
KW  - capillary electrophoresis
KW  - artificial neural networks
N2  - Increase of precision in capillary electrophoresis can be achieved applying suitable markers and evaluating calibration curves and data analysis with artificial neural networks. They are able to account for errors in both x- and y-axes, nonlinear response of detector and non-linearity of calibration curves eventually. A comparison of the artificial neural networks approach with ordinary least-squares (OLS) and bivariate least-squares regression (BLS) was done. While OLS and BLS give similar results, the method proposed and tested in analysis of several pharmaceutical products yields lower prediction errors than traditional linear least-squares methods and the precision of analysis was found in the range 0.5-1.5% relative. (C) 2002 Elsevier Science B.V. All rights reserved.
ER  -

POLÁŠKOVÁ, Pavla, Gaston Guillermo BOCAZ BENEVENTI, Hua LI a Josef HAVEL. Evaluation of calibration data in capillary electrophoresis using artificial neural networks to increase precision of analysis. \textit{JOURNAL OF CHROMATOGRAPHY A}. AMSTERDAM: ELSEVIER SCIENCE BV, 2002, roč.~979, 1-2, s.~59-67, 8Increase. ISSN~0021-9673.

Podrobný výpis o publikaci