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

POLÁŠKOVÁ, Pavla, Gaston Guillermo BOCAZ BENEVENTI, Hua LI and 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, vol. 979, 1-2, p. 59-67, 8Increase. ISSN 0021-9673.

Basic information

• Original name: Evaluation of calibration data in capillary electrophoresis using artificial neural networks to increase precision of analysis
• Authors: POLÁŠKOVÁ, Pavla (203 Czech Republic), Gaston Guillermo BOCAZ BENEVENTI (152 Chile), Hua LI (156 China) and Josef HAVEL (203 Czech Republic, guarantor).
• Edition: JOURNAL OF CHROMATOGRAPHY A, AMSTERDAM, ELSEVIER SCIENCE BV, 2002, 0021-9673.

Other information

• Original language: English
• Type of outcome: Article in a journal
• Field of Study: 10406 Analytical chemistry
• Country of publisher: Netherlands
• Confidentiality degree: is not subject to a state or trade secret
• Impact factor: Impact factor: 3.098
• RIV identification code: RIV/00216224:14310/02:00007964
• Organization unit: Faculty of Science
• UT WoS: 000179406700007
• Keywords in English: calibration data; capillary electrophoresis; artificial neural networks
• Tags: artificial neural networks, calibration data, Capillary electrophoresis

Abstract

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.

Links

• GA203/02/1103, research and development project: Name: Umělé neuronové sítě a plánování pokusů v analytické chemii, zejména v separačních metodách

Investor: Czech Science Foundation, Artificial neural networks and experimental design in analytical chemistry, especially in separation methods