Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Artificial neural networks for quantification in unresolved capillary electrophoresis peaks
Autore:
Latorre, RM; Hernandez-Cassou, S; Saurina, J;
Indirizzi:
Univ Barcelona, Dept Analyt Chem, E-08028 Barcelona, Spain Univ BarcelonaBarcelona Spain E-08028 yt Chem, E-08028 Barcelona, Spain
Titolo Testata:
JOURNAL OF SEPARATION SCIENCE
fascicolo: 6, volume: 24, anno: 2001,
pagine: 427 - 434
SICI:
1615-9314(200107)24:6<427:ANNFQI>2.0.ZU;2-3
Fonte:
ISI
Lingua:
ENG
Soggetto:
PERFORMANCE LIQUID-CHROMATOGRAPHY; PARTIAL LEAST-SQUARES; DIODE-ARRAY DETECTION; EXPERIMENTAL-DESIGN; OVERLAPPED PEAKS; RESOLUTION; OPTIMIZATION; REGRESSION; PHASE; HPLC;
Keywords:
capillary electrophoresis; overlapping peaks; amino acid derivatives; artificial neural networks; partial least squares regression;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Physical, Chemical & Earth Sciences
Citazioni:
26
Recensione:
Indirizzi per estratti:
Indirizzo: Saurina, J Univ Barcelona, Dept Analyt Chem, Diagonal 647, E-08028 Barcelona, Spain Univ Barcelona Diagonal 647 Barcelona Spain E-08028 ona, Spain
Citazione:
R.M. Latorre et al., "Artificial neural networks for quantification in unresolved capillary electrophoresis peaks", J SEP SCI, 24(6), 2001, pp. 427-434

Abstract

Artificial neural networks (ANN) have been applied to the resolution of overlapping capillary electrophoresis peaks of amino acid derivatives labelled with 1,2-naphthoquinone-4-sulfonate (NOS). The separation was performed with a fused-silica capillary and the corresponding 3D-electropherograms were recorded in a range from 225 to 550 nm with a diode array detector (DAD). Since complete resolution of all the analytes was not accomplished, a chemometric approach was used to improve the quantification mathematically. In the present case, a three-layer back propagation (BP) ANN with a sigmoid transfer function was built in order to perform the amino acid determination. The inputs of the ANN were the spectra or the electropherograms of each sample and the outputs were the concentrations of the amino acid derivatives in the overlapping peaks to be predicted. The results were compared with those from partial least squares regression (PLS) and, in general, ANN provided better predictions than PLS.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 29/03/20 alle ore 03:01:03