Summary
A two layer perceptron with backpropagation of error is used for quantitative analysis in ICP-AES. The network was trained by emission spectra of two interfering lines of Cd and As and the concentrations of both elements were subsequently estimated from mixture spectra. The spectra of the Cd and As lines were also used to perform multiple linear regression (MLR) via the calculation of the pseudoinverse S+ of the sensitivity matrix S. In the present paper it is shown that there exist close relations between the operation of the perceptron and the MLR procedure. These are most clearly apparent in the correlation between the weights of the backpropagation network and the elements of the pseudoinverse. Using MLR, the confidence intervals over the predictions are exploited to correct for the optical device of the wavelength shift.
Similar content being viewed by others
References
Munk ME, Madison MS, Robb EW (1991) Microchim Acta II:505
Schierle C, Otto M, Wegscheider W (1992) Fresenius J Anal Chem 343:561
Borggaard C, Thodberg HH (1992) Anal Chem 64:545
Long JR, Gregoriou VG, Gemperline PJ (1990) Anal Chem 62: 1791
Bos A, Bos M, van der Linden WE (1992) Anal Chim Acta 256: 133
Bos M, Weber HT (1991) Anal Chim Acta 247:97
Zupan J, Gasteiger J (1991) Anal Chim Acta 248:1
Massart DL (1988) Chemometrics: a textbook. Elsevier, Amsterdam
Martens H, Naes T (1989) Multivariate calibration. Wiley, New York
Rumelhart DE, McClelland JL (1987) Parallel distributed processing, Vol 1. MIT Press, Cambridge
Press WM, Flannery BP, Teukolsky SA, Vetterling WT (1990) Numerical recipes in C. Cambridge University Press, New York
van Veen EH, De Loos-Vollebregt MTC (1990) Spectrochim Acta 45B:313
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Schierle, C., Otto, M. Comparison of a neural network with multiple linear regression for quantitative analysis in ICP-atomic emission spectroscopy. Fresenius J Anal Chem 344, 190–194 (1992). https://doi.org/10.1007/BF00322708
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF00322708