Y. Li et al., Simultaneous determination of multicomponents in air toxic organic compounds using Artificial Neural Networks in FTIR spectroscopy, SPECT LETT, 32(3), 1999, pp. 421-429
The application of Artificial Neural Networks (ANNs) for nonlinear multivar
iate calibration using simulated FTIR data was demonstrated in this paper.
Neural networks consisting of three layers of nodes were trained by using t
he back-propagation learning rule. Since parameters affect the performance
of the network greatly, simulated data were used to train the network in or
der to get a satisfactory combination of all parameters. The mixtures of fo
ur air toxic organic compounds whose FTIR spectra are overlapped were chose
n to evaluate the calibration and prediction ability of the network. The re
lative standard error (RSD%), the percent standard error of prediction samp
les (%SEP) and the percent standard error of calibration samples (%SEC) are
used for evaluating the ability of the neural network.