Nondestructive quantitative analysis of cimetidine tablets using artificial neural networks in near-infrared spectroscopy

This project was designed to explore the application of artificial neural networks (ANNs) and near-infrared (NIR) spectroscopy for nondestructive quantitative analysis of cimetidine tablets. The models of conventional spectra (SNV pretreated), first-derivative spectra, and second-derivative spectra, have been established, respectively. In order to be compared with the tablets, the powders were also determined. Both tablets and powders were found to provide similar results in the quantification of the active compound (cimetidine). Of all the models, the second-derivative models resulted in the lowest relative standard error (<0.1%). The parameters affecting the network were discussed, and unknown specimens were predicted. The degree of approximation, a new evaluation criterion of the network, was employed, which proved the accuracy of the predicted results.