Abstract
Neural networks have been found to be good general classifiers of the binned C-13 NMR spectra of limonoids and associated extractives from the Meliaceae family. 5 ppm binning of the C-13 NMR spectra was found to be superior to 10 ppm binning. The excellent results obtained by developing the system on real extractives using the 5 ppm binning, revealed that the system developed was robust and general enough to tolerate the inherent problems associated with natural product extraction. Experiments concerning the effect of noise and missing bins were also conducted and documented. A literature-sourced sample set was also added in order to ensure the system was not specifically designed to cope only with the unique data set on which it had been trained.