At array of nine piezoelectric quartz crystals, each coated with a dif
ferent derivative compound of crown-ether, was constructed for multico
mponent analysis of organic vapors. The usefulness of this array was e
valuated by quantitating known mixture samples in both two and three c
omponent cases using two chemometric techniques, partial least squares
(PLS) and artificial neural networks (ANN). The results show that the
prediction was better for ANN in both two and three component cases.
The method to avoid overfitting in ANN training was also discussed.