APPLICATION OF FOURIER-TRANSFORM TO MULTIVARIATE CALIBRATION OF NEAR-INFRARED DATA

An approach for extracting the relevant features for multivariate cali bration of the hydroxyl number in a polyol from a near-infrared (NIR) spectroscopic data set by using the Fourier transform, is presented. I t is carried out in the frequency domain starting from the first 50 po wer-spectra (PS) coefficients as the input to a genetic algorithm (GA) . The appropriate PS coefficients selected by the GA were used to buil d a multiple linear-regression (MLR) model, The performance of the new approach is compared with MLR after wavelength selection with GA, wit h the standard PCR and PLS methods applied to the wavelength domain, a nd PCR and PLS applied to the full PS domain. Furthermore, it was also compared to the 'Uninformative Variable Elimination' (UVE) PLS method in the frequency domain, The results demonstrate that PS is a fast an d powerful reduction method. The coefficients selected are of two type s: one that correlates with the characteristic investigated, and the o ther that takes into account different clusters, This also shows that the method can be used to investigate the structure of the data. (C) 1 998 Elsevier Science B.V.