SOY-SAUCE CLASSIFICATION BY GEOGRAPHIC REGION-BASED ON NIR SPECTRA AND CHEMOMETRICS PATTERN-RECOGNITION

Statistical and artificial neural network (ANN) pattern recognition te chniques were applied to NIR spectra of 38 soy sauce samples collected from the northern/central, western, and southern regions in Japan and related to differences in food flavorings. Linear discriminant analys is (LDA) and ANN using factor scores calculated from NIR spectra showe d more accurate differentiations than those based on the original spec tra. In LDA, the correctly assigned ratio was 81.6%. Correct classific ation ratios shown by Partial least squares (PLS2) were 84.2% and by A NN 76.3% in the cross-validation test. The differentiations suggested that there are quality differences in soy sauce among the three region s in Japan.