A Hybrid Model for Nondestructive Measurement of Internal Quality of Yogurt

A nondestructive optical method for determining the sugar and acidity contents of yogurt was investigated. Two types of preprocessing were used before the data were analyzed with multivariate calibration methods of principal component artificial neural network (PC-ANN) and partial least square (PLS). In PC-ANN models, the scores of the principal components were chosen as the input nodes for the input layer of ANN. After adjusting the number of input nodes (principal components), hidden nodes, at the same time learning rate and momentum of the network, a model with a correlation coefficient of 0.89/0.91, a root mean square error of prediction (RMSEP) of 0.41/0.04 showed an excellent prediction performance to sugar/acidity. At the same time, the sensitive wavelengths corresponding to the sugar content and acidity of yogurts were proposed on the basis of regression coefficients by PLS