APPLICATION OF ARTIFICIAL NEURAL NETWORK TO PREDICTION OF CANTONESE SOY SAUCE BREWING AND CHANGING PATTERN CONCERNING TOTAL NITROGEN AND -AMINO ACID NITROGEN

摘要

In the present study, the artificial neural network was used to predict thenbrewing of traditional Cantonese soy sauce and its changing pattern withnregard to total nitrogen (TN) and a-amino acidic nitrogen (AN). The effects ofnparameters during brewing on the contents of TN and AN were modeled bynvarious networks. After the 7-40-2 network was determined statistically, it wasnused to extract the possible correlations between TN and AN, and the relativensignificance of some factors. It was found that the change of TN and ANncontents with the change of time and acidic protease activity was stronglyncorrelated with an R value of 0.9848 and 0.9916, respectively. As for thenrelative significances of inputs, aging time is the key factor for both outputsnduring the moromi aging. And for other inputs, it was temperature >npH > neutral protease activity > acid protease activity for TN, andntemperature > acidic protease activity > neutral protease activity > pH fornAN, respectively.