期刊名称：Advances in Information Technology and Management
印刷版ISSN：2167-6372
出版年度：2012
卷号：1
期号：3
页码：127-131
语种：English
出版社：World Science Publisher
摘要：Elman artificial neural network (ANN) models were developed using backpropagation networks with a single hidden layer and sigmoid activation functions for predicting the shelf life of kalakand stored at 6 o C. Input variables were moisture, titratable acidity, free fatty acids, tyrosine and peroxide value of the product, while the overall acceptability score was taken as the output variable. It was found that ANN with 5à20à1 topology gave the best fitting with the experimental data, which made it possible to predict the shelf life of kalakand.
关键词：Artificial Intelligence;Artificial Neural Networks;Elman Backpropagation;Kalakand;Shelf Life Prediction
