Application of simulated neural networks as Non-Linear Modular Modeling Method for predicting shelf life of processed cheese / Sumit Goyal and Gyanendra Kumar Goyal

• Main Authors: Goyal, Sumit (Author), Goyal, Gyanendra Kumar (Author)
• Format: Article
• Language: English
• Published: Universiti Teknologi MARA, Perlis, 2012-12.
• Subjects: Neural networks (Computer science); Article
• Online Access: Get fulltext; View Fulltext in UiTM IR

 This paper presents the capability of simulated neural network (SNN) models for predicting the shelf life of processed cheese stored at ambient temperature 30o C. Processed cheese is a dairy product generally made from medium ripened Cheddar cheese. Elman and Linear Layer(Train) SNN models were developed. Body & texture, aroma & flavour, moisture, free fatty acids were used as input variables and sensory score as the output. Neurons in each hidden layers varied from 1 to 40. The network was trained with single as well as double hidden layers up to 100 epochs, and transfer function for hidden layer was tangent sigmoid while for the output layer, it was pure linear function. Mean square error, root mean square error, coefficient of determination and nash - sutcliffo coefficient performance measures were used for testing prediction potential of the developed models. Results showed a 4201 topology was able to predict the shelf life of processed cheese exceedingly well with R2 as 0.99992157. The corresponding RMSE for this topology was 0.003615359. From this study it is concluded that SNN models are excellent tool for predicting the shelf life of processed cheese.