Soft Computing Methodology for Shelf Life Prediction of Processed Cheese

Abstract

Feedforward multilayer models were developed for predicting shelf life of processed cheese stored at 30o C. Input variables were Soluble nitrogen, pH, Standard plate count, Yeast & mould count and Spore count. Sensory score was taken as output parameter for developing feedforward multilayer models. Mean square error, root mean square error, coefficient of determination and nash - sutcliffo coefficient performance measures were implemented for testing prediction potential of the soft computing models. The study revealed that soft computing multilayer models can predict shelf life of processed cheese.