Heuristic Machine Learning Feedforward Algorithm for Predicting Shelf Life of Processed Cheese

Abstract

This paper describes the potential of machine learning feedforward algorithm for predicting shelf life of processed cheese. Soluble nitrogen, pH, Standard plate count, Yeast & mould count, and Spore count were taken as input parameters, and sensory score as output parameter for developing feedforward single and multilayer models. The dataset was divided into two disjoint sets, one for training and the other for validation. Backpropagation algorithm based on Bayesian Regularization was selected for training the feedforward models. 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. The study revealed that feedforward models are good in predicting shelf life of processed cheese.