Prediction of storage quality of fresh-cut green peppers using artificial neural network

To extend the shelf-life of fresh-cut fruits and vegetables, it is essential to develop models that can accurately predict their storage quality. In view of this, an artificial neural network (ANN) model based on back propagation (BP) algorithm was developed to predict the storage quality (degree of yellowness, water loss, textural firmness and vitamin C content) of fresh-cut green peppers. The prediction accuracy of ANN was compared with that of multiple linear regression-based models. The root mean square error (RMSE), mean absolute error (MAE), sum of squared residuals (SSR) and standard error of prediction (SEP) were used as comparison parameters. The results showed that the accuracy and goodness of fit of the storage quality parameters predicted by ANN were better than those predicted by multiple linear regression-based models. The RMSE, MAE, SSR and SEP values obtained from the former were much lower than those obtained from the latter.