Prediction of pores formation (porosity) in foods during drying: generic models by the use of hybrid neural network

摘要: Abstract General porosity prediction models of food during air-drying have been developed using regression analysis and hybrid neural network techniques. Porosity data apple, carrot, pear, potato, starch, onion, lentil, garlic, calamari, squid, celery were used to develop the model 286 points obtained from literature. The best generic was based on four inputs as temperature drying, moisture content, initial porosity, product type. error for predicting is 0.58%, thus identified an accurate model.