Modeling of freeze drying behaviors of strawberries by using artificial neural network

Abstract

The freeze drying process is based on different parameters, such as drying time, pressure, sample thickness, chamber temperature, sample temperature and relative humidity. Hence, the determination of the drying behaviors, such as MC and MR, of the freeze drying process are too complex. In this paper, to simplify this complex process, the use of artificial neural networks has been proposed. An artificial neural networks model has been developed for the prediction of drying behaviors, such as MC and MR, of strawberries in the freeze drying process. The back-propagation learning algorithm with variant which is Levenberg-Marquardt (LM) and Fermi transfer function have been used in the network. In addition, the statistical validity of the developed model has been determined by using the coefficient of determination (R 2), the root means square error (RMSE) and the mean absolute percentage error (MAPE). R 2, RMSE and MAPE have been determined for MC and MR as 0.999, 0.001924, 0.152284 and 0.999, 1.87E-05, 0.13393, respectively. © 2008 TIBTD Printed in Turkey. © 2012 Elsevier B.V., All rights reserved.