|
Neural network
approach for modeling the mass transfer of potato slices
during osmotic dehydration using genetic algorithm
M. R. Amiryousefi*
and M. Mohebbi
Department of Food Science and Technology, Ferdowsi
University of Mashhad, P. O. Box: 91775-1163, Mashhad, Iran.
*Corresponding author. E-mail: mramiryousefi@yahoo.com
.
Accepted 19 November, 2009 |
|
In this study, an approach for designing a neural network
based on genetic algorithm has been used to model mass
transfer during osmotic dehydration of potato slices. The
experimental data were obtained through a complete
randomized design with different osmotic solutions (5, 10
and 15% w/w) and potato to solution ratios
(1:6,
1:8
and 1:10)
at varying temperatures (30, 40 and 60°C) and the best model
obtained with optimization of a multi-layer perceptron
neural network had a mean absolute error of 0.260, 0.516 and
0.137 for moisture content, water loss and solid gain of
osmotically dehydrated slices respectively.
Key words:
Osmotic dehydration, potato, neural network, genetic
algorithm, modeling, mass transfer. |
