Neuro-fuzzy and response surface modeling of osmotic dehydration of pomegranate arils

In this research, pomegranate arils are dehydrated by osmotic dehydration in 40, 50, and 60 % sucrose ýsolutions and at 45, 55 and 65 degrees Cýþ þý and Weight Reduction, Solids grain and Water Loss of the products ýwere measured at 60, 120 and 180 minutes of process. Osmotic dehydration processes was modeled by ýcombination of neural network and fuzzy logic techniques (Neuro-fuzzy) and response surface methodology. ýFor modeling, interpolation and increase of the data’s, fuzzy logic was used. By entering the obtained results ýfrom fuzzy model into the neural network tool, the Feed-Forward-Back-Propagation network with the ýtopology of 3-8-3 and the correlation coefficient of 0.98344ýþ þand mean square error of 0.02278ýþ þwith ýapplication of Log-sigmoid transfer functionþ þý(logsig) and Levenberg–Marquardt learning algorithm was ýdetermined as the best neural model. Regression models created by response surface methodology by ýcorrelation coefficient of 0.90 were also capable for prediction of response factors but in comparison with ýNeuro-fuzzy models have a lower accuracy.ý