The study evaluated the feasibility of applying computational intelligence methods as a non-destructive technique in describing the drying behaviour of persimmon fruit using vacuum drying (VD) and hot-air-drying (HAD) methods and to compare the results with thin layer mathematical models. Drying temperatures were 50, 60 and 70 °C. Kinetic models were developed using semi-theoretical thin layer models and computational intelligence methods: multi-layer feed-forward artificial neural network (ANN) and support vector regression (SVR). The statistical indicators of coefficient of determination (R2) and root mean square error (RMSE) were used to assess the suitability of the models. The thin-layer mathematical models namely page and logarithmic accurately described the drying kinetics of persimmon slices with the highest R2 of 0.9999 and lowest RMSE of 0.0031. ANN showed R2 and RMSE values of 1.0000 and 0.0003, while SVR showed R2 of 0.9999 and RMSE of 0.0004. The validation results indicated good agreement between the predicted values obtained from the computational intelligence methods and the experimental moisture ratio data. Based on the study results, computational intelligence methods can reliably be used to describe the drying process of persimmon fruit.
展开▼