Experimental investigation and modeling of wild sage seed gum coating effect on the fried eggplant slices characteristics at different temperature

Fried food products are very popular due to their unique characteristics such as color, smell, taste and desirable texture. During the frying process, food is immersed in an oil bath at a temperature above the boiling point of water. This results in counter flow of water vapour (bubbles) and oil at the surface of the product. Colour changes measured may be used to predict both chemical and quality changes in a food. The colour parameters have previously proved valuable in describing visual colour deterioration and providing useful information for quality control in fruits and fruit products. The oil uptake problem associated with fried products can be decreased by using hydrocolloids as edible coating. Also, the sensorial examination results showed that the coated products with gums have total acceptability better than the uncoated samples. Using of hydrocolloids (gums) to decrease the oil uptake during deep-fat frying is one of the easy and most convenient way which does not needs changes in frying devises (Khazaei et al 2016; Salehi 2020a). The term “gum” is used to explain a group of naturally occurring polysaccharides. Gums have a good functional characteristic such as emulsifying, coating agents, packaging films, gelling, stabilizers, solubility and textural improvement (Salehi 2017). Gums influence on the gelatinization and retrogradation of starch and decreased the retrogradation of starch. Wild sage seed mucilage is a gum extracted from wild sage (Salvia macrosiphon L.) seeds. The performance of artificial neural networks (ANN) was reported by some researcher. They reported that these approaches are able to estimated characteristics of various fruits and vegetables with high precision. It has been shown that nonlinear approaches based on ANN are far better in generalization and estimation in comparison to empirical models. Determination of the best number of neurons in hidden layers of ANN models is generally carry out by trial and error. The genetic algorithm optimization method can be used to overcome this inherent limitation of ANN. Genetic algorithm is the search technique for optimal value, mimicking the mechanism of biological evolution. It has a high capability to find the optimum value of a complex objective function, without falling into local optima (Salehi 2020b; Amini et al 2021).

The cleaned wild sage seeds were firstly soaked in water at a seed/water a portion of 1:20, 25°C, and for 20 min. The mucilage extract was separated from the swollen wild sage seeds by passing the seeds through an extractor. Controlling frying conditions and using edible hydrocolloid coatings (gums) is one of the best ways in reduction of oil uptake, moisture retention and improving the appearance properties of fried foods. In this study, different concentrations of wild sage seed gum (0, 0.5, 1 and 1.5%) were used to coating of eggplant slices during deep frying at 150, 175 and 200°C and the relationship between process parameters and the quality of final product were modeled by genetic algorithm-artificial neural network method. To examine the changes in colour indexes including lightness (L*), redness (a*) and yellowness (b*), images were taken after the frying. In order to investigate the effect of frying temperature and wild sage seed gum concentration on the colour changes of fried eggplant, a computer vision system was used. Sample illumination was achieved with HP Scanner (Hp Scanjet 300). Neurosolution software (version 5, NeuroDimension, Inc., USA) was employed for making the GA-ANN model. In the hidden layers and output layer a sigmoid activation function was used (due to the highest r-values in comparison to the other functions, hyperbolic tangent and a linear).The Levenberg–Marquardt (LM) optimization method was applied to network training. The crossover probability and the mutation probability operators were adjusted equal to 0.9 and 0.01, respectively. Also, a sensitivity analysis was done to supply the measure of relative significance between the inputs of the ANN model and to show how the model output changed in response to input changes.

The results of this study showed that coating with wild sage seed gum reduced the oil uptake of the final product. Coating pretreatment maintained the final product moisture and moisture content of the sample coated with 1.5% wild sage seed gum was higher than the other samples. This process was modeled by genetic algorithm-artificial neural network method with 2 inputs include wild sage seed gum concentration and frying temperature and 5 outputs includes oil percentage, moisture content, and three main color indexes (yellowness (b*), redness (a*), and lightness (L*)). The results of modeling showed that a network with 3 neurons in a hidden layer and using the sigmoid activation function can predict the physicochemical properties of fried eggplant slices.

Wild sage seed gum concentration and oil temperature are the process parameters which affect the parameters of eggplant slices during frying. Sensitivity analysis results showed that the changes in the concentration of wild sage seed gum had the highest effect on the moisture content and then on the oil content of fried eggplant slices. Also, the change of frying temperature has the highest effect on the lightness index of fried samples.