Microencapsulation of Dragon Fruit Peel Extract by Freeze-Drying Using Hydrocolloids: Optimization by Hybrid Artificial Neural Network and Genetic Algorithm

The freeze-drying encapsulation process was used to encapsulate dragon fruit peel extract with three distinct wall materials: maltodextrin, gum arabica, and gelatin. modeled using a feed forward back propagation artificial neural network four, eleven, four neurons in the input, hidden, output layers. Three of input were concentrations material (g), while fourth ultrasonication power. efficiency, antioxidant activity, hygroscopicity, solubility freeze-dried powder. procedure optimized hybrid (ANN) genetic algorithm (GA) approach. optimal composition for obtained by integrated ANN GA 4.461 g 3.863 arabic, 3.198 power achieving homogenous mixture determined be 123 W. At condition, predicted values responses found 88.143%, 81.702%, 6.924 g/100 g, 32.841%, respectively. Under conditions, relative deviation between model experimental outcomes less than 2.077%. thermal stability encapsulated powder followed first order kinetic modeling. results showed that sample treated at pH 7 more thermally stable 80 °C 3.6. half-life time 140 min 103 3.6,