Modeling and optimization of osmotic dehydration of wax apple slices using adaptive neuro-fuzzy inference system

Abstract

The effect of ultrasound on osmotic dehydration of wax apple was investigated using the Fuzzy inference system, and the process parameters of ultrasonic assisted osmotic dehydration were optimized. The effect of ultrasonication temperature (XUT; 25 - 45 °C), sonication time (XIt; 140 - 220 min), sugar concentration (XSC; 30 - 70%), and sample to solvent ratio (XSS; 1:6 - 1:14) was studied. The responses such as water loss, solid gain, and color change, were investigated by modeling the ultrasonic assisted osmotic dehydration of wax apple using an adaptive neural fuzzy interface (ANFIS). Three ANFIS models were developed for the responses with Gaussian and linear membership functions as the input and output membership functions, respectively. The developed ANFIS model had R2 value more than 0.985 and an RMSE value less than 0.04, indicating a higher predictive capability. The ANFIS output was considered as input for the genetic algorithm (GA) optimization, with the objective of achieving maximal water loss while minimizing solid gain and color change. The integrated ANFIS-GA optimized the process parameters with a fitness value of 2.8. The optimum values of ultrasonic assisted osmotic dehydration process parameters were ultrasonication temperature of 38.6 °C, sonication time of 186 min, sugar concentration of 62%, and solvent to sample ratio of 11.7 w/v. The predicted values of the response water loss, solid gain, and color change at the optimum condition were observed to be 40.698, 3.097, and 10.916, respectively.