Appraisal of Artificial Neural Network and Response Surface Methodology in Modeling and Process Variable Optimization of Oxalic Acid Production from Cashew Apple Juice: A Case of Surface Fermentation

摘要: This study assessed the effects and interactions of cashew apple juice (CAJ) concentration, pH, time, methanol NaNO3 concentration on oxalic acid fermentation in a central composite design. The efficacies artificial neural network (ANN) response surface methodology (RSM) modeling optimizing process were evaluated using correlation coefficient (R), determination (R2), absolute average deviation (AAD). highest production observed was 120.66 g/L under optimum values CAJ 291 g/L, pH 6.9, time 10.82 days, 2.91% (v/v), 1.05 that numerically predicted by developed RSM quadratic model. Using ANN model coupled with rotation inherit optimization, 286.75 following values: 6.5, 12.64 3.82% 2.41 g/L. results showed (R = 0.9996, R2 0.9999, AAD 0.21%) better than 0.9986, 0.9973, 1.00%) for fermentation. use led to 2.4-fold increase yield over