Prediction of supercritical extraction recovery of EGCG using hybrid of Adaptive Neuro-Fuzzy Inference System and mathematical model

Supercritical extraction of antioxidants and pharmaceuticals is one of the most important applications in the field of supercritical fluids. Epigallocatechin gallate (EGCG) has pharmacological properties which include anti-oxidative, apoptotic, anti-obesity, anti-arteriosclerotic, anti-diabetic, anti-bacterial, anti-viral, and anti-mutagenic effects. In this study, recovery of EGCG supercritical extraction from green tea was modeled by hybrid of Adaptive Neuro-Fuzzy Inference System (ANFIS) and mathematical modeling with the constant distribution coefficient. Different ANFIS networks (by changing the type and number of membership functions and training algorithms) were compared with evaluation of networks accuracy in EGCG recovery prediction and subsequently the suitable network was determined. The obtained results in this work indicated that ANFIS was effective method for prediction of EGCG recovery and was successfully validated with experimental data. Finally the proposed hybrid model optimized with genetic algorithm in order to achieve maximum EGCG extraction recovery.