Adaptive Neuro-Fuzzy Inference System for Modeling the Cephalexin (CFX) Adsorption on the Octenyl Succinic Anhydride Starch

Abstract

Adaptive neuro-fuzzy interference (ANFIS) system is applied to modeling the removal of cephalexin antibiotic (CFX) by adsorption using the Octenyl succinic anhydride OSA Starch as amphiphilic polysaccharidique adsorbent. The effects of various parameters such as contact time, pH, temperature, and OSA-Starch dosage were investigated. These parameters are considered as intputs for the ANFIS system, while the output is the amount of adsorbed cephalexin per mass unit of OSA starch. The predicted values are very similar to the experimental results with correlation coefficient $(R^{2})$ of 0.998 and MSE $1.64\times 10^{-}14$. The results showed that ANFIS modeling could effectively predict and simulate the adsorption process.