The Application of Fuzzy Inference System and Adaptive Neuro-Fuzzy Inference System as Artificial Intelligence Methods for Modeling and Prediction of the Ceftriaxone Removal Percentage Using Nano Zero-Valent Iron Coupled with Strontium Hexaferrite

In this study, the removal efficiency of ceftriaxone (CTX) from aqueous media was assessed via nano zero-valent iron (nZVI) incorporated with strontium hexaferrite (SrFe۱۲O۱۹) (nZVI/SrFe۱۲O۱۹). The synthesized adsorbent was characterized using Scanning Electron Microscopy (SEM), Energy Dispersive X-ray (EDX), Fourier-Transform InfraRed (FT-IR), spectroscopy, and X-Ray Diffraction (XRD). The experiments with different parameters such as pH, adsorbent dosage, and initial concentration were designed. Two artificial intelligence methods, including the Fuzzy Inference System (FIS) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were used to model for predicting the percentage of CTX removal. The mean recovery value was found to be ۱۰۰.۰۳% and ۱۰۰.۰۰۰۶% for FIS and ANFIS, respectively. Root mean square error (RMSE) and mean absolute percentage error (MAPE) were ۰.۱۲۹۱, ۰.۰۳۸۴%, and ۰.۰۰۲۶, ۰.۰۱۰۵% for FIS and ANFIS, respectively. These results represent that both FIS and ANFIS models are capable of predicting the removal percentage of CTX with high precision and accuracy. It can also be said that the ANFIS model indicated a higher predictive ability than the FIS model based on the good agreement with predicting values of experimental data. The nZVI/SrFe۱۲O۱۹ can be used effectively to overcome contamination problems posed by antibiotics in the environment.

Keywords:

Fuzzy Inference System , Adaptive neuro-fuzzy inference system , Nano zero-valent iron , ceftriaxone , Adsorption