In this study, genetic algorithm–artificial neural network (GA-ANN) and adaptive neuro-fuzzy inference system (ANFIS) models were used for prediction of drying time (DT) and moisture ratio (MR) of basil seed mucilage (BSM) in an infrared (IR) dryer. The GA-ANN and ANFIS were fed with 3 inputs of IR radiation power, the distance of mucilage from lamp surface, mucilage thickness for prediction of average DT. Also, to predict the MR, these models were fed with 4 inputs of IR power, lamp distance, mucilage thickness and treatment time. The developed GA–ANN, which included 8 hidden neurons, could predict the DT of BSM with a correlation coefficient (r) of 0.97. Also, the GA–ANN model with 10 neurons in one hidden layer, could predict the MR with a high r-value (r=0.99). The calculated r-values for prediction of DT and MR using the ANFIS-based subtractive clustering algorithm were 0.96 and 0.99, respectively. Sensitivity analysis results showed that mucilage thickness and treatment time were the most sensitive factor for prediction of DT and MR of BSM drying, respectively.
