Improved pullulan production and process optimization using novel GA–ANN and GA–ANFIS hybrid statistical tools

Abstract

Pullulan production from Aureobasidium pullulans was explored to increase yield. Non-linear hybrid mathematical tools for optimization of process variables as well as the pullulan yield were analyzed. The one variable at a time (OVAT) approach was used to optimize the maximum pullulan yield of 35.16 0.29 g/L. The tools predicted maximum pullulan yields of 39.4918 g/L (genetic algorithm coupled with artificial neural network (GA–ANN)) and 36.0788 g/L (GA coupled with adaptive network based fuzzy inference system (GA–ANFIS)). The best regression value (0.94799) of the Levenberg–Marquardt (LM) algorithm forANNand the epoch error (6.1055 10􀀀5) for GA–ANFIS point towards prediction precision and potentiality of data training models. The process parameters provided by both the tools corresponding to their predicted yield were revalidated by experiments. Among the two of them GA–ANFIS results were replicated with 98.82% accuracy. Thus GA–ANFIS predicted an optimum pullulan yield of 36.0788 g/L with a substrate concentration of 49.94 g/L, incubation period of 182.39 h, temperature of 27.41 C, pH of 6.99, and agitation speed of 190.08 rpm.