Modelling of Grewia mollis Stem Bark Gum Extraction Yield Using Neuro-Fuzzy Technique

In this paper, Adaptive Neuro-Fuzzy Inference System (ANFIS) was used to model and predict Grewia Polysaccharide Gum (GPG) extraction yield from Grewia mollis (GM) powder/water system. The data for modelling the process behaviour consisted of four inputs (process temperature, GM powder/water ratio, process time and pH) and GPG yield as the output. The gbell Membership Function (MF) was used for the fuzzification of input variables and hybrid algorithm was chosen for the learning method of input–output data of the process. Simulation study was conducted on the developed ANFIS architecture at different MFs and epoch numbers to establish minimum error and maximum correlation coefficient (R) of the model. From the results obtained, ANFIS can be used as a reliable tool for modelling and prediction of GPG powder/water extraction process behaviour. The R between the experimental and predicted values was found to be high (> 0.96) and the mean percentage error was less than 2%, showing the great efficiency and reliability of the developed model.