Keywords: adaptive neuro-fuzzy inference system, ANFIS, O&, #47, W emulsion, response surface methodology, RSM, formulation factors, processing variables, optimal emulsions, fatty alcohol, neural networks, fuzzy logic
An adaptive neuro-fuzzy inference system for optimising the emulsifier concentration in the formulation of an O/W emulsion
An emulsion is composed of several formulation factors and processing variables. The optimisation of concentration of an emulsifier that produces the most stable emulsion has been a very tedious task if done experimentally. Several responses relating to the effectiveness, usefulness, stability as well as safety must be optimised simultaneously. Hence, expertise and experience are required to design an acceptable emulsion for use in pharmaceuticals and also as cosmetics. A response surface method (RSM) has widely been used for selecting acceptable emulsions. However, prediction of pharmaceutical responses based on the second-order polynomial equation commonly used in a RSM, is often limited to low levels, resulting in poor estimations of optimal emulsions. The purpose of this study was to describe the basic concept of the multi-objective simultaneous optimisation technique, in which an adaptive neuro-fuzzy inference system, ANFIS is incorporated and simultaneously used in identifying the optimum concentration of a fatty alcohol, for formulating a stable O/W emulsion.