Prediction of Viscosities of Aqueous Two Phase Systems Containing Protein by Artificial Neural Network

Selvaraj Raja, Varadavenkatesa

Abstract

The viscosities of aqueous two phase system containing bovine serum albumin (BSA) were predicted by artificial neural network (ANN) as a function of concentration of poly-ethylene-glycol (PEG), concentration of BSA and temperature. A three layer feed forward neural network based on Levenberg-Marquardt (LM) algorithm which consisted of three input neurons, 10 hidden neurons and one output neuron (3:10:1) was developed. The performance parameters were calculated and compared with the conventional Grunberg-Nissan empirical model. The satisfactory values suggest that the proposed ANN model has the capability of predicting viscosity in a better way than the conventional empirical model.