Optimisation of the addition of carrot dietary fibre to a dry fermented sausage (sobrassada) using artificial neural networks.

An optimisation problem was formulated to maximise the amount of carrot dietary fibre (CDF) in a dry fermented sausage, while maintaining product quality, by using 0-12% CDF as the decision variable, and limiting values of several physico-chemical and textural parameters (moisture content, water activity, pH, colour, non-protein nitrogen, free fatty acid, compression work and hardness) as constraints. The evolution of each quality parameter during the ripening process was estimated by developing a multi-layer feed forward artificial neural network (ANN), taking into consideration the CDF concentration and the ripening time as independent variables. Results indicate an optimum CDF concentration of 4.9% with a good correlation between experimental and estimated values (mean relative error≤3.35%).