Artificial Neural Networks for the Evaluation of Physicochemical Properties of Carrots (Daucus carota L.) Subjected to Different Cooking Conditions as an Alternative to Traditional Statistical Methods

Abstract

The study aimed to evaluate the impact of different cooking methods (sous vide, boiling, and steamed) on the physicochemical properties of carrots (Daucus carota L.). The colorimetric parameters, texture, carotenoid content, and antioxidant capacity of carrots were observed. The steam cooking method proved to be the best method to preserve the concentration of carotenoids and showed a protection of about 40%, regarding the antioxidant capacity, a property also observed in the sous vide method, independent of the time. In terms of texture, the steam cooking method rendered them a greater softness. Moreover, this study corroborates that artificial neural networks (ANNs) can be used as an effective tool for data treatments by grouping according to their similarities. The results obtained with ANN provided the same information when compared to those of the commonly used traditional multivariate statistical techniques considering that the self-organizing maps proved to be easier to visualize and analyze.