Predicting adulteration of grated Parmigiano Reggiano cheese with Ricotta using electrophoresis, multivariate nonlinear regression and computational intelligence methods

Abstract

Urea polyacrylamide gel electrophoresis combined with statistical methods was used to detect the addition of Ricotta to grated Parmigiano Reggiano cheese. The adulterated samples were prepared by adding grated Ricotta to grated Parmigiano Reggiano cheese in six different ratios. The logistic regression and rank correlation performed worse than the naïve Bayes classifier at identifying samples of grated Parmigiano Reggiano containing more than 20% Ricotta in terms of area under the receiver operating characteristic curve and classification accuracy. This work can be considered a pilot study to investigate the potential of machine‐learning methods to predict the authenticity of Parmigiano Reggiano cheese.