Oxidative stability of virgin olive oil: evaluation and prediction with an adaptive neuro-fuzzy inference system (ANFIS)

Background An adaptive neuro-fuzzy inference system (ANFIS) was employed to predict the oxidative stability of virgin olive oil (VOO) during storage as a function of time, storage temperature, total polyphenol, alpha-tocopherol, fatty acid profile, ultraviolet (UV) extinction coefficient (K-268), and diacylglycerols (DAGs). Results The mean total quantities of polyphenols and DAGs were 1.1 and 1.9 times lower in VOOs stored at 25 degrees C than in the initial samples, and the mean total quantities of polyphenols and DAGs were 1.3 and 2.26 times lower in VOOs stored at 37 degrees C than in the initial samples, respectively. In a single sample, alpha-tocopherol was reduced by between 0.52 and 0.91 times during storage, regardless of the storage temperature. The mean specific UV extinction coefficients (K-268) for VOO stored at 25 and 37 degrees C were reported as 0.15 (ranging between 0.06-0.39) and 0.13 (ranging between 0.06-0.35), respectively. The ANFIS model created a multi-dimensional correlation function, which used compositional variables and environmental conditions to assess the quality of VOO. The ANFIS model, with a generalized bell-shaped membership function and a hybrid learning algorithm (R-2 = 0.98; MSE = 0.0001), provided more precise predictions than other algorithms. Conclusion Minor constituents were found to be the most important factors influencing the preservation status and freshness of VOO during storage. Relative changes (increases and reductions) in DAGs were good indicators of oil oxidative stability. The observed effectiveness of ANFIS for modeling oxidative stability parameters confirmed its potential use as a supplemental tool in the predictive quality assessment of VOO. (c) 2019 Society of Chemical Industry