Comparison of Arrhenius model and artificial neuronal network for predicting quality changes of frozen tilapia...

The objectives of this study were to study the quality changes (ice crystal morphology, Ca²⁺-ATPase activity, total sulfhydryl [SH] content, intrinsic fluorescence intensity [IFI], and K value [freshness determination]) of tilapia at different storage temperatures for 112 days, and kinetic models and artificial neuronal network (ANN) were developed to predict the changes. There was a dramatic increase in cross-section area and equivalent diameter and a sharp decrease in Ca²⁺-ATPase activity and SH content during the first 4 weeks (p < 0.05). IFI_λmax decreased by 43.95%, 29.77%, 28.97% and 18.58% after 16 weeks at 265 K, 259 K, 253 K, and 233 K. The kinetic model established by IFI_λmax could be accurately described the quality changes during storage at 233-265 K. However, the prediction accuracy established by other indices decreased at later stages (14-16 weeks). The ANN model was superior to Arrhenius models and performed better for all indicators.