Effects on beef microstructure using fractal dimension and ANN modelling

Abstract

The freezing time of beef has been predicted using an artificial neural network (ANN), which relies on data obtained from the microstructure of meat. For this reason, cross-sectional images of beef meat were captured during six periods of frozen storage (2, 4, 6, 8, 10, and 12 months after slaughter). The equivalent diameter and ratio of area of the ice crystals relative to the cell were determined, and the fractal dimension was chosen to describe the porous microstructure due to the crystallization of ice in frozen beef. As a result, when meat has been frozen for a long time, larger ice crystals form. In contrast, the fractal dimension decreased with the change in the microstructure of muscle tissue during storage. Artificial neural network analysis (ANN) revealed a high accuracy of prediction performance for each morphological attribute. These results show that the fractal dimension can be used as an effective method to characterize the structure of beef during frozen storage, and ANN models can successfully describe structural changes in beef meat during frozen storage.