The prediction of lean meat and subcutaneous fat with skin content in pork cuts on the carcass meatness and weight

Abstract

Early post-mortem, objective and non-destructive prediction of tissue distribution in the major pork cuts is a challenge for the meat industry. Mathematical models to predict pig carcass composition using total lean meat percentage and carcass weight were evaluated in this study. The data were obtained from 455 cold pig carcasses which were dissected according to the EU reference method; total lean meat percentage and carcass weight ranged from 42.45 to 69.21% and from 23.26 to 55.22 kg, respectively. Developed empirical models gave a reasonable fit to the experimental data and successfully predicted the carcass composition and tissue distribution in primal cuts. The second order polynomial models showed high coefficients of determination for prediction of experimental results (between 0.612 and 0.929), while the artificial neural network (ANN) model, based on the Broyden–Fletcher–Goldfarb–Shanno iterative algorithm, showed better prediction capabilities (overall r2 was 0.889). The newly developed software, based on ANN model is easy, fast, cheap and with sufficient precision for application in the meat industry.