PREDICTION OF BULLS’ SLAUGHTER VALUE FROM GROWTH DATA USING ARTIFICIAL NEURAL NETWORK
2005, 6 (2) p. 133-142
The objective of this research was to investigate the usefulness of artifi cial neural network (ANN) in the prediction of slaughter value of young crossbred bulls based on growth data. The studies were carried out on 104 bulls fattened from 120 days of life until the weight of 500 kg. The bulls were group fed using mainly farm feeds. After slaughter the carcasses were dissected and meat was subjected to physico-chemical and organoleptic analyses. The obtained data were used for the development of an artifi cial neural network model of slaughter value prediction. It was found that some slaughter value traits (hot carcass, cold half-carcass, neck and round weights, bone content in dissected elements in half-carcass, meat pH, dry-matter and protein contents in meat and meat tenderness and juiciness) can be predicted with a considerably high accuracy using the artifi cial neural network.