Pork carcass composition derived from a neural network model of electromagnetic scans.

Abstract

We used an advanced computer logic system (NETS 3.0) to decipher electromagnetic (EM) scans in lieu of traditional linear regression for estimation of pork carcass composition. Fifty EM scans of pork carcasses were obtained on-line (prerigor) at a swine slaughter facility. Right sides were cut into wholesale parts and dissected into fat, lean, and bone to obtain total dissected carcass and primal cut lean. In this study, the input layer consisted of 81 nodes (80-point EM scan curve and warm carcass weight), one hidden layer of 42 nodes, and an output layer consisting of one node, which were run separately for outputs of ham, loin, or shoulder lean. The hidden layer connected to the output of total lean contained 50 nodes. Thirty-five scans were used for training of the network. The new network was then tested with 15 previously unseen input/output pairs. Separate neural networks were developed for the estimation of dissected total carcass, ham, loin, and shoulder lean. The NETS configuration improved on linear regression equations for estimation of total carcass lean by .31 kg, ham lean by .284 kg, and shoulder lean by .148 kg. Our results show that advanced computer logic systems have the capacity to improve upon traditional linear regression equations for prediction of pork carcass composition.

Prediction of the Nutrient Content in Dairy Manure Using Artificial Neural Network Modeling

“…The comparative advantage of ANN over more conventional econometric models such as MLR and polynomial regression (PNR) models (Lugo-Ospina et al, 2005) is that it can model complex, possibly nonlinear relationships without any prior assumptions about the underlying data-generating process (White, 1990). Because of these features, ANN have been widely used in animal science (Berg et al, 1998;Fernández et al, 2006). The objective of this paper is to present various applications of the ANN in rapid estimation of dairy manure nutrient content.…”

Application of Artificial Neural Networks in Meat Production and Technology

“…In these cases the aim was either to predict carcass lean meat content (Hwang et al, 1997;Berg et al, 1998;Lu & Tan, 2004) or to replace the classifier using automated grading (Borggaard et al, 1996 Other studied applications were interested in prediction of fat depots based on in vivo measurements (Peres et al, 2010) or prediction of carcass maturity (Hatem et al, 2003). In the case of pig classification, studies using ANN are rare (Berg et al, 1998), probably because the current classification methods are based on objective measurements on the carcass which are well correlated to lean meat content thus providing sufficient accuracy using standard regression methods. There was an interesting study in bovine carcass classification addressing the problem of classifier effect and repeatability in bovine carcass grading (Díez et al, 2003), demonstrating another possible application of ANN for the purposes of monitoring.…”

Neural network modeling of carcass measurements to predict beef tenderness

“…The theory and specific procedures of NN modeling of meat data have been described in studies to predict marbling score (Brethour 1994), taste panel scores (Park et al 1994), and pork carcass composition (Berg et al 1998). The objectives of this study were to develop NN models 1) to predict beef tenderness (WBS) using multiple carcass measurements and 2) to classify carcasses into tenderness categories.…”