Prediction of amino acid profiles in feed ingredients: Genetic algorithm calibration of artificial neural networks

Linear regression (LR) has been used to predict the amino acid (AA) profile s of feed ingredients, given proximate analysis (PA) input. Artificial neur al networks (ANN have also been trained to predict AA levels, generally wit h better results. Past projects have indicated that ANN more effectively id entified the complex relationship between nutrients and feed ingredients th an did LR. It was shown that the maximum R-2 value, a measurement of the am ount of variability explained by the model, was highest when a general regr ession neural network (GRNN) with iterative calibration (GRNNIT) was used t o train the ANN. This was in comparison to LR, Ward backpropagation (WBP) o r 3-layer backpropagation (3BP) architectures. The current study investigat ed the potential of a new, advanced method of calibration using the genetic algorithm (GA) to optimize GRNN smoothing values. Calibration of an ANN al lows the neural network to generalize well and therefore provide good resul ts on new data. A GRNN architecture (NeuroShell 2 (R) Software) with GA cal ibration (GRNNGA) was used to train an ANN to predict AA levels in maize, s oya bean meal (SBM), meat and bone meal, fish meal and wheat, based on prox imate analysis input. Within the GRNNGA architecture, ANN were trained with either an Euclidean or City Block distance metric and a (0,1), (- 1,1), (l ogistic) or (tanh) input scale. Predictive performance was judged on the ba sis of the maximum R2 value. In general, maximum R2 values were higher when the GA calibration was used in comparison to LR. For example, the highest methionine (MET) R2 value for SBM was 0.54 (LR), 0.81 (3BP), 0.87 (WBP), 0. 92 (GRNNIT) and 0.98 (GRNNGA). Genetic algorithm calibration of GRNN archit ecture led to further improvements in ANN performance for AA level predicti ons in most of the cases studied.. Exceptions were the TSAA level in SBM (0 .94 with GRNNIT vs. 0.90 with GRNNGA) and the TRY level in maize (0.88 with GRNNIT vs. 0.61 with GRNNGA). (C) 2001 Elsevier Science B.V. All rights re served.