Prediction model for true metabolizable energy of feather meal and poultry offal meal using group method of data handling-type neural network.

A group method of data handling-type neural network (GMDH-type NN) with an evolutionary method of genetic algorithm was used to predict the TME(n) of feather meal (FM) and poultry offal meal (POM) based on their CP, ether extract, and ash content. Thirty-seven data lines consisting of 15 FM and 22 POM samples were collected from literature and used to train a GMDH-type NN model. A genetic algorithm was deployed to design the whole architecture of the GMDH-type NN. The accuracy of the model was examined by R(2) value, adjusted R(2), mean square error, residual standard deviation, mean absolute percentage error, and bias. The developed model could accurately predict the TME(n) of FM or POM samples from their chemical composition. The R(2) for the GMDH-type NN model had a higher accuracy of prediction than 2 models reported previously. This study revealed that the novel modeling of GMDH-type NN with method of genetic algorithm can be used to predict the TME(n) of poultry by-products.