Comparison of response surface methodology and artificial neural network to estimate the bird responses to dietary attributes

Nowadays, the poultry industry has gained special importance due to higher demand for white meat than red meat. One of the main factors affecting body weight gain in broiler chickens is the nutritional requirements for essential amino acids including methionine, lysine, and threonine. In this survey, the growth rate of the birds in response to dietary levels of Met, Lys, and Thr were analyzed using response surface methodology (RSM) and artificial neural networks (ANN). The efficiency of these methods was assessed using some statistical parameters including coefficient of determination (R2), mean square error (MSE), mean absolute deviation (MAD), mean absolute percentage error (MAPE), and average absolute deviation (AAD). The higher R2 of ANN models (R2 = 0.92) than that of RSM models (R2 = 0.51) and lower residual distribution for ANN models revealed that ANN is the more efficient tools for recognition of birds responses to nutritional factors than regression method.