No abstract

Several researchers have developed prediction equations to estimate the metabolisable energy (ME) of energetic and protein concentrate feedstuffs used in diets for broilers. The ME is estimated by considering CP, ether extract, ash and fibre contents. However, the results obtained using traditional regression analysis methods have been inconsistent and new techniques can be used to obtain better estimate of the feedstuffs' energy value. The objective of this paper was to implement a multilayer perceptron network to estimate the nitrogen-corrected metabolisable energy (AMEn) values of the energetic and protein concentrate feeds, generally used by the poultry feed industry. The concentrate feeds were from plant origin. The dataset contains 568 experimental results, all from Brazil. This dataset was separated into two parts: one part with 454 data, which was used to train, and the other one with 114 data, which was used to evaluate the accuracy of each implemented network. The accuracy of the models was evaluated on the basis of their values of mean squared error, R 2 , mean absolute deviation, mean absolute percentage error and bias. The 7-5-3-1 model presented the highest accuracy of prediction. It was developed an Excel R AMEn calculator by using the best model, which provides a rapid and efficient way to predict the AMEn values of concentrate feedstuffs for broilers.Keywords: avian production, broilers, metabolisable energy, multilayer perceptron ImplicationsIt is difficult and expensive to estimate the nitrogencorrected metabolisable energy (AMEn) values of the feedstuffs used for broilers. The results of this study demonstrate that the implementation of multilayer perceptron networks (MLP) in a meta-analysis is suitable to estimate these energy values. Furthermore, a calculator was created on the basis of the results of the MLP, which allows an efficient way of predicting the AMEn values.

No abstract

A set of prediction equations to estimate the nitrogen-corrected apparent metabolizable energy (AMEn) of individual ingredients and diets used in the poultry feed industry was evaluated. The AMEn values of three energy ingredients (maize, sorghum and defatted maize germ meal), four protein ingredients (soybean meal, maize gluten meal 60% crude protein, integral micronized soy and roasted whole soybean) and four diets (three containing four feedstuffs, complex diets, and one containing only corn-soybean meal, basal diet) were determined using a metabolism assay with male broilers from 1 to 7, 8 to 21, 22 to 35, and 36 to 42 days old. These values were compared to the AMEn values presented in the tables of energy composition or estimated by equation predictions based on chemical composition data of feedstuffs. In general, the equation predictions more precisely estimated the AMEn of feedstuffs when compared to the tables of energy composition. The equation AMEn (dry matter [DM] basis) = 4,164.187+51.006 ether extract (% in DM basis)–197.663 ash–35.689 crude fiber (% in DM basis)–20.593 neutral detergent fiber (% in DM basis) (R2 = 0.75) was the most applicable for the prediction of the energy values of feedstuffs and diets used in the poultry feed industry.

INTRODUÇÃOA diversidade de alimentos e subprodutos utilizados na alimentação de frangos de corte exige o conhecimento preciso da composição química e valores de energia metabolizável (EM) desses alimentos, possibilitando a formulação de dietas equilibradas nutricional e economicamente. Uma forma rápida de determinar os valores de EM consiste na utilização de equações de predição, estabelecidas em função da composição química deles, normalmente de fácil e rápida obtenção.Existem, à disposição na literatura, vários trabalhos de pesquisa, em que se estabeleceram equações de predição para os valores energéticos de uma série de alimentos (ZHAO et al., 2008;WAN et al., 2009). Porém, os resultados obtidos utilizando-se essas equações não têm sido satisfatórios. Com o intuito de melhorá-los, pode-se utilizar o princípio da meta-análise. Um dos objetivos da meta-análise é a obtenção de novos resultados, a partir da síntese de n observações distintas, porém relacionadas entre si (LOVATTO et Prediction equations of energetic values of feedstuffs obtained using meta-analysis and principal components