Please use this identifier to cite or link to this item:
Title: Neural network committee to predict the AMEn of poultry feedstuffs
Keywords: Committee machine
Ensemble estimators
HPD intervals
Metabolizable energy
Highest probability density (HPD)
Issue Date: Aug-2014
Publisher: Springer
Citation: MARIANO, F. C. M. Q. et al. Neural network committee to predict the AMEn of poultry feedstuffs. Neural Computing & Applications, [S.l.], v. 25, p. 1903-1911, Aug. 2014. DOI: 10.1007/s00521-014-1680-3.
Abstract: A committee of neural networks is the aggregation of two or more neural networks for making overall predictions that are supposedly more accurate than those obtained by the individual networks. The objective of this paper was to assign some uncertainty over the predictions of neural networks, using a network committee to estimate the nitrogen-corrected metabolizable energy (AMEn) values of the energetic and protein concentrate feedstuffs for broilers. The dataset used to implement each expert network contains 568 experimental results. Another dataset with 48 bioassay results was used as test data. From several implemented multilayer perceptrons, the networks that presented the best generalization performance were selected to constitute the committee. The percentage of correct predictions was used as the criterion to compare committees that contained different numbers of networks. The highest probability density intervals were obtained for each feedstuff in the test data in this comparison. The estimator that ensured more accurate predictions was selected. The highest accuracy for predicting the AMEn values of concentrate feedstuffs for broilers was achieved by a committee with 1,000 networks with the use of the mode of the empirical distribution obtained from 1,000 estimated values of the AMEn. The accuracy of the models was evaluated based on their values of error measures between the observed and predicted values, in which the mode of the empirical distribution presented lower values of mean squared error (MSE = 45,285.43), mean absolute deviation (MAD = 177.66) and mean absolute percentage error (MAPE = 5.97 %) compared to the mean and the median.
Appears in Collections:DZO - Artigos publicados em periódicos

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.