Journal
POULTRY SCIENCE
Volume 89, Issue 7, Pages 1562-1568Publisher
POULTRY SCIENCE ASSOC INC
DOI: 10.3382/ps.2010-00639
Keywords
meat and bone meal; metabolizable energy; neural network model; partial least squares model; multiple linear regression model
Categories
Ask authors/readers for more resources
There has been a considerable and continuous interest to develop equations for rapid and accurate prediction of the ME of meat and bone meal. In this study, an artificial neural network (ANN), a partial least squares (PLS), and a multiple linear regression (MLR) statistical method were used to predict the TME(n) of meat and bone meal based on its CP, ether extract, and ash content. The accuracy of the models was calculated by R(2) value, MS error, mean absolute percentage error, mean absolute deviation, bias, and Theil's U. The predictive ability of an ANN was compared with a PLS and a MLR model using the same training data sets. The squared regression coefficients of prediction for the MLR, PLS, and ANN models were 0.38, 0.36, and 0.94, respectively. The results revealed that ANN produced more accurate predictions of TME(n) as compared with PLS and MLR methods. Based on the results of this study, ANN could be used as a promising approach for rapid prediction of nutritive value of meat and bone meal.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available