Comparison of logistic and neural network models to fit to the egg production curve of White Leghorn hens

• Grant number: 11/00703-6
• Support Opportunities: Regular Research Grants - Publications - Scientific article
• Start date: March 01, 2011
• End date: August 31, 2011
• Field of knowledge: Agronomical Sciences - Animal Husbandry - Genetics and Improvement of Domestic Animals
• Principal Investigator: Danísio Prado Munari
• Grantee: Danísio Prado Munari
• Host Institution: Faculdade de Ciências Agrárias e Veterinárias (FCAV). Universidade Estadual Paulista (UNESP). Campus de Jaboticabal. Jaboticabal , SP, Brazil

Abstract

Neural networks are capable of modeling any complex function and can be used in animal production areas. The aim of this study was to investigate the possibility of using neural networks on an egg production data set and fitting models to the egg production curve by applying two approaches: one using a nonlinear logistic model and the other using two artificial neural network models (multilayer perceptron, MLP, and radial basis function, RBF). Two data sets from two generations of a White Leghorn strain that had been selected mainly for egg production were used. In the first data set, the mean weekly egg-laying rate was ascertained over a 54-week egg production period. This data set was used to adjust and test the Logistic model and train and test the neural networks. The second data set, covering 52 weeks of egg production, was used to validate the models. Mean absolute deviation, mean square error and coefficient of determination were used to evaluate the fit of the models. The MLP neural network had the best fit in the test and validation phases. The advantage of using neural networks is that they can be fitted to any kind of data set and do not require model assumptions like those required in the nonlinear methodology. The results confirm that MLP neural network can be used as an alternative tool to fit to egg production. The benefits of the MLP are the high flexibility and their lack of a priori assumptions when estimating a noisy non-linear model. (AU)