Use of Artificial Neural Networks to estimate production parameters of broilers breeders in the production phase.

Visualização do Trabalho Completo
Arquivo do Adobe Acrobat com 304kb (pdf)

1) Although the poultry industry uses state-of-the-art equipment and up-to-date services, in Brazil it also generally makes decisions involving all its production parameters based on purely subjective criteria. This paper reports the use of artificial neural networks to estimate performance parameters in production birds belonging to a South Brazilian poultry farm. Recorded data from 22 broiler production breeder flocks were obtained, during the periods between 26th of April, 1998 and 19th of December, 1999, which corresponded to 689 data lines of weekly recordings.
2) These data were processed by artificial neural networks using the software NeuroShell 2(R) version 4.0TM (Ward Systems Group(R)). The artificial neural network models generated were compared and selected based on their largest determination coefficient (R2), lowest Mean Squared Error (MSE), as well as on an uniform scatter in the residual plots. The authors conclude that it is possible to explain the performance parameters of production birds, with the use of Artificial Neural Networks.
3) The method supplies tools for the decisions made by the technical staff to be based in objective, scientific criteria. This method also allows simulations of the consequences related to these decisions, and reports the contribution of each variable to the poultry production parameters under study.

Key words: Poultry, Management, Production, Broiler Breeders, Artificial Neural Networks and Artificial Intelligence.