NON-LINEAR MODELING AND ALGORITHM DEVELOPMENT FOR POULTRY HENS
Abstract
Author(s): Bhupendra Sharma and Dr. Subhash Chandra Sikdar
In present study, modeling poultry egg production has been carried out. Seven nonlinear models are evaluated for fitting the average weekly flock poultry egg production. Among the models considered, c ompartmental model due to McMillan et al., 1970, which is a combination of monomolecular and an exponential function is found to be superior. When ANN models are developed for the same data, it is found that ANN model using RBF architecture is found to be better compared to the ANN model based on MLP architecture and further ANN using RBF architecture is better than the best nonlinear model identified for this data.
