Modeling of growth in Lohmann LSL pullets with neural networks and nonlinear regression models

Journal Title: Revista MVZ Cordoba - Year 2013, Vol 18, Issue 3

Abstract

Objective. Modeling the pullet growth curve of the Lohmann LSL line, by using nonlinear model (MNL), nonlinear mixed model (MNLM) and artificial neural networks (ANN). Materials and methods. An average of 33 birds, were weighed from day 21 to 196 of life for 558 individual weight records. To adjust the growth curve the following models were used: nonlinear Von Bertalanffy (MNL), nonlinear mixed Von Bertalanffy (MNLM) and artificial neural networks (RNA). The models were compared with a correlation coefficient and precision measurements: mean square error (MSE), Mean Absolute Deviation (MAD) and the mean absolute percentage error (MAPE). Results. Correlation values, between actual and estimated data, were 0.999, 0.990 and 0.986 for MNLM, RNA and MNL respectively. The most accurate model based on the MAPE, MAD and CME criteria was MNLM followed by RNA. The prediction graph for RNA was similar to MNLM. The RNA performance was higher than MLN. Conclusions. The best model for the prediction of growth curves of commercial Lohmman LSL birds to 196 days of age, was the MNLM, with multiple measurements per animal at the time. RNA performance was higher MLN.

Authors and Affiliations

Luis Galeano-Vasco, M. Sc *| Universidad de Antioquia, Facultad de Ciencias Agrarias, Grupo investigación Genética, Mejoramiento y Modelación Animal, A.A. 1226, Medellín, Colombia.Correspondencia: lf.galeano.vasco@gmail.com, Mario Cerón-Muñoz, Ph. D| Universidad de Antioquia, Facultad de Ciencias Agrarias, Grupo investigación Genética, Mejoramiento y Modelación Animal, A.A. 1226, Medellín, Colombia.

Keywords

Related Articles

Lymph nodes extramedullary plasmacytoma in a dog

Extramedullary plasmacytoma is a tumor mass composed of plasma cells distant from the bone marrow, classified as skin tumor and is not often present in dogs. The veterinary center ZOOGAR received a canine patient, male,...

Productive performance of hair lambs, fed with fresh lemon pulp as an energy source

Objective. Evaluate the effect of the inclusion of different levels of fresh lemon pulp (FLP) was determined as a substitute of sorghum grain in the feeding of hair sheep in parameters of daily weight gain (DWG), daily f...

Efect of three types of live preys on larviculture of the trans-andean shovelnose catfish (Sorubim cuspicaudus)

Objective. Assess the effect of different live prey in the larviculture of Trans-andean shovelnose catfish (Sorubim cuspicaudus). Materials and methods. At the beginning of exogenous feeding, zooplankton produced in meso...

Swine Carcass Condemnation in Commercial Slaughterhouses

Objective. The research was conducted to evaluate the main causes of carcass condemnation, as well as the financial loss caused by it, at a commercial slaughterhouse located in Dourados, MS, Brazil. Materials and methods...

Neospora caninum infection in beef cattle reared under grazing conditions in north-central Mexico

Objetive. To determine the seroprevalence of N. caninum antibodies and prevalence of parasite DNA in blood, and estimate the association between seroprevalence and the potential risk of some factors in beef cattle under...

Download PDF file
  • EP ID EP3335
  • DOI -
  • Views 395
  • Downloads 18

How To Cite

M. Sc *, Ph. D (2013). Modeling of growth in Lohmann LSL pullets with neural networks and nonlinear regression models. Revista MVZ Cordoba, 18(3), 3861-3867. https://europub.co.uk/articles/-A-3335