![]() ![]() Multivariate Adaptive Regression Splines (MARS) data mining algorithm is a non-parametric regression method employed to obtain the prediction of live weight by using body measurements. The implication is that at appropriate ages based on the quadratic models, the production characteristics of Isa Brown layers can be targeted for maximal production. This prediction model revealed that BW, FI, CEN, HDEP, HHEP and EW would attain optimal limits at ages 64.93, 66.67, 53.49, 53.30, 54.23 and 81.28 weeks of laying, respectively. The quadratic model appeared to be better in forecasting performance parameters. With the exception of MTLY (P > 0.05) which was not affected by age, other parameters increased significantly (P < 0.05) with age. Linear and quadratic functions were fitted to predict the performance parameters from age. Where there were significant differences in the means of the seven production parameters based on age, they were separated using Duncan's Multiple Range Test procedure. The effect of age (25, 30, 35, 40, 45, 50, 55, 60, 65 and 70 weeks) on weekly BW, FI, WI, MTLY, CEN, HDEP, HHEP and EW was determined using one-way analysis of variance (ANOVA). Data were collected from 25 to 70 weeks of age. The parameters measured were weekly body weight (BW), feed intake (FI), water intake (WI), number of birds that died (mortality, MTLY), cumulative egg number (CEN) per week, hen-day egg production (HDEP), hen-housed egg production (HHEP) and egg weight (EW). There were three replicates of sixteen cells each containing five birds. A total of two hundred and forty hens on cage were utilized in the study. This study aimed at evaluating the production characteristics of Isa Brown layers in cages and to estimate the age of optimal production using two different regression models. The identification of appropriate models to optimize the performance of layers will help boost poultry production. In conclusion, non-linear models and NN models yielded a good fit with the age-weight data of TADP chickens on-station and on-farm. Based on the goodness-of-fit criteria, Gompertz 3P had the best predictive values (AdjR 2 = 0.989-0.998) for TADP chickens raised on-station, while logistic 3P was the best-fit model for TADP chickens raised on-farm. The AdjR 2 for Gompertz 3P was higher than or equal to the AdjR 2 for logistics 3P, Gompertz 4P and logistics 4P but was equal to or lower than the AdjR 2 for the neural network (NN) for all TADP chickens raised on-station. Parameters used to evaluate the growth models were the adjusted coefficient of determination (AdjR 2), Akaike's information criterion (AIC), Bayesian information criterion (BIC) and root mean square error (RMSE). Data for body weight were collected every 14 days from 1939 birds reared on-station, and every 28 days from 58,639 birds reared on-farm. In this study, we evaluated the ability of five mathematical models (3P and 4P Gompertz, 3P and 4P logistic and neural network) to predict the growth of six tropically adapted dual purpose (TADP) chicken breeds (Fulani, FUNAAB Alpha, Kuroiler, Noiler, Sasso and Shika-Brown) under on-station and on-farm in Nigeria. 2021) Comparison of five mathematical models that describe growth in tropically adapted dual-purpose breeds of chicken, ABSTRACT Mathematical models provide valuable information for livestock improvement programmes. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |