ABSTRACT
Udder measures have been used to assess milk yield of sheep through classical methods of estimation. Artificial neural networks (ANN) can deal with complex non-linear relationships between input and output variables. In the current study, ANN were applied to udder measures from Pelibuey ewes to estimate their milk yield and this was compared with linear regression. A total of 357 milk yield records with its corresponding udder measures were used. A supervised learning was used to train and teach the network using a two-layer ANN with seven hidden structures. The globally convergent algorithm based on the resilient backpropagation was used to calculate ANN. Goodness of fit was evaluated using the mean square prediction error (MSPE), root MSPE (RMSPE), correlation coefficient (r), Bayesian's Information Criterion (BIC), Akaike's Information Criterion (AIC) and accuracy. The 15-15 ANN architecture showed that the best predictive milk yield performance achieved an accuracy of 97.9% and the highest values of r2 (0.93), and the lowest values of MSPE (0.0023), RMSPE (0.04), AIC (- 2088.81) and BIC (- 2069.56). The study revealed that ANN is a powerful tool to estimate milk yield when udder measures are used as input variables and showed better goodness of fit in comparison with classical regression methods.
Subject(s)
Mammary Glands, Animal , Milk , Animals , Bayes Theorem , Female , Linear Models , Neural Networks, Computer , SheepABSTRACT
Methane (CH4) is a greenhouse gas generated during the feed fermentation processes in the rumen. However, numerous studies have been conducted to determine the capacity of plant secondary metabolites to enhance ruminal fermentation and decrease CH4 production, especially those plants rich in tannins. This review conducted a descriptive analysis and meta-analysis of the use of tannin-rich plants in tropical regions to mitigate CH4 production from livestock. The aim of this study was to analyse the effect of tannins supplementation in tropical plants on CH4 production in ruminants using a meta-analytic approach and the effect on microbial population. Sources of heterogeneity were explored using a meta-regression analysis. Final database was integrated by a total of 14 trials. The 'meta' package in R statistical software was used to conduct the meta-analyses. The covariates defined a priori in the current meta-regression were inclusion level, species (sheep, beef cattle, dairy cattle, and cross-bred heifers) and plant. Results showed that supplementation with tropical plants with tannin contents have the greatest effects on CH4 mitigation . A negative relationship was observed between the level of inclusion and CH4 emission (-0.09), which means that the effect of CH4 mitigation is increasing as the level of tannin inclusion is higher. Therefore, less CH4 production will be obtained when supplementing tropical plants in the diet with a high dose of tannins.
ABSTRACT
THE OBJECTIVE OF THIS STUDY WAS TO COMPARE THE GOODNESS OF FIT OF FOUR LACTATION CURVE MODELS: Wood's Gamma model (WD), Wilmink (WL), and Pollott's multiplicative two (POL2) and three parameters (POL3) and to determine the environmental factors affecting the complete lactation curve of F1 dairy sheep under organic management. A total of 5,382 weekly milk yields records from 150 ewes, under organic management were used. Residual mean square (RMS), determination coefficients (R(2)), and correlation (r) analysis were used as an indicator of goodness of fit for each model. WL model best fitted the lactation curves as indicated by the lower RMS values (0.019), followed by WD (0.023), POL2 (0.025) and POL3 (0.029). The four models provided total milk yield (TMY) estimations that were highly correlated (0.93 to 0.97) with observed TMY (89.9 kg). The four models under estimated peak yield (PY), whereas POL2 and POL3 gave nearer peak time lactation estimations. Ewes lambing in autumn had higher TMY and showed a typical curve shape. Higher TMY were recorded in second and third lambing. Season of lambing, number of lambing and type of lambing had a great influenced over TMY shaping the complete lactation curve of F1 dairy sheep. In general terms WL model showed the best fit to the F1 dairy sheep lactation curve under organic management.
