Application of Machine Learning Algorithms to Describe the Characteristics of Dairy Sheep Lactation Curves.

In recent years, machine learning (ML) algorithms have emerged as powerful tools for predicting and modeling complex data. Therefore, the aim of this study was to evaluate the prediction ability of different ML algorithms and a traditional empirical model to estimate the parameters of lactation curves. A total of 1186 monthly records from 156 sheep lactations were used. The model development process involved training and testing models using ML algorithms. In addition to these algorithms, lactation curves were also fitted using the Wood model. The goodness of fit was assessed using correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and relative root mean square error (RRSE). SMOreg was the algorithm with the best estimates of the characteristics of the sheep lactation curve, with higher values of r compared to the Wood model (0.96 vs. 0.68) for the total milk yield. The results of the current study showed that ML algorithms are able to adequately predict the characteristics of the lactation curve, using a relatively small number of input data. Some ML algorithms provide an interpretable architecture, which is useful for decision-making at the farm level to maximize the use of available information.

Estimation of body weight in hair ewes using an indirect measurement method.

The aim of the present study was to develop and evaluate an equation to predict body weight (BW) using hip width (HW) in Pelibuey ewe lambs and ewes. Five hundred seventy-seven 2-month-old to 3-year-old, non-pregnant, non-lactating, clinically healthy ewe lambs and adult ewes with a mean BW of 34.7 ± 12.4 kg and HW of 15.6 ± 3.4 cm were considered. Three equations were evaluated: BW (kg): - 19.17 + 3.46 × HW (Eq. 1), BW (kg): - 17.79 + 3.25 × HW + 0.007 × HW2 (Eq. 2) and BW (kg): 0.39 × HW1.63 (Eq. 3). Independent data from 80 animals with similar characteristics (BW of 23.4 ± 10.9 kg and HW of 12 ± 3.1 cm) were also considered to evaluate the developed equations. The evaluation was based on the relationship between the observed and predicted values of BW analysed using a linear regression, the mean squared error of prediction (MSEP), the root MSEP (RMSEP) and the concordance correlation coefficients (CCCs). Additionally, cross-validation analyses were performed using the k-folds validation (k = 10) procedure. The correlation coefficient (r) between BW and HW was 0.94 (P < 0.001). The parameters for precision and accuracy showed that the proposed equations had high precision (R2 > 0.95%), accuracy (Cb > 0.98) and reproducibility (CCC > 0.96) in predicting the BW of ewe lambs and adult ewes. Equation (1) accurately predicted observed BW, with a bias (observed - predicted) of 4.3 kg and RMSEP of 9.68% with respect to the observed BW (random error of 84.23%); it also generated the best prediction according to the residual mean squared prediction error, coefficient of determination and mean absolute error. In conclusion, the highly correlated relationship between BW and HW in Pelibuey ewe lambs and adult ewes under humid tropic conditions enabled the development of mathematical models herein to estimate BW with an adequate goodness of fit. The linear model showed the best performance according to the goodness-of-fit evaluation and internal and external validation; hence, this model is proposed for use in both the experimental and commercial farms.

Antioxidant and antibacterial activities of a starch film with bioextracts microencapsulated from cactus fruits (Opuntia oligacantha).

The use of unconventional sources is very relevant in the food area. In the present study the development of active films with the addition of bioextract (BE) or microencapsulated bioextract (MBE) from xoconostle (Opuntia oligacantha) on chayotextle starch was investigated. The film formulations were: 4 g of chayotextle starch, 2 g of glycerol and 180 g of water, three films with BE added (0.4, 0.8 and 1.2 g) and three films with MBE added (0.4, 0.8 and 1.2 g). Total phenols, total flavonoids, antioxidant activity (ABTS and DPPH), Salmonella typhimurium inhibition, color and mechanical properties of the films were analyzed. The film with 1.2 g of MBE showed high concentration of total phenols (54.12 ± 0.77 mg EAG/100 g), total flavonoids (16.65 ± 0.10 mg QE/100 g) and antioxidant activity (29.11 ± 0.48 and 41.42 ± 1.81 mg EAA for ABTS and DPPH respectively). The addition of bioextract from xoconostle is an option for the development of active films with antioxidant properties.

Evaluation of comparative advantages in the profitability and competitiveness of the small-scale dairy system of Tulancingo Valley, Mexico.

This article combines a Policy Analysis Matrix with a sensitivity and poverty line analysis with the objective of evaluating the economic contribution of comparative advantages to the private profitability and competitiveness of small-scale dairy systems. For 1 year, socioeconomic data were collected from 82 farms selected from four strata via statistical sampling. Two scenarios were established to determine the quantitative contribution of comparative advantages: (1) a simulated scenario, which accounted for the cost of purchasing the total food and the opportunity cost of the family labour force (FLF), and (2) an actual production scenario, which accounted for the cost of producing food and eliminating the payment of the FLF and included other income. The E3 and E4 producers were the most profitable and competitive in the simulated scenario and actual production scenario. Of the four scales evaluated, the E2 and E1 producers were the most efficient in taking advantage of the economic contribution provided by the comparative advantages in their own production of food and employment of the FLF, in addition to accounting for other income, a condition that increased their profitability by 171 and 144% and competitiveness by 346 and 273%, respectively. The poverty results indicated that only E3 and E4 producers were non-vulnerable in the simulated scenario and actual production scenario. The purchase of food was the comparative advantage with the greatest sensitivity to cost increases in the two scenarios analysed, which exacerbated the effect on the E1 and E2 producers.