RESUMO

The objective of this study was to characterize calvings with low and high difficulty based on the productive and reproductive performance of dairy cows. Calvings were grouped in no calving assistance, calving with low assistance, and calving with high assistance. The original data set comprised 1,902 calving records obtained from a large dairy farm in Southeast Brazil. Factor analysis was applied using the SAS® Studio 3.8 statistical program through the factor procedure, considering the Multivariate Analysis category. Milk fat (0.92-0.79) and total solids (0.91-0.80) were strongly correlated with Factor 1. Calving interval (0.87- 0.68) and the number of AI (artificial inseminations) per conception (0.87-0.71) showed high correlations with Factor 2. Milk yield (0.84-0.76) and accumulated milk yield (0.84-0.77) were strongly correlated with Factor 3. Based on the results, we conclude that the three calving scenarios were characterized by well-defined and independent factors. Cows which required a high assistance at calving showed a lower variance explained by the model for milk fat and total solids contents, calving interval, and the number of AIs per conception.

O objetivo deste estudo foi caracterizar os partos com leve ou severa dificuldade e diferenciá-los com base no desempenho produtivo e reprodutivo de vacas leiteiras. Os partos foram agrupados em partos sem assistência, partos com baixa assistência e partos com elevada assistência. O banco de dados original continha 1902 registro de partos que foram obtidos de uma grande fazenda comercial localizada no Sudeste do Brasil. A análise fatorial foi aplicada através do programa estatístico SAS® Studio 3.8 por meio de procedimento fatorial, considerando a categoria de análise multivariada. Os teores de gordura do leite (0,92- 0,79) e de sólidos totais (0,91-0,80) foram altamente correlacionados com o fator 1. Intervalo entre partos (0,87-0,68) e número de IA (inseminações artificiais) por concepção (0,87-0,71) apresentaram alta correlação com o fator 2. Produção de leite (0,84-0,76) e produção acumulada de leite (0,84-0,77) foram altamente correlacionados com o fator 3. Baseados nos resultados, é possível concluir que as três situações de parto foram caracterizadas por fatores independentes e bem definidos. Vacas que necessitaram de alta assistência ao parto apresentaram menor variância explicada pelo modelo para teores de gordura e sólidos totais do leite, intervalo entre partos e número de IA por concepção.

Assuntos

RESUMO

Vegetables are important in economic, social, and nutritional matters in both the Brazilian and international scenes. Hence, some researches have been carried out in order to encourage the production and consumption of different species such as nonconventional vegetables. These vegetables have an added value because of their nutritional quality and nostalgic appeal due to the reintroduction of these species. For this reason, this article proposes the use of the machine learning technique in the construction of models for supervised classification and identification in an experiment with five leafy special of nonconventional vegetables (Tropaeolum majus, Rumex acetosa, Stachys byzantina, Lactuca cf. indica e Pereskia aculeata) assessing the characteristics of the macro and micro nutrients. In order to evaluate the classifiers' performance, the cross-validation procedure via Monte Carlo simulation was considered to confirm the model. In ten replications, the success and error rates were obtained, considering the false positive and false negative rates, sensibility, and accuracy of the classification method. Thus, it was concluded that the use of machine learning is viable because it allows the classification and identification of nonconventional vegetables using few nutritional attributes and obtaining a success rate of over 89% in most of the classifiers tested.

Assuntos