For years, effort has been devoted to establishing an effective bull breeding soundness evaluation procedure; usual research on the subject is based on BBSE (Bull Breeding Soundness Examination) methodologies, which have significant limitations in terms of their evaluation procedure, such as high cost, time-consuming and administratively difficult. This research focuses on the creation of a prediction model to supplement and/or improve the BBSE approach, through the study of two algorithms, Clustering and Artificial Neural Network (ANN), to find the optimum Machine Learning (ML) approach for our application, with an emphasis on data categorization accuracy. The tool is designed to assist veterinary medicine and farmers in identifying key factors and increasing certainty in their decision-making during the selection of bulls for breeding purposes, providing data from a limited number of factors generated from a deep pairing study of bulls. Zebu Bulls, European Bulls, and Crossbred Bulls were the general groupings. The data utilized in the model's creation (N =359) considers five variables that influence improvement decisions. This approach enhances decision-making by 12%. ANN obtained an accuracy of 90%; Precision was 97% for satisfying, 92% for unsatisfying, and 85% for Bad.

[Objetive] The objective of the present study was to characterize different sperm subpopulations based on morphometric parameters of frozen-thawed semen in two bovine subspecies using a CASA system. [Methodology] The experiment was carried out at the Costa Rica Institute of Technology from May to December 2023. Spermatozoa from 10 bulls (five animals of each species Bos taurus and Bos indicus) were evaluated after thawing of the semen doses by an ISAS^®v1, computer-assisted sperm analysis (CASA)-Morph system. Sub-populations of head morphometric spermatozoa were characterized using multivariate procedures such as principal components (PCs) analysis and clustering methods (k-means model) [Results] The ejaculate of male exhibits significant heterogeneity and comprises diverse sperm subpopulations with differing morphometric patterns. Three different sperm subpopulations were identified from three PCs: t head size, head shape, and symmetry of the sperm head and the degree to which it was pyriform. The proportions of the different sperm subpopulations varied in the two-bovine subspecies; Bos taurus and Bos indicus. Results indicated that subpopulations SP1, SP2, and SP3 were different for PC criteria and these differences were relevant. The variability in sperm morphometry assessments underscores the need to standardize semen evaluation protocols [Conclusions] These findings highlight the importance of knowing the diversity in sperm morphometry between subspecies to both improve in vitro evaluation tests and to distinguish subspecies.

The agronomic characteristics of Cenchrus purpureus were assessed through a randomized block experimental design with seven accessions (Taiwan grass, King grass, Elephant grass, Merkeron, CT-115, Purpule grass and Maralfalfa) as treatments and four replications research was carried out at the Instituto Tecnológico Superior de Tantoyuca, in 2019 and 2020, under rainfed conditions. Sowing density was established at 36 tillers in 25 m2. Green and dry matter yield, daily rates of dry matter accumulation in leaves, leaf/stem ratio, height, leaf area index and cutting frequency were assessed. Rainfall amount, temperature, relative humidity and global radiation levels were recorded to assess their effect on the evaluated variables. One-way ANOVA and multivariate analysis techniques, such as multiple linear regression (MLR), Clustering, and Principal component analysis (PCA) with the Statistica V7 software, were used. The leaf area index was greatest (p < 0.05) on the dry season. Green and dry matter yield were greatest in Maralfalfa (p < 0.05). Variation in the results is attributed to weather phenomena; nonetheless, Elephant grass and Maralfalfa showed the highest yields. Quality parameters must be evaluated to identify those grasses with the best attributes.