The thermal environment in livestock buildings affects the productive and reproductive performance of animals. Therefore, monitoring thermal environment variables is necessary. This study reviewed the applicability of the electronic device ESP8266 module to monitoring animal production. The ESP8266 module is a microcontroller that enables the collection, storage and transmission of data that influence livestock production. The data collected are transferred to cloud computing systems allowing the development of supervisory systems that can be accessed by smartphones, tablets or computers. With this type of microprocessor, it is possible to develop autonomous management systems for animal production. Connected devices using the internet of things, artificial intelligence, machine learning and blockchain will facilitate the analysis of data from the production chain and the appropriate decision-making. Managers of livestock production systems will be in charge of following up and monitoring the processes.

Computer simulation can provide reliable information about fluid flow behavior, including ventilation, in animal production systems. The ventilation system is essential for thermal conditioning, as it favors animal comfort and enhance productivity. The objective of this study was to develop and validate a CFD (Computational Fluid Dynamics) model to analyze the ventilation system in a compost barn. A mesh with greater refinement was used near the air inlet and outlet and the floor, that is, in these regions the mesh number of cells was larger, which makes a denser mesh. For the validation, data on air velocity were collected in the barn to compare with the results of the simulation. Dead zones of ventilation were identified in the barn, there was an increase in the average air velocity at the air outlet, and temperatures and air velocity were found below the optimal recommended by the literature. However, the adjusted model showed good fit with the values measured, indicating that is a good tool to predict the behavior of air velocity. In addition, the detection of ventilation dead zones inside the barn demonstrates the need for a supplementary ventilation system.

This study resulted from the demand for seeds with physiological qualities and studies in germination tests applied for seed improvement aimed at productive and homogeneous harvests. The objective of this study was to improve the classification of seeds in germination tests by introducing YOLO as a classification tool for germinated or nongerminated seeds to specify the results and optimize the analysis period. Germination tests were performed for Glycine max (soybean) seeds, and the capture of images from the tests and conventional categorization was performed by uncorrelated individuals, for the processing of these images and application to YOLO. Subsequently, graphical analyses of the YOLO results and comparison metrics with conventional categorization were performed to determine the accuracy of YOLO as a seed categorization tool. The results derived from the analysis of the graphs and comparisons to the conventional methodology of seed classification showed the effectiveness of YOLO for classifying seeds as germinated or nongerminated, reaching 95% accuracy in seed classification, beyond the range of 0–0.110 of the prediction errors, determined by the application of the methodology of mean square error, highlighting the efficiency of YOLO.