Aprendizaje automático y PYMES: Oportunidades para el mejoramiento del proceso de toma de decisiones

Objective: To design and develop a continuous simulation model based on System Dynamics to analyze reproductive parameters considering artificial insemination and reproductive policies aimed at sustainability in a dairy herd. Methodology: The procedure is classified into four stages: (I) Analysis of the behavior of the dairy herd and definition of the problem, (II) Description of processes and contextualization of a model, (III) Generation of the preliminary model, verification, validation and (IV) Analysis of results. Results: It was shown that using simulation tools it is possible to model the processes within the dairy herd. The effective detections of periods of heat constitute a determining factor in the application of policies of artificial insemination and in general in the sustainability of the herd. Therefore, using a reproductive biotechnology protocol, such as heat synchronization and fixed-term artificial insemination, are policies that mitigate the problems associated with reproductive problems. Conclusions: The use of system dynamics allowed us to have a holistic approach to the problem considering all the relevant variables to evaluate improvement policies. The model presented in the development of the research allowed evaluating different policies associated with animal management, meat exploitation in dry cows, and policies of continuous review on situations associated with the efficiency in the identification of cows in heat.

Section: Resultsmentioning

confidence: 99%

A system dynamics approach for dairy herd modeling considering fixed-term artificial insemination scenario

Ceballos²,

Sánchez-Torres³

2022

“…This is normally in the range of 10-20. The literature presents various applications associated with multivariate regression methods [13,14,15,16,17], however, this work in particular focuses on the analysis of three of the magnitudes of greatest application at the industrial level: temperature, pressure and mass.…”

Section: Mean Squared Deviation In the Calibration Of Measuring Instr...mentioning

confidence: 99%

Application of the method of ordinary least squares in the calibration of temperature, pressure and mass meters

Vásquez

Yepes²,

Galvis³

et al. 2023

The goal of this paper is applied the Ordinary Least Squares (OLS) method as a strategy in order to reduce the uncertainty measurement associated to the relevant physical quantities. Methodology or method: This work was motivated due to the efforts made in the measurement sciences to investigate alternative methods that allow obtaining greater metrological reliability of the results, that is, reducing the uncertainty associated with the measurement. Thus, the applied methodology consisted of the development of a computational code using the MatLab tool, in which an algorithm was programmed that supports the application of the OLS method. Three of the most used physical magnitudes at an industrial level were evaluated: temperature, pressure and mass. These magnitudes were evaluated from the calibration of three measuring instruments: thermistor, manometer and digital scale. Results: The applied methodology allowed to: (i) obtain the matrix of the coefficients for polynomials of degrees 1, 2, 3 and 4 that adjust the experimental data; (ii) to draw the calibration curves for each of the obtained polynomials and (iii) to estimate the fit uncertainty (i.e.: the mean squared deviation) to specify the polynomial that best models the experimental data for a reliability level of 95.45 % (k = 2). The consolidated results confirmed a reduction in the uncertainty associated with the adjustment polynomial of 99.8% for the temperature measurement, 45.6% for the pressure measurement and 53.9% for the mass measurement. Conclusions: Finally, a discussion of the results is presented, confirming the effectiveness of the ordinary least squares method as a strategy to reduce the uncertainty associated with the calibration of measuring instruments.

“…Además se utilizó este método, ya que no era posible asignar de manera aleatoria los individuos al grupo experimental (aquel que se expone al cuasiexperimento) y el grupo de control (aquel que se utiliza para hacer comparaciones entre las mediciones [19]). En el diseño experimental se realizó un cuasi-experimento en una organización en Colombia (cuyos datos específicos son confidenciales como éticas en experimentación [20]) con un sistema de Mainframe legado.…”

Section: Metodologíaunclassified

Implementación de prácticas DevOps en un Sistema de Mainframe Legado

Villegas

Monsalve²,

Cardona³

et al. 2022

Objetivo: Presentar una experiencia de implementación de prácticas DevOps en un Sistema de Mainframe Legado o SML. Metodología: Se usó una investigación cuasi experimental, la cual se caracterizó por presentar como grupo de control el proceso de despliegue manual dentro de una organización y como grupo experimental una propuesta de automatización de ciertos puntos del proceso. La metodología para este tipo de investigación permitió observar el comportamiento de ambos procesos, registrar datos y realizar análisis cuantitativo de las variables observadas, entre ellas: el tiempo de despliegue, la frecuencia de despliegue, el tiempo para restaurar, la disponibilidad, la calidad de los entregables y el volumen de cambios. Resultados: La implementación de prácticas DevOps en un SML evidenciaron mejoras en las capacidades de TI de la organización, se logró generar mayor velocidad en los despliegues, detección temprana de errores, trazabilidad y control en ambientes de desarrollo y pruebas. Conclusiones: El presente articulo mostró que es posible implementar prácticas DevOps en un SML, dichas prácticas emergen como una nueva posibilidad en la mantenibilidad de este tipo de sistemas. DevOps es una promesa que se debe abordar analizando los procesos neurálgicos, midiendo las capacidades y generando cultura en los equipos de desarrollo.