José Ignacio Rodríguez Molano

Exposure to Particulate Matter (PM) is linked to respiratory and cardiovascular diseases, certain types of cancer, and accounts for approximately seven million premature deaths globally. While governments and organizations have implemented various strategies for Air Quality (AQ) such as the deployment of Air Quality Monitoring Networks (AQMN), these networks often suffer from limited spatial coverage and involve high installation and maintenance costs. Consequently, the implementation of networks based on Low-Cost Sensors (LCS) has emerged as a viable alternative. Nevertheless, LCS systems have certain drawbacks, such as lower reading precision, which can be mitigated through specific calibration models and methods. This paper presents the results and conclusions derived from simultaneous PM₁₀ and PM_2.5 monitoring comparisons between LCS nodes and a T640X reference sensor. Additionally, Relative Humidity (RH), temperature, and absorption flow measurements were collected via an Automet meteorological station. The monitoring equipment was installed at the Faculty of Environment of the Universidad Distrital in Bogotá. The LCS calibration process began with data preprocessing, which involved filtering, segmentation, and the application of FastDTW. Subsequently, calibration was performed using a variety of models, including two statistical approaches, three Machine Learning algorithms, and one Deep Learning model. The findings highlight the critical importance of applying FastDTW during preprocessing and the necessity of incorporating RH, temperature, and absorption flow factors to enhance accuracy. Furthermore, the study concludes that Random Forest and XGBoost offered the highest performance among the methods evaluated. While satellites map city-wide patterns and MAX-DOAS enables hourly source attribution, our calibrated LCS network supplies continuous, street-scale data at low CAPEX/OPEX—forming a practical backbone for sustained micro-scale monitoring in Bogotá.

Context: Job sequencing has been approached from a static perspective, without considering the occurrence of unexpected events that might require modifying the schedule, thereby affecting its performance measures. Method: This paper presents the development and application of a genetic algorithm to the Job Shop Rescheduling Problem (JSRP), a reprogramming of the traditional Job Shop Scheduling Problem. This novel approach seeks to repair the schedule in such a way that theoretical models accurately represent real manufacturing environments. Results: The experiments designed to validate the algorithm aim to apply five classes of disruptions that could impact the schedule, evaluating two performance measures. This experiment was concurrently conducted with a genetic algorithm from the literature in order to facilitate the comparison of results. It was observed that the proposed approach outperforms the genetic algorithm 65% of the time, and it provides better stability measures 98% of the time. Conclusions: The proposed algorithm showed favorable outcomes when tested with well-known benchmark instances of the Job Shop Scheduling Problem, and the possibility of enhancing the tool's performance through simulation studies remains open.

Se presenta un trabajo relacionado con la analítica del aprendizaje, la cual consiste en la recopilación y el análisis de datos generados por los estudiantes y sus iteraciones, con el fin de comprender y optimizar el aprendizaje. Se plantea una revisión referencial de los últimos cinco años a través de bases de datos con el fin de identificar aspectos relativos al crecimiento de este enfoque y sus campos de aplicación en la educación superior. El volumen de investigaciones relacionadas va en aumento debido a la necesidad de investigar modelos más acertados de predicción y de nuevos algoritmos dentro del área de la ciencia de datos.

Esta propuesta plantea la selección de variables que influyen en la predicción del rendimiento en estudiantes de ingeniería industrial de la Universidad Distrital (Colombia) por diferentes metodologías: filtro, envoltura e integrados. Se implementaron algoritmos de clasificación a través del lenguaje de programación Python como árbol de decisión, K vecinos más cercanos, perceptrón y otros, los cuales son comparados para conocer el mejor resultado de predicción. El género y el puntaje ICFES (examen de estado en Colombia) para condición matemática se encuentran en el rango superior de todos los métodos de selección de características, y el algoritmo perceptrón arroja mejor exactitud con respecto a los otros algoritmos usados. Se concluye que las variables que más influyen en el rendimiento académico de los estudiantes de ingeniería son: edad, género, puntaje ICFES para aptitud matemática, puntaje global ICFES, valor de matrícula y puntaje ICFES para condición matemática y cohorte.

Introduction: The present article is the result of the investigation and approach to the applications and developments of blockchain and Internet of Things (IoT), developed during the second semester of the year 2019 and first of 2020. Problem: Construction of environments and mediums in a cluster structure that allow companies and institutions to cooperate and compete to achieve efficiency and strengthen grouping. Objective: Integrate blockchain and IoT to develop and present a two-level architecture, from which a support environment is established and a series of functionalities are offered for a cluster implementation. Methodology: Review articles to achieve an approach to blockchain and IoT architecture, configuration and description of structural and functional levels. Results: An architecture with a structural level constituted by a decentralized computer application based on blockchains, a sensory and response network that incorporates IoT technologies and an intermediate component of cloud computing; this, at a functional level that manages to offer users support and help in their activities from modules created with a particular specialty. Conclusion: The structural level furthered the integration of base technologies, blockchain and IoT; on the other hand, the second level of architecture reveals the potential and versatility of these technologies. Originality: Proposal for the implementation of blockchain, IoT and cloud computing in a cluster structure. Limitations: The difficulty of accessing a cluster to perform a test of the architecture in a real environment.

Una organización requiere suministrar bienes y servicios a los clientes, cuándo, cómo y dónde los requieran; ello se logra, por medio de actividades de valor, enmarcadas dentro del proceso logístico. Bajo este contexto surgió la presente investigación, con el propósito de determinar cuáles son los elementos que impulsan el valor en las actividades del proceso logístico de las empresas del sector floricultor del departamento de Cundinamarca. El estudio se tipificó como descriptivo, no experimental y transversal. La información fue recolectada a través de dos cuestionarios, uno para los clientes internos del proceso logístico y otro para los trabajadores del área logística. La confiabilidad se obtuvo a través del método Alfa de Cronbach y los valores resultantes para los cuestionarios aplicados fueron: clientes de 0.797 y trabajadores logísticos de 0.877; los cuales son altamente confiables. Una vez aplicados y analizados los instrumentos, se evidenció que la mayoría de los factores que generan valor en las actividades del proceso logístico son coincidentes entre las poblaciones estudiadas y conservan relación con las bases teóricas utilizadas. Se concluye que el éxito de una organización no solo es consecuencia lógica de realizar bien las acciones operativas de apoyo, sino que además es necesario generar valor en cada actividad de la empresa para satisfacer los requerimientos de los clientes y mantenerlos en el tiempo.

This document describes the implementation and results of the problem-based learning method (ABP), as a strategy that fosters creative skills in students of applied mechanical matter. Initially a theoretical framework is developed associated with the evolution of traditional education towards one that strengthens the competences related to creativity and innovation which are not strongly developed. Subsequently, an approach is made to the problem in a case study (garbage generation in the residential urban area). From which devices are designed that help in the process of recycling and transport to the recyclers of Bogotá. It is proposed, the evolution of the type of traditional teaching currently practiced towards a methodology that allows greater participation and responsibility on the part of the student in their own learning and presenting an opportunity for the development of creative skills. Finally, statistics of the results of this work are presented, where the students state that solving real problems facilitates the assimilation of concepts and fosters their creativity. Results that are contrary to what happened with traditional education: monotony, student disinterest and poor application of concepts. The new strategies help the student to be active in their learning; faces him to acquire skills and attitudes that will be helpful in his profession.