Pregrado Ingeniería Electrónica

URI permanente para esta colecciónhttp://hdl.handle.net/11634/205

Examinar

Mostrando 1 - 20 de 549

Implementación de un prototipo de sistema electrónico de detección de contactos y registro de tiempos como coporte en la determinación de faltas en el circuito de agility canino
(Universidad Santo Tomás, 2026-08-12) Mahecha Pérez, Heidy Nicoll; Gálvez Lizarazo , Oscar Mauricio; Higuera Castro , Gustavo Adolfo; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001342623; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000742198; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0002434240; https://scholar.google.com/citations?user=XOhDruwAAAAJ&hl=es&oi=ao; https://orcid.org/0000-0001-6858-5293; https://orcid.org/0000-0001-5945-4312; https://orcid.org/0009-0006-5387-5793
This thesis project aims to design, develop, and implement an electronic system prototype for automated contact detection and timekeeping in canine agility courses, serving as a support tool for officiating in official competitions and training sessions. The system minimizes the margin of error associated with human visual judgment by incorporating sensing technologies and embedded processing. The proposed solution involves implementing a network of piezoresistive sensors made from Velostat material; this allows for the detection of variations in surface pressure exerted by dogs as they traverse specific contact zones on obstacles, in accordance with international regulations. Concurrently, a timing system based on HC-SR04 ultrasonic sensors is integrated to start and stop the course timer automatically with an accuracy of less than 5 ms. Both systems connect to a processing unit based on an ESP32 microcontroller, which handles signal acquisition, conditioning, and real-time data transmission. The collected data is sent to a dedicated web platform that displays course times and records whether each participant made contact with the obstacles. This interface is designed for use by judges, trainers, and the general public. The prototype was validated in a controlled environment simulating an agility competition, evaluating parameters such as timing accuracy, Velostat sensor detection sensitivity, processing latency, and inter-module communication stability. The results demonstrate favorable performance compared to traditional methods, offering a low-cost, scalable system. This proposal contributes to the development of sports technology tools, promotes transparency in decision-making during competitions, and represents a step forward in the digital transformation of officiating in canine agility.
Pronóstico del precio diario de bolsa en el mercado eléctrico colombiano usando modelos autorregresivos.
(Universidad Santo Tomás, 2026-07-23) Becerra Pulido, Juan David; Garrido Silva, Gianina; Ramírez Murillo, Harrynson; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001538476; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001614550; https://scholar.google.com/citations?user=kFV2TV0AAAAJ&hl=es&oi=ao; https://scholar.google.com/citations?user=ou83QTIAAAAJ&hl=es&oi=ao; https://orcid.org/0000-0002-6607-9626; https://orcid.org/0000-0002-3474-4783
The Colombian Wholesale Electricity Market (MEM) exhibits highly dynamic price behavior due to the interaction of operational, hydrological, and demand-related factors, making accurate forecasting a challenging task using conventional methods. This research developed a forecasting model based on autoregressive techniques by implementing a Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) model to simultaneously capture the temporal dependence of electricity prices and the influence of relevant external variables. The proposed methodology included data acquisition from the Colombian Mining and Energy Information System (SIMEM), exploratory time-series analysis, data preprocessing through outlier treatment, statistical transformations, standardization, lag generation, and feature selection. Subsequently, AR, ARX, SARIMA, and SARIMAX models were implemented and compared using MAE, MSE, and RMSE performance metrics, while the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) were employed to identify the most appropriate model structure. The results demonstrated that incorporating exogenous variables, including electricity demand, hydroelectric participation, and reservoir storage levels, significantly improves forecasting performance compared to purely autoregressive approaches. The SARIMAX model achieved the best predictive performance, reducing the RMSE by 18.5% and the MAE by 14.2% relative to the baseline model while maintaining stable behavior during validation. Furthermore, the sensitivity analysis identified electricity demand as the most influential predictor, followed by hydroelectric participation and reservoir storage. Overall, the obtained results confirm that autoregressive models with exogenous variables provide an effective and interpretable approach for forecasting electricity market prices in Colombia, supporting operational planning, market analysis, and decision-making within the National Interconnected System.
Bogotá’s traffic prediction system using graph neural networks
(Universidad Santo Tomás, 2025-05) García Pérez, Juan Camilo; Martínez Vasquez, David Alejandro; Mateus Rojas , Armando; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001560096; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000680630; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001816224; https://scholar.google.com/citations?user=U5Qf1nUAAAAJ&hl=es&oi=ao; https://scholar.google.com/citations?user=1az5o_IAAAAJ&hl=es&oi=ao; https://scholar.google.com/citations?user=vNvgsOwAAAAJ&hl=es&oi=ao; https://orcid.org/0000-0001-9750-2653; https://orcid.org/0000-0002-2399-4859; https://orcid.org/0000-0001-6973-9477
Vehicle congestion in urban areas like Bogotá represents a significant challenge affecting citizens’ quality of life, economic efficiency, and the environment. Long commute times, air pollution, and traffic-related stress are pressing issues requiring innovative solutions to promote sustainable urban mobility. While methodologies exist to address these problems, they often fail to capture the inherent complexity of urban environments, particularly the inter connected factors of traffic flow and population density.
Implementación de un prototipo de control de nivel y caudal de agua con monitoreo de variables para el modelo a escala 1:50 de la planta existente en la finca San José del Municipio de Cota
(Universidad Santo Tomás, 2026-06-30) Diaz Camacho, David Santiago; Gelvez Lizarazo, Oscar Mauricio; Torres Pinzón, Carlos Andrés; Bejarano Rodríguez, Mayra Alejandra; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001342623; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000692670; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0002434249; https://scholar.google.com/citations?user=XOhDruwAAAAJ&hl=es&oi=ao; https://scholar.google.com/citations?user=ca0gXCgAAAAJ&hl=es&oi=ao; https://orcid.org/0000-0001-6858-5293; https://orcid.org/0000-0003-0367-8143; https://orcid.org/0009-0006-5082-6865
The project focuses on the pressing issue faced in areas where water supply is a daily challenge due to time and travel constraints between communities. Its core approach is the facilitation of informed decision-making through the acquisition and visualization of data related to storage and distribution. Consequently, the technical solution involves the implementation of a scaled-down prototype that features a data acquisition system. This system utilizes sensors for measuring the process's critical variables—primarily level and flow rate—while integrating a communication protocol, a user interface (UI), and the control of various actuators. The results obtained demonstrate that the quality of the controller’s response does not strongly depend on the simulated mathematical model. In contrast, the response of the prototype is limited by the accuracy of the sensors used to record the measurements of the controlled variable. Finally, it is verified that a future implementation of the system could be carried out at the San José farm, considering sensors and actuators appropriate to the scale of the installation.
Diseño y fabricación de un baño termostático de líquido para la calibración de termómetros en rangos de baja y alta temperatura
(Universidad Santo Tomás, 2026-07-04) Parra Florez, Julian; Camacho Parra, Cristian; Chaparro Becerra, Willian; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001713601; https://scholar.google.es/citations?user=Z7wSIokAAAAJ&hl=es; https://orcid.org/0000-0001-5470-700X
In the field of biomedicine, equipment calibration is essential to guarantee the reliability of medical devices. This process involves verifying and regulating their accuracy, ensuring that the values obtained are as close to reality as possible and allowing for correct diagnoses and safe treatments for patients. Currently, Clinical Solutions SAS lacks a means to perform precise thermometer calibration, especially when temperatures below 0 °C or high and stable temperatures are required. Therefore, the purpose of this project is to provide the company with a simple and intuitive way to perform precise calibration of thermometers at both low and high temperatures using standard temperature measurement equipment. This project focuses on designing, programming, and implementing a low- and high-temperature thermostatic bath for thermometer calibration. To achieve the desired temperature ranges, a compression system and a heating device are used, all managed by a microcontroller. The microcontroller also allows for wired connection, monitoring, and control of the thermostatic bath. The project is expected to offer high precision and meet the minimum standards for thermometer calibration, maintaining stability at the user-requested temperature while providing useful and reliable data for calibration purposes.
Estudio Técnico Comparativo para la Selección de Equipos y Arquitecturas de Ciberseguridad IT/OT en EBSA, Basado en las Normas IEC62443 e IEC62351
(Universidad Santo Tomás, 2026-06-23) Barón Arias, Juan Pablo; Chaparro Becerra, William Fabián; Salazar Madrigal, Angélica María; Camacho Parra, Cristian David; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001680448
The digital transformation of the electric power sector has accelerated the convergence of Information Technology (IT) and Operational Technology (OT), improving operational efficiency while increasing the exposure of critical infrastructures to cyber threats. In this context, this research presents a comparative technical study for the selection of cybersecurity equipment and architectures applicable to IT/OT environments, based on the guidelines established by IEC 62443 and IEC 62351 standards. The proposed methodology was structured into five sequential phases: documentary review and regulatory analysis, conceptual characterization of IT and OT environments, definition of technical evaluation criteria, comparative assessment of cybersecurity alternatives, and the proposal of a reference architecture validated through a simulated environment using GNS3. The study identified critical assets and information flows within a typical electrical distribution substation, developed a weighted evaluation matrix based on technical, operational, and feasibility criteria, and analyzed representative cybersecurity solutions without prioritizing specific vendors. The results demonstrate that network segmentation, access control, and secure communications are fundamental mechanisms for reducing the cyberattack surface in electrical infrastructures. Furthermore, the proposed reference architecture provides a technical framework aligned with the defense-in-depth principles of IEC 62443 and the communication security mechanisms defined in IEC 62351, supporting informed decision-making for the progressive implementation of cybersecurity strategies in electric utilities such as Empresa de Energía de Boyacá (EBSA).
Soporte documental del proceso de pasantía y trazabilidad técnica del levantamiento, validación y gestión de inventario de infraestructura de seguridad electrónica
(Universidad Santo Tomás, 2026-06-22) Rodríguez Avella, Juan Sebastián; Gutiérrez Cáceres, Edgar Andrés; Salazar, Angélica María; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000702919; https://scholar.google.es/citations?hl=es&user=DT5Iu_YAAAAJ&view_op=list_works&authuser=2&gmla=AJsN-F7Lf3UKeGIds0NbwKU_wrFOQYB0kq92Sy8cOMxDrpsOm9eVgEz3IgkwasfaNXGx8T6pHdIqSHOgOsvFE9N9pi31Gm4aUf6DSWTz2q_oKaURJtV-dug; https://orcid.org/0000-0001-6729-7353
This document presents the technical and documentary development associated with the internship process, focused on the survey, validation, organization, and updating of the inventory of electronic security infrastructure across different institutional sites. In this context, it includes field verification activities, information review and correction, updating of technical records, plan standardization, and evidence consolidation, with the purpose of building a more reliable, organized, and traceable information base for consultation, control, and analysis processes. Additionally, the logbook includes other operational and support activities carried out during the same period, including incident response, technical validations, follow-up of related systems, and infrastructure support tasks. It also incorporates a complementary human talent management module associated with infrastructure operation and maintenance, based on biometric attendance control. This module complements the main project by linking the management of technological assets with the monitoring of the personnel involved in their supervision, support, and administration. Overall, the document provides a structured view of the work performed, highlighting its methodological approach, the technical traceability applied, and the results obtained during the internship.
Desarrollo e Implementación de Algoritmos de Visión Artificial en Plataforma Robótica para Tareas Pick and Place
(Universidad Santo Tomás, 2026-06-23) Moreno Daza, Ángel Esteban; Lasprilla Fernández, Marco Antonio; Gutiérrez Cáceres, Edgar Andrés; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000702919; https://scholar.google.es/citations?hl=es&user=DT5Iu_YAAAAJ&view_op=list_works&authuser=2&gmla=AJsN-F7Lf3UKeGIds0NbwKU_wrFOQYB0kq92Sy8cOMxDrpsOm9eVgEz3IgkwasfaNXGx8T6pHdIqSHOgOsvFE9N9pi31Gm4aUf6DSWTz2q_oKaURJtV-dug; https://orcid.org/0000-0001-6729-7353
This thesis proposes the development of a robotic Pick and Place system that integrates computer vision in a three-dimensional environment, using the WLKATA Mirobot 6-axis robotic arm and the Intel RealSense D435i camera. Since the automation of object manipulation tasks is a major focus in modern industry, this work aims to improve the optimization, precision, and safety of such processes. Therefore, the project addresses the implementation of intelligent robotic systems capable of identifying, locating, and autonomously manipulating objects, contributing to the advancement of applied robotics. The project includes the implementation of a real-time 3D perception system supported by an object detection model based on YOLOv8 using the Intel RealSense D435i camera. This perception layer supports motion planning and kinematic control of the WLKATA Mirobot 6-axis arm to perform Pick and Place operations accurately and in coordination. An NVIDIA Jetson Orin Nano board is used as the system core to i
Monitoreo Autónomo de Paneles Solares Mediante Dron Parrot Anafi Thermal y Visión Artificial
(Universidad Santo Tomás, 2026-06-23) Paez Benitez, Daniel Sebastian; Riaño Pérez, Juan Camilo; Gutiérrez Cáceres, Edgar Andrés; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000702919; https://scholar.google.com/citations?user=DT5Iu_YAAAAJ&hl=en; https://orcid.org/0000-0001-6729-7353
This project proposes the design and implementation of an autonomous thermal inspection system for the evaluation of photovoltaic panels using a Parrot ANAFI Thermal drone. The system will execute preprogrammed flight paths from a ground control station and will acquire synchronized RGB and radiometric thermal images in order to identify hotspots associated with operational faults and maintenance needs. Mission control will be developed in Python through the integration of the Parrot Olympe SDK with a ROS 2–based architecture, enabling reliable flight control and data acquisition. Anomaly detection will be addressed using computer vision techniques oriented toward thermal image analysis. As a result, a graphical user interface will be provided for mission monitoring and the review of detected findings. The project aims to reduce inspection time, improve operational safety, and provide objective evidence to support predictive maintenance activities. The present document is organized into six main chapters. Chapter 1 presents the project introduction, including the problem statement, objectives, and the general methodological approach. Chapter 2 develops the state of the art and the technological surveillance analysis. Chapter 3 describes the architecture and operation of the developed system, along with a general guide for its execution and the testing activities performed. Chapter 4 presents the obtained results and their discussion. Chapter 5 presents the operational integration within the graphical user interface, including visualization, configuration, and system management functions. Finally, Chapter 6 outlines the conclusions and recommendations derived from the work.
Gestión de intermitencia en la generación fotovoltaica mediante microrred con mecanismo power to heat y drs del laboratorio de energías renovables de la USTA
(Universidad Santo Tomás, 2026-04-28) Sánchez Torres, Glenda Victoria; Beltrán Salgado, Santiago; Paternina Durán, José Luis; Mojica Casallas, Carlos Javier; Gélvez Lizarazo, Óscar Mauricio; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001652171; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000639214; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001342623; https://scholar.google.com/citations?user=VEsFa94AAAAJ&hl=es&oi=ao; https://scholar.google.com/citations?user=XOhDruwAAAAJ&hl=es&oi=ao; https://orcid.org/0000-0001-8138-9588; https://orcid.org/0000-0002-3757-9410; https://orcid.org/0000-0001-6858-5293
This document presents the implementation of an experimental microgrid aimed at managing solar photovoltaic energy through Power-to-Heat (PtH) mechanisms and the use of distributed energy resources (DERs) available in the Renewable Energy Laboratory at Universidad Santo Tomás. The purpose of this work is to design a system that enables the utilization of variable photovoltaic generation through coupling with controlled thermal loads, contributing to the flexibility and efficiency of the energy system. In the development of this research, the main mathematical modeling techniques used for the characterization of PtH technologies are identified based on a specialized literature review. Subsequently, the mathematical model of the electric furnace available in the laboratory is selected and validated through experimental tests, allowing the representation of its thermal behavior and energy storage capacity. Finally, a microgrid is implemented integrating the furnace as a flexible thermal load for the management of photovoltaic generation, together with a set of solar panels, an inverter, complementary electrical loads, and a network analyzer. Communication between devices is carried out through the Modbus RS-485 protocol, managed by an embedded system based on the Raspberry Pi Pico 2. The results demonstrate that the application of the Power-to-Heat mechanism allows for better utilization of the available photovoltaic energy, reducing dependence on the electrical grid and improving self-consumption and self-sufficiency indices. Likewise, it is shown that the proper thermal programming of the furnace contributes to mitigating solar generation intermittency, leading to a more efficient use of the system.
Arquitectura multi-agente descentralizada para detección de eventos en el ambiente
(Universidad Santo Tomás, 2026-04-20) Castaño Ortiz, Daniel Fernando; Martínez Vásquez, David Alejandro; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001560096; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0002173917; https://scholar.google.com/citations?user=U5Qf1nUAAAAJ&hl=es&oi=ao; https://orcid.org/0000-0001-9750-2653; https://orcid.org/0009-0003-2216-0937
Environmental event detection is a key challenge in modern robotics, particularly in systems that require autonomy, cooperation, and distributed decision-making. Decentralized multi-agent systems (MAS) emerge as anefficient alternative to centralized approaches, offering greater scalability, robustness, and fault tolerance. This work proposes the design and implementation of a decentralized multi-agent architecture based on ROS 2 for environmental event detection, using TurtleBot3 Burger mobile platforms and deep reinforcement learning. The research followed an experimental and applied approach, structured into three phases: (1) analysis and selection of physical variables, algorithms, and robotic platform; (2) development of the decentralized architecture integrating a leader agent trained through the Deep Q-Learning (DQN) algorithm and follower agents controlled by the ROBOTIS Follower algorithm; and (3) system validation in the Gazebo simulator using the ROS2middleware for inter-node communication and independent namespace management for each robot. Over 1000 training episodes, the leader agent showed a progressive improvement in cumulative rewards, achieving stable learning and autonomous navigation without collisions. In the multi-agent simulation, the follower robots accurately replicated the leader’s trajectory, maintaining stable formations and effective communication. Finally, physical tests confirmed the successful transfer of the trained model, maintaining consistency with the simulated behaviors. The results confirm that combining deep reinforcement learning with a decentralized ROS 2-based architecture is a viable strategy for developing cooperative behaviors in mobile robotics. The designed system reduces the dependence on a central controller, enhances scalability, and establishes a solid foundation for future validations in more complex physical environments.
Diseño e ingeniería de una red FTTH como medio de comunicación para redes Smart Grids o redes eléctricas inteligentes en el sistema de distribución de la EBSA zona Puerto Boyacá
(Universidad Santo Tomás, 2026-03-26) Roa Avila, Astrid Lorena; Camacho Parra, Cristian David; Salazar Madrigal, Angélica María; Chaparro Becerra, William Fabián; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001713601; https://scholar.google.es/citations?user=Z7wSIokAAAAJ&hl=es; https://orcid.org/0000-0001-5470-700X
In this project, the need to modernize the communication infrastructure for EBSA smart grids in the Puerto Boyacá area is addressed. Currently, monitoring of medium-voltage line reclosers is carried out using GPRS technology, which presents significant limitations in data transmission and affects operational efficiency and quality of service. As a solution, the design and engineering of an FTTH (Fiber to the Home) optical fiber network is proposed, a technology that offers more reliable communications for power system operation. The project includes several stages, among which are: evaluating different technologies for smart grid implementation; establishing a technically viable and reliable design for fault management in the circuits through reclosers, which must be activated automatically or via remote control; and ensuring that the design considers a scalable system with a level of reliability that complies with the current regulatory framework for the electrical sector, serving as a benchmark for the modernization of communications in the different distribution network topologies in the department of Boyacá.
Interfaz Gráfica para la Medición del Tamaño de Burbujas en Procesos de Flotación Basada en Imágenes
(Universidad Santo Tomás, 2026-03-25) Rodriguez Fonseca, Jonathan Ernesto; Pardo Beainy, Camilo Ernesto; Gutiérrez Cáceres, Edgar Andrés; Gutiérrez Briones, Leopoldo Esteban Manuel; Universidad Santo Tomás; https://scholar.google.com/citations?user=iLrVanwAAAAJ&hl=en; https://orcid.org/0000-0003-0012-3679
The flotation method plays a crucial role in mining to concentrate valuable materials by adhering particles to air bubbles in an aqueous environment. The foam zone, where these bubbles are grouped, provides vital information about the effectiveness of the procedure, especially through the analysis of the bubble size distribution. However, direct visual observation is limited and subjective, making it difficult to obtain quantitative and repeatable measurements of foam behavior. The purpose of this project is to develop a methodology based on digital image processing that allows the capture, preprocessing, segmentation and characterization of bubbles in the foam region of a flotation column, using computer vision algorithms in Python and libraries such as OpenCV. The proposed tool, of a non-invasive and low-cost nature, seeks to facilitate an accurate evaluation of relevant operating parameters in the future, improving the stability of the process and the recovery of minerals. The work will be developed in conjunction with the University of Concepción (Chile), combining technical and academic capabilities to move towards automated monitoring systems in laboratory contexts and, potentially, in the mining industry. Foam flotation is one of the most widely used operations in mineral processing, as it allows valuable particles to be separated from gangue by adhering to air bubbles in an aqueous medium. In this context, the foam zone of a flotation column is a fundamental visual indicator of process performance, as characteristics such as size, shape, stability and bubble distribution are directly related to ore recovery and the quality of the concentrate obtained. However, in many academic and industrial settings, foam evaluation continues to be performed predominantly visually and qualitatively, introducing subjectivity, making it difficult to compare between trials, and limiting the development of more advanced control strategies. This paper presents the development of a methodology based on digital image processing for the identification and analysis of bubbles in the foam region of a flotation column under laboratory conditions. The proposal is implemented in Python using open-source libraries, with the aim of building a non-invasive and low-cost tool that allows quantitative information to be obtained on parameters such as the area and distribution of bubble sizes. The study is carried out in collaboration with the metallurgy laboratory of the University of Concepción (Chile), where a pilot column and the necessary experimental conditions for the controlled capture of images and video of the foam are available. The methodology considers, firstly, an analysis of the physical and operational principles of the flotation process and foam formation, in order to establish the criteria that guide the design of the image acquisition system. Subsequently, the experimental arrangement is developed, consisting of a high-definition digital camera, a dimmable LED lighting system and an adjustable support structure that allows the position and angle of capture to be fixed. From the videos obtained, representative frames of the foam area are extracted, which are subjected to a preprocessing stage that includes filtering, contrast enhancement and correction of lighting conditions, seeking to highlight the contours of the bubbles and reduce the influence of noise. In the next phase, segmentation techniques are implemented to separate the bubbles from the bottom and the column, evaluating different thresholding strategies and morphological operations. Individual bubbles are identified on the segmented images and geometric properties such as area and equivalent diameter are calculated, from which size distributions are constructed for different operating conditions. These results are integrated into a graphical user interface that allows uploading videos or images, visualizing the segmentation process, adjusting basic parameters and obtaining tables and graphs with the characterization of the foam in an automated way. The experimental results obtained in the pilot column show the feasibility of the proposed methodology to detect and quantify bubbles under laboratory conditions, providing an objective basis for the analysis of the foam zone. The tool developed is projected as a support for research and teaching in mineral flotation, as it facilitates the comparison of tests and the evaluation of changes in operating conditions. Likewise, the approach adopted opens the possibility of future extensions towards online monitoring systems and integration with advanced control strategies, contributing to the development of accessible, reproducible and adaptable solutions for foam analysis in the mining industry.
Diseño de Guías Prácticas de Fundamentos de Ciberseguridad Cisco
(Universidad Santo Tomás, 2026-03-24) Aguilar Cárdenas, Santiago; Chaparro Becerra, William Fabián; Salazar Madrigal, Angélica María; Camacho Parra, Cristian David; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001347383; https://scholar.google.com/citations?user=5_dx9REAAAAJ&hl=en
This paper addresses the design, development, and validation of a set of practical guidelines aimed at teaching the fundamentals of cybersecurity and networks in the context of university engineering education. The proposal arises from the need to strengthen practical learning in the laboratory through structured materials that allow theoretical concepts to be integrated with the configuration and operation of real network infrastructures. To this end, a methodology based on Problem-Based Learning (PBL) was used, in line with the institutional educational model, aimed at resolving situations representative of real network and security scenarios. The guides developed cover content related to an introduction to cybersecurity, IP addressing and subnetting, Cisco router configuration, access control lists (ACLs), IPsec VPNs, and ASA firewalls, combining the use of simulation tools and physical equipment available in the laboratory. As part of the process, a technical validation phase of the network equipment was carried out, identifying and solving configuration and operational problems in new and old devices, ensuring their operability for the proposed practices. Learning assessment was carried out using evaluation rubrics, designed as comprehensive tools for assessing student performance, taking into account technical, functional, and time management criteria during the execution of activities. The results show that the guides allow for the standardization of laboratory practices, facilitate the correct implementation of network configurations, and contribute to the development of technical and analytical skills, promoting student autonomy and the application of acquired knowledge in new scenarios.
Identificación de episodios de estrés con señales EEG y EDA mediante modelos de machine learning
(Universidad Santo Tomás, 2026-03-19) Barrero Solano, Yefri Stiven; Martínez Vásquez, David Alejando; Toro Tovar, Billy Vladimir; Mateus Rojas, Armando; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001560096; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001402348; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000680630; https://scholar.google.com/citations?user=U5Qf1nUAAAAJ&hl=es&oi=ao; https://scholar.google.com/citations?user=1az5o_IAAAAJ&hl=es&oi=ao; https://orcid.org/0000-0001-9750-2653; https://orcid.org/0000-0002-2399-4859
Stress is a critical emotional state with significant impacts on physical health and cognitive performance. Its traditional assessment relies on subjective methods such as questionnaires, which are prone to bias and lack temporal precision. While physiological signals like electroencephalography (EEG) and electrodermal activity (EDA) offer objective measurements, their individual use faces technical limitations and interindividual variability. The multimodal integration of these signals through machine learning (ML) models emerges as a promising alternative for the reliable detection of stress episodes. This study implemented a multimodal approach integrating EDA, EEG, and electrocardiography (ECG) signals from 10 participants undergoing cognitive tasks and sleep deprivation. After preprocessing, which included temporal segmentation and feature extraction (e.g., EDA phasic components, EEG spectral powers), binary labels (stress/no stress) were generated using the unsupervised k-means algorithm. Three supervised classification models (Decision Tree, SVM, KNN) were trained and optimized using only EDA features, with performance evaluated using metrics such as accuracy, F1-score, and AUC-ROC. In the task with balanced classes, the models showed acceptable performance, with an AUC-ROC of up to 0.8119 (KNN). In the task with class imbalance (85% stress), a drop in real discriminative capacity was observed (AUC-ROC of 0.4862 for KNN), despite deceptively high global metrics (e.g., 82.35% accuracy). Phasic EDA features (mean SCR amplitude and count) were identified as the most determinant. It was demonstrated that phasic EDA features contain sufficient information for the identification of acute stress, providing a basis for the development of low-cost wearable systems. The research underscores the criticality of class balance in data and the need to use robust metrics such as AUC-ROC for reliable evaluation. This work lays the foundation for future developments of stress monitoring systems applicable in clinical and everyday environments.
Caracterización de Circuitos RLC Planares usando 3 métodos de fabricación para componentes 3D
(Universidad Santo Tomás, 2025-09-22) Moreno Quintero, Luis Santiago; Gutiérrez, Ricardo Casallas; Universidad Santo Tomas
In recent years, new manufacturing methods have taken an important relevance in the manufacture of prototypes and in the research on these, this has resulted in progress in materials for obtaining devices; the development of these technologies can result in an improvement in manufacturing costs by improving development times. In this document, we worked on the fabrication of RLC circuits, which are the basis of electronics. We also reviewed the theoretical foundations, the fabrication methods and the data obtained. With this, we seek to make a frequency analysis of the circuits created with the different fabrication methods, taking into account the properties of the materials to be used and the way they are implemented. This project was carried out with the help of the University of Los Andes, which provided us with essential material and equipment for the elaboration of this document, without which it would not have been possible.
Control de posición del rotor de un motor de inducción por el método de control de campo orientado (FOC)
(Universidad Santo Tomás, 2025-12-16) Martín Delgado, Javier Armando; Mojica Casallas, Carlos Javier; Torres Pinzón, Carlos Andrés; Universidad Santo Tomás; https://orcid.org/0000-0002-3757-9410; https://scholar.google.com/citations?user=ca0gXCgAAAAJ&hl=es&oi=ao; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000692670; https://orcid.org/0000-0002-3757-9410; https://orcid.org/0000-0003-0367-8143
This document presents the design, implementation, and evaluation of a Field-Oriented Control (FOC) system applied to the rotor position control of a Siemens 1LA7 070-4YC60 induction machine. The main objective was to develop a control strategy that decouples flux and torque, ensuring a precise and stable dynamic response to variations in load and reference. The project was structured in phases that included machine modeling, compensator design, simulations in a MATLAB/Simulink environment, and experimental implementation using hardware provided by the MEM research group. The experimental results demonstrate robust performance of the FOC system: the current loop showed response times of less than 25 ms without overshoot; the speed loop, although initially affected by noise, was stabilized through digital filtering; and the position loop achieved steady-state stability, although overshoot occurred during transients due to the lack of integral action. Furthermore, an energy conversion efficiency exceeding 78% was achieved at full load. This work contributes to academic training by integrating theory, simulation, and practice, and lays the groundwork for future developments in advanced control of electrical machines in industrial and educational contexts.
AUTOMATIZACIÓN DE INFORMES DIARIOS DE LA MESA DE SERVICIO EN POWER BI MEDIANTE CONSULTAS SQL BANCO DE OCCIDENTE
(Universidad Santo Tomás, 2026-01-25) Leiva Bonilla, Laura Natalia; Gutiérrez Cáceres, Edgar Andrés; Chaparro Becerra, William Fabian
In the banking sector, the prompt and efficient management of incidents, requests, and tasks is essential to ensure operational continuity and guarantee end-user satisfaction. Proper handling of these processes not only secures the stability of services but also contributes to strengthening customer trust and safeguarding the institution’s reputation. Currently, within the Service Desk, the generation of daily reports is carried out manually through Oracle queries and the use of Excel spreadsheets. While this method has made it possible to maintain a basic level of operational control, it remains a repetitive task that is highly dependent on human intervention. This increases the likelihood of errors and delays the availability of critical information. Furthermore, this procedure limits the ability to conduct accurate, in-depth, and timely data analysis, while also demanding a considerable amount of time and resources. This project proposes the automation of these reports through the implementation of interactive dashboards in Power BI, enabling a clearer, faster, and more dynamic visualization of information. By establishing direct connections to data sources, eliminating manual processes, and incorporating intelligent measures and advanced filters, the goal is to optimize data analysis and facilitate the interpretation of key performance indicators. In doing so, the project seeks to strengthen strategic decision-making and ensure efficient, reliable, and real-time data analysis.
Sistema de gestión para la reducción de tiempos en los procesos de selección de monitores, desarrollo y evaluación de monitorías de la Universidad Santo Tomás usando Power Platform.
(Universidad Santo Tomás, 2026-01-22) Barrera López, Diego Alejandro; Rincón Cárdenas, Daniel Felipe; Vitola Oyaga, Jaime; Segura Torres, Darío Alejandro; Universidad Santo Tomás
This project describes the development of a system for managing the selection, development, and evaluation processes of academic monitors at Universidad Santo Tomás, using Microsoft's Power Platform tools. Previously, these processes were carried out manually through approximately 56 Excel files, resulting in a high workload and significant time consumption for those involved, especially the staff of the Student Development Coordination. In response to this situation, the main objective was to develop a support system for the monitor selection, development, and evaluation processes at Universidad Santo Tomás, by using the Power Platform toolset to reduce the time required for these procedures. The process began with the collection of requirements from the Student Development Coordination, using use case diagrams. Then, an evaluation of Power Platform tools was conducted to determine the most suitable ones for visual interface development, business logic, and data storage. Based on the requirements, the data model and software mockups were designed, followed by the system’s development using three specific Power Platform tools. Finally, a functional test was carried out in the Faculty of Electronic Engineering with a group of students to verify the correct operation of the system and its compliance with the established requirements. The results showed a significant reduction in the time and effort required to carry out the entire monitoring process, especially in the creation of the call for applications, monitor selection, and their final evaluation.
Implementación de un sistema de reconocimiento de comandos de voz en sistemas embebidos orientado a entornos domóticos y al desarrollo de una guía de laboratorio
(Universidad Santo Tomás, 2025-06-01) Vargas Cruz, Sergio Emiro; Melo Suarez, David Ricardo; Mojica Casallas, Carlos Javier; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000639214; https://orcid.org/0000-0002-3757-9410
This project presents the design and implementation of a voice command recognition sys tem on an embedded platform aimed at controlling home automation devices. The system is based on the TMS320C5535 digital signal processor, integrating TLV320AIC3204 audio co dec and a UART interface with an Arduino to toggle actuators voice commands. It includes complete stages of audio acquisition, preprocessing (silence removal, Z-score normalization, pre-emphasis, and windowing), feature extraction using Mel-frequency cepstral coeficients (MFCC), and classification using three models: Dynamic Time Warping (DTW), Gaussian Mix ture Models (GMM), and Euclidean Distance with CMVN normalization. Results indicate that GMM achieves the best trade-off between accuracy (86 % under noisy conditions) and compu tational efficiency. A complementary lab guide was developed to enhance the learning of digital signal processing and to encourage student engagement in this key area of electronic enginee ring.

Examinar

Envíos recientes