Repositorio Institucional UniAgustiniana
El Repositorio Institucional de la UniAgustiniana administra, preserva y difunde en OPEN ACCESS los documentos académicos de la institución: tesis, trabajos finales de graduación, libros, artículos, resultados de investigación, trabajos docentes, etc. Actualmente está indexado en varios recolectores mundiales de metadatos OAI-PMH que incrementan su visibilidad y permiten la consulta y citación de sus contenidos en todo el planeta, garantizando de este modo el acceso ilimitado y continuo a nuestra producción académica/universitaria.
Recent Submissions
Diseño de un Sistema de Alarma con Botón de Pánico para los Corredores Seguros en Situaciones de Robo
Pinzon-Nieto, Katerin; Niño-Villamil, Daniel; Umbacia-Betancourt, Eliana
The purpose of this project is to design, assemble, and validate a prototype portable alarm with a panic button aimed at strengthening security in university safe corridors and reducing response times to theft situations, The system integrates wireless communication modules (XBee PRO S3B), GPS geolocation, and a monitoring interface implemented in Node-RED, complemented by a Telegram Chat Bot for automatic notification of alerts in real time.
During this development period, the prototype was designed and assembled, selecting low-energy consumption electronic components that are highly compatible with each other. Experimental tests were also carried out with antennas of different gains, including a 5 dB omnidirectional antenna and a 15 dB Yagi directional antenna, in order to evaluate the range, link stability, and accuracy of the GPS locator. In general terms, the results demonstrated the reliable performance of the system in university environments.
In conclusion, the prototype developed demonstrates the technical and functional viability of a portable alert system based on IoT technologies, capable of contributing to the safety and well-being of the university community through a rapid, traceable, and accessible response.
Diseño e implementación de un Sistema Portátil de Monitoreo de variables Ambientales Basado en IoT en la Universitaria Agustiniana
Silva-Moreno, Miguel Angel; Culma-Caraballo, Kevin Sebastian; Rodriguez-Veloza, Edgar Fabian
The Universitaria Agustiniana is located in an area with high vehicular flow, a condition that can significantly influence the environmental variables present in the green areas and open spaces of the campus. To characterize these factors, this project develops a portable environmental monitoring system based on IoT technologies, capable of measuring and displaying in real time parameters such as temperature, relative humidity, atmospheric pressure, altitude, and an air quality index estimated from the gas resistance of the BME680 sensor, used as a reference for detecting volatile organic compounds (VOC).
The system integrates the Bosch BME680 sensor and an ESP32 module responsible for wireless communication using the MQTT protocol. The device is assembled in a laser-cut wooden structure that ensures mechanical stability and protection of the components during measurement sessions. Data reception, processing, and visualization are performed from a laptop that functions as a local server and monitoring point.
The visualization platform, developed in Node-RED, enables real-time monitoring and access to historical data collected in the Ayape, Salazar, Buitrago, and sports field areas. The methodology included the electronic design of the prototype, firmware programming, configuration of the communication environment, and validation through field tests at various measurement points.
This system does not aim to replace professional environmental monitoring instruments; instead, it offers a practical, low-cost, and learning-oriented solution that supports basic environmental analysis and strengthens technological skills within the academic community.
Desarrollo de una Aplicación móvil de Ejercicios Mentales para la Prevención de Enfermedades Neurológicas en Personas de la Tercera Edad.
Ariza-Ramirez, Julian Andres; Castro-Ladino, Kevin Mateo
The main purpose of this project is to develop a mobile application that allows senior citizens to minimize the progression of neurological diseases, preventing further decline and maintaining optimal health. This application will enable them to track their progress and monitor any improvements or changes. This document contains all the centralized information about this self-help process. It also provides a detailed score, detecting any changes in the individual's cognition. This allows the user to effectively manage their own internal health status through a results system, along with a specialist physician who will provide the patient with an analysis of areas for improvement. The client can then continue using the self-help tool we have created to enhance their mental health.
Desarrollo de un Chat Bot en Telegram para la Capacitación Continua de Asesores Comerciales de OPPO COLOMBIA
Ardila-Martínez, Cristian; Villalba-Alonso Mauricio
Abstrac
The "Ollie Bot AI" project aims to implement a chatbot on Telegram for the continuous training of OPPO COLOMBIA sales advisors. Its main objective is to solve the problem of scattered access to critical information about products, sales arguments, and competitor comparisons, which currently makes it difficult for advisors to respond quickly and accurately to customers.
The chatbot will centralize this information, allowing advisors to make queries in natural language or through buttons to obtain immediate responses. It will use technologies such as Google Dialogflow for Natural Language Processing (NLP), Java, and PostgreSQL.
Ollie Bot AI is expected to optimize response time, improve the quality of information provided, boost sales, increase customer satisfaction, and help identify topics for future training sessions and brand objectives.
Keywords: Ollie Bot AI, chatbot, training, sales advisors, Google Dialogflow, sales
Implementación de un sistema basado en técnicas de machine learning para la detección de correos electrónicos de spear phishing
Herrera-Marroquin, Juan esteban; Valle-Diaz, Francisco Clemente
The purpose of this project was to develop an automated solution capable of identifying malicious emails using large-scale language models (LLM) and machine learning techniques. For its implementation, an application programming interface (API) integrated into the n8n platform was designed, allowing for the establishment of a functional workflow for analyzing suspicious emails and automatically generating reports. Additionally, the Hybrid Analysis tool was incorporated to scan potentially malicious files and links, optimizing threat detection and classification processes.
During the research, studies and official data were collected that demonstrate the increase in phishing and spear phishing attacks in Colombia, especially during the COVID-19 pandemic, highlighting the need to implement technological solutions based on artificial intelligence. The system was validated through controlled tests with simulated emails, yielding positive results in identifying and classifying fraudulent messages, demonstrating the effectiveness of the developed model.