Ingeniería en Sistemas, Electrónica e Industrial
Permanent URI for this communityhttp://repositorio.uta.edu.ec/handle/123456789/1
Browse
46 results
Search Results
Item Prototipo electrónico de monitoreo cerebral en tiempo real con enfoque en la detección temprana de enfermedades neurodegenerativas mediante técnicas de inteligencia artificial.(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Telecomunicaciones., 2026-07-09) Gamboa Cornejo, Kevin Renato; Córdova Córdova, Edgar Patricio; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Telecomunicaciones.The present research arises from the global and local problematic of neurodegenerative diseases, which affect more than 55 million people worldwide. In the Ecuadorian context, approximately 100,000 people suffer from some type of dementia, facing diagnostic limitations due to high costs and the low availability of specialized equipment in provinces such as Tungurahua. The general objective of this project is to develop an electronic prototype for real-time brain monitoring to facilitate the early detection of these pathologies through the use of Artificial Intelligence (AI) techniques. The methodology is framed within applied research with bibliographic-documentary and experimental approaches. The designed system integrates low-cost hardware, including non-invasive electroencephalography (EEG) sensors and microcontrollers for the acquisition and wireless transmission of bioelectrical signals. For data processing, machine learning and deep learning algorithms are implemented to identify anomalous neuronal patterns associated with cognitive impairment. The development includes a real-time visualization interface that allows health professionals to monitor cortical activity and receive alerts based on the preliminary diagnoses of the AI model. As a result, an accessible and portable technological tool is obtained that reduces the economic gap in neurological diagnosis, promoting more inclusive and preventive medical care. It is concluded that the convergence between neuroengineering and AI offers a viable solution to improve the quality of life of patients through timely intervention in the early stages of the disease.Item Prototipo electrónico de monitoreo cerebral en tiempo real con enfoque en la detección temprana de enfermedades neurodegenerativas mediante técnicas de inteligencia artificial.(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Telecomunicaciones., 2026-07-09) Zamora Lozada, Kevin Isrrael; Córdova Córdova, Edgar Patricio; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Telecomunicaciones.The present research arises from the global and local problematic of neurodegenerative diseases, which affect more than 55 million people worldwide. In the Ecuadorian context, approximately 100,000 people suffer from some type of dementia, facing diagnostic limitations due to high costs and the low availability of specialized equipment in provinces such as Tungurahua. The general objective of this project is to develop an electronic prototype for real-time brain monitoring to facilitate the early detection of these pathologies through the use of Artificial Intelligence (AI) techniques. The methodology is framed within applied research with bibliographic-documentary and experimental approaches. The designed system integrates low-cost hardware, including non-invasive electroencephalography (EEG) sensors and microcontrollers for the acquisition and wireless transmission of bioelectrical signals. For data processing, machine learning and deep learning algorithms are implemented to identify anomalous neuronal patterns associated with cognitive impairment. The development includes a real-time visualization interface that allows health professionals to monitor cortical activity and receive alerts based on the preliminary diagnoses of the AI model. As a result, an accessible and portable technological tool is obtained that reduces the economic gap in neurological diagnosis, promoting more inclusive and preventive medical care. It is concluded that the convergence between neuroengineering and AI offers a viable solution to improve the quality of life of patients through timely intervention in the early stages of the disease.Item Clasificación de residuos mediante una aplicación android con un modelo entrenado para el aprendizaje en niños de primaria(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software., 2026-07-07) Peña López, John Alejandro; Ibarra Torres, Oscar Fernando; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software.This research addresses the problem of incorrect waste classification through the development of "MiniEco", an Android mobile application integrated with artificial intelligence for primary school students at the Juan León Mera La Salle Educational Unit. The Mobile-D methodology was used for software development and CRISP-DM for artificial intelligence. After initially training a ResNet50 architecture with TrashNet, it failed in real-time due to unvaried backgrounds and camera frame processing issues. Therefore, the system was optimized using a more diverse, real world dataset and selecting the EfficientNetV2S model. This model was converted to TensorFlow Lite to ensure 100 percent offline operation, achieving a laboratory accuracy of 94.50 percent with a final application size of 36 MB, which maintained a CPU consumption of 16 percent on low-end hardware. In the validation phase with 32 students, a significant increase in ecological knowledge was recorded, moving from 18.75 percent correct answers in the initial diagnosis to an effectiveness of up to 93 percent in tests with the tool. The usability evaluation using the SUS metric showed a satisfaction rate of 96 percent among the students. It is concluded that the integration of local computer vision and mobile gamification strengthens environmental learning at an early age, overcoming institutional connectivity limitations and providing an autonomous, scalable, and highly efficient pedagogical tool.Item Implementación de un sistema de reportería y visualización de datos con funciones de recomendación y predicción, utilizando técnicas de business intelligence (BI) e inteligencia artificial (IA), en la Dirección de Investigación y Desarrollo (DIDE) de la Universidad Técnica de Ambato (UTA)(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software., 2026-07-06) Santamaría Márquez, Christopher Paul; Santamaría Márquez, Christopher Paul; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software.This thesis focused on the implementation of a data reporting and visualization system with recommendation and prediction functions, using Business Intelligence and Artificial Intelligence techniques, at the Research and Development Directorate of the Technical University of Ambato. The identified problem was related to the manual management of scientific information, data traceability, and centralization. The research was conducted using an applied, field-based, and non-experimental approach, considering five staff members involved in information management processes as the population. A structured interview with a Likert scale and a complementary semistructured interview were used for the diagnostic process, allowing the identification of eight problems and ten institutional needs. As a result, a web platform based on Scrum + XP was developed, integrating scientific article management, bulk upload, institutional workflow, external integration, ETL processes, an extensible OLTP model, a constellation-type data warehouse, dashboards, and exportable reports. Furthermore, an AI module was implemented with monthly scientific output forecasting, forecasting by faculty and research area, data quality recommendations, editorial recommendations, and AI readiness analysis using weighted indicators. The evaluation showed 80 successful reporting operations, a 100% success rate, an average time of 10.53 seconds, and an estimated reduction of 99.66%. The post-implementation structured interview based on CSUQ received a score of 4.59/5, 100% acceptance, and a Cronbach's alpha of 0.973. It is concluded that the system strengthens information management and supports data-driven decision-making.Item Sistema web progresivo para la gestión de la ejecución y seguimiento de la formación del talento humano y generación de reportes mediante inteligencia artificial en la Empresa Eléctrica Ambato regional centro norte S.A(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software., 2026-07-06) Ramirez Manzano, Oscar Joel; Núñez Miranda, Carlos Israel; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software.This research examined how to optimize the management and monitoring of human talent training at Empresa Eléctrica Ambato Regional Centro Norte S.A. through a Progressive Web Application and an artificial intelligence module for report generation. The study followed an applied research modality and used a key-informant interview, a diagnostic survey of institutional staff, a TAM survey with 124 users, expert validation with 3 Human Talent users, and the Extreme Programming methodology to plan, design, code, and validate the solution. The research identified five critical institutional processes, defined functional, technological,and non-functional requirements, and implemented modules for events and training activities, attendance, materials, certificates, notifications, audit, and AI-based reporting. DeepSeek was incorporated into the analytical module because of its ability to interpret natural-language queries and transform them into useful administrative reports for decision-making. The results showed functional compliance in black-box tests, PWA technical validation, and, as a complementary measure, a final success rate of 86.7 percent in the analytical module evaluation. The TAM survey reported 91.5 percent perceived usefulness, 83.9 percent perceived ease of use, 92.5 percent confidence and security, and 90.8 percent attitude and intention to use. Expert validation showed favorable assessment of the administrative and analytical modules. The research concluded that the solution was functional, technically viable, and relevant for modernizing institutional training management.Item Medidor virtual de flujo (VFM) con inteligencia artificial para la predicción del flujo de gas en el campo Pucuna(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software., 2026-07-06) Montesdeoca Cruz, Marco Felipe; Jara Mora, Santiago David; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software.At Petroecuador’s Pucuna field, associated-gas measurement in flares is limited by scarce instrumentation, manual estimates, and high costs of physical meters, hindering operational decisions. This study proposes a Virtual Flow Meter (VFM) using artificial intelligence to estimate daily gas flow from operational variables (pressure, temperature, and liquid production). The work combined semi-structured interviews, a Virtual Flow Metering literatura review, and 2,192 daily observations stored in PostgreSQL. Ridge, Random Forest, SVR, and MLP were evaluated; the multilayer perceptron achieved the best test performance (25 %): R2 = 97.02%, MAE = 0.13%, andRMSE = 0.18%. An integrated system was built with RAD, Laravel, Python/FastAPI, Tensor- Flow/Keras, PostgreSQL, and Docker for data loading, training, prediction, and visualization; daily predictions can be aggregated by period (e.g., monthly) to support operational balances. Fifteen functional and non-functional requirements reached 100% compliance through unit, integration, and black- and white-box testing. The results confirm the technical feasibility of a software VFM for field pilot deployment and model recalibration.Item Chatbot basado en procesamiento de lenguaje natural para tareas de soporte técnico en la empresa Mivilsoft S.A.(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Tecnologías de la Información., 2026-07-03) Ballesteros Moya, David Augusto; Aldás Flores, Clay Fernando; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Tecnologías de la Información.This project arises from the need for a system that preserves the fluidity of the communication channels preferred by clients while centralizing the collected information to enable traceability and auditing. To achieve this, the project leverages modern technologies based on artificial intelligence. The project included an assessment of the company’s needs and the resources available to address them. Based on this analysis, it was determined that the solution would be implemented as an Odoo module integrated into the system currently in operation, incorporating technologies such as LangChain and pgvector to enable artificial intelligence capabilities. Additionally, a literature review was conducted on technologies, software architectures, and best practices related to the use of natural language models. The resulting system is capable of maintaining a conversational interaction with the user and, based on the user’s needs and the given context, can make decisions such as registering a new support ticket, responding to user inquiries, or retrieving information about tickets related to a specific issue.Item Sistema inteligente de alarmas comunitarias con arquitectura IOT para la empresa Ecuaseg.(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Telecomunicaciones., 2026-07-01) Toapanta Toctaguano, Jhon Roberth; Vargas Guevara, Carlos Luis; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Telecomunicaciones.This thesis project describes the design and implementation of an Intelligent Community Alarm System based on an Internet of Things (IoT) architecture, developed to optimize citizen security processes for the company ECUASEG (Ecuadorian Electronic Security Company) in the city of Ambato. The current problem lies in the inefficiency of conventional alarm systems, which lack automated mechanisms for verifying early warnings, generating false positives and prolonged response times in risk situations. To overcome this limitation, the research was methodologically structured using a three-layer technological model: Perception, Network, and Application. In the perception layer, sensor nodes based on ESP32 microcontrollers and a video surveillance system coupled to a Raspberry Pi 4 were implemented. The latter integrates a YOLOv8 computer vision model optimized with the SORT algorithm, allowing for the real-time detection and tracking of objects and people in perimeter areas. Experimental results demonstrated 92.5% object detection accuracy with YOLOv8 and a 40% reduction in alarm transmission latency compared to traditional analog systems, while maintaining a packet loss rate of less than 1.2% under simulated network environments. In conclusion, the integration of machine vision and IoT validates the system's technical feasibility, offering a robust, scalable, and efficient solution for crime mitigation and strengthening community safety in the local context.Item Desarrollo de un aplicativo web-móvil con reconocimiento de imágenes para la gestión de servicios técnicos en aparatos electrónicos(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software, 2026-06-29) Curicho Soria, Johan Israel; Jerez Mayorga, Daniel Sebastian; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de SoftwareThe main objective of this project was the development and implementation of a web-mobile application with image recognition capabilities. This application will enable the management and generation of technical service reports within Electrónica Mantilla, aiming to reduce documentation errors and improve processing times. The Mobile Sprint agile methodology was used to develop the system, allowing for a process adapted to the project's needs. The technological architecture utilized Supabase as the Backend as a Service, Next.js for the web-based administrative environment, and React Native for the mobile application. The integration of an Artificial Intelligence model was based on YOLOv8 Nano, which recognizes labels on electronic devices. An OCR engine was also integrated to automatically extract the necessary text and perform relevant validations. The resulting system allows the company to centralize information and manage service order processes in real time. The application automatically identifies electronic devices, recurring faults, and potential solutions provided by the company, streamlining and accelerating the technician's diagnostic process and service report generation. Acceptance testing demonstrated 97.11% accuracy in the Artificial Intelligence model, while the automatic generation of PDF reports helps technicians optimize the closing of each service call.Item Desarrollo de una aplicación para la generación de ilustraciones 2D de figuras humanas utilizando recursos basados en inteligencia artificial y su efecto en los tiempos de creación.(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software, 2026-01) Villafuerte Grijalva, Mauricio Fernando; Jara Moya, Santiago David; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de SoftwareThe 2D illustrations of human figures are a widely used medium in presentations, informational materials, and signage due to their ability to clearly represent scenes and concepts. However, despite their apparent visual simplicity, their creation often requires intermediate or advanced knowledge of digital editing or illustration tools, making them difficult for users without prior experience. To facilitate access, an application was developed for generating 2D illustrations of human figures using artificial intelligence-based resources. The tool incorporates a 2D model and automates repetitive and complex processes. Development was carried out using the Kanban methodology and Python as the primary language. Pygame was used for the model's interface and interaction, while MediaPipe was used as the AI component for capturing and transferring poses from reference photographs. The results showed an 85% reduction in the time required to generate an illustration compared to a traditional workflow using various tools, as well as a significant simplification of the creative process. The application allows users to adjust the model's position, import a photograph to replicate its pose, customize the character's appearance, and export the resulting illustration with a transparent background. The project demonstrated that integrating artificial intelligence techniques with simplified interfaces can substantially optimize the generation of 2D illustrations, making it accessible to inexperienced users and reducing both the complexity and time required for image creation.