Ingeniería en Sistemas, Electrónica e Industrial

URI permanente para esta comunidadhttp://repositorio.uta.edu.ec/handle/123456789/1

Examinar

Resultados de la búsqueda

Mostrando 1 - 6 de 6
  • Item type:Ítem,
    Plataforma móvil para el monitoreo y analítica predictiva de datos microclimáticos: caso de estudio torre meteorológica ubicada en la Facultad de Ingeniería en Sistemas, Electrónica e Industrial de la Universidad Técnica de Ambato
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software, 2026-06)
    Pérez Veliz, William Leonardo
    ;
    Jerez Mayorga, Daniel Sebastián
    ;
    Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software
    This research aimed to develop a mobile platform for monitoring and predicting meteorological variables to determine microclimates on the campus of the Faculty of Systems Engineering, Electronics, and Industrial Engineering. The study was structured in three phases. First, raw data from the institutional weather tower was collected and cleaned by applying exploratory data analysis, average signal filtering, and temporal feature engineering to generate optimal numerical matrices for temperature, solar radiation, and barometric pressure. Second, four predictive algorithms —Random Forest, XGBoost, Stacked LSTM, and CNN-LSTM— were trained and evaluated using R², MAE, and RMSE metrics. Results demonstrated that no single universal model is optimal: Random Forest achieved the highest accuracy for temperature (R² = 0.88), while XGBoost outperformed the rest for solar radiation (R² = 0.82) and barometric pressure (R² = 0.91). Additionally, a heuristic rainfall probability estimator based on pressure and temperature deltas was implemented due to the absence of a physical rain gauge. Third, the complete technological ecosystem was built: an asynchronous FastAPI backend following Clean Architecture principles integrating serialized models, and a cross-platform React Native mobile application featuring real-time dashboard, historical visualization, and four-hour forecast modules. The platform was validated through integration and usability testing, confirming its operability and low latency in production environments.
  • Item type:Ítem,
    Sistema Iot con análisis predictivo para el monitoreo de la salud de sistemas de bombeo de campos petroleros
    (2026)
    Bonilla Bonilla Erick Bladimir
    ;
    Ayala Baño Elizabeth Paulina
    ;
    Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones
    The operation of electric submersible pumps (ESPs) in oil fields is impacted by failures, downtime, and the limited use of digital tools for condition monitoring. To address this challenge, an IoT system with predictive analytics was developed to monitor the health of ESPs, with the aim of supporting maintenance decision-making and reducing the occurrence of critical failures in continuous production environments. To develop the solution, the CRISP-DM methodology was applied, defining a predictive analytics workflow based on historical data. In this stage, operational records were integrated, structured, and refined using electrical, hydraulic, mechanical, and thermal variables, and a preprocessing pipeline was implemented—including validation, cleaning, and feature transformation—to ensure data consistency and quality. On this basis, a multi-label dataset with five classification targets was built, enabling the joint execution of diagnostic and prognostic tasks. Subsequently, ensemble models based on decision trees were compared, and a multi-label Random Forest approach was adopted due to its balance of performance, robustness, and generalization capability across multiple classes and operational variability. During controlled-environment testing, the system achieved an approximate overall weighted precision of 85%, with per-label accuracies of 82% for failure variable, 83% for subcomponent, 82% for severity, 83% for pump state, and 91% for 24-hour failure prediction. Finally, deployment was carried out using Docker, a FastAPI inference service, InfluxDB, and Grafana dashboards, enabling visualization of process variables and estimated operating status, and demonstrating the technical feasibility of the proposed solution for predictive maintenance.
  • Item type:Ítem,
    Sistema de detección de niveles de atención en estudiantes mediante análisis de imágenes de video empleando visión artificial
    (2025-08)
    Yugcha Rubio Edison David
    ;
    Castro Martin Ana Pamela
    ;
    Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones
    The present work developed a system for real-time monitoring of the attention level of students, through the implementation of computer vision and deep learning. The system uses a webcam to capture images of the student, which are processed by algorithms such as MediaPipe and YOLOv8 to detect postures, gestures, gaze direction and distracting objects. From this data, a neural network-based model classifies the level of attention into three categories: high, medium and low. The solution was validated at the Gustavo Iturralde Fiscal School, located in the Lasso parish, where structured tests were applied to 12-year-old students. The results showed adequate accuracy and significant agreement between the system's automatic evaluation and the teacher's direct observation. In the activities carried out, the system and the observer coincided in the classification of attention levels, consistently identifying high, medium and low states according to the behavior of the students during the different tests. This alignment between the two methods reinforces the usefulness of the system as a complementary tool for the objective monitoring of attention in the classroom. The implementation proved to be practical, non-invasive and compatible with the school environment. The system provides a valuable tool for improving pedagogical management, allowing teachers to identify attention levels in a timely manner and apply corrective strategies. Its adaptability and accuracy position it as a technological resource with high potential for future research and educational applications.
  • Item type:Ítem,
    Dispositivo portátil para la detección temprana de arritmias cardiacas en adultos mayores mediante técnicas de inteligencia artificial
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2025-02)
    Aguilar Paucar Karol Nataly
    ;
    Benalcázar Palacios Freddy Geovanny
    Cardiovascular diseases are one of the leading causes of death worldwide, with cardiac arrhythmias being a significant factor in many of these cases. Early detection of these irregularities is crucial to prevent serious complications and improve patients' quality of life. This research focuses on the development of a portable device for the early detection of cardiac arrhythmias, combining advanced biomedical module technologies, signal processing, and machine learning models. The device uses an LSTM autoencoder-decoder model to analyze electrocardiogram (ECG) signals in real time, identifying abnormal patterns in time series and distinguishing between normal and arrhythmic heart rhythms. The high-quality ECG5000 database was used for training and validating the model. The research includes key stages such as data acquisition, preprocessing to reduce noise and artifacts, model implementation, and validation testing in a controlled environment. Preliminary results show that the device is capable of detecting arrhythmias with high accuracy and speed, making it a valuable tool for remote monitoring and the prevention of cardiovascular events. This project not only contributes to technical advancements but also provides an accessible solution for cardiac health monitoring, improving the ability of patients and healthcare professionals to address cardiovascular conditions promptly and efficiently.
  • Item type:Ítem,
    Detección de niveles de estrés en estudiantes universitarios a partir de señales electrofisiológicas mediante técnicas de machine learning
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2024-02)
    Pazmiño de la Cruz, Shirley Lizbeth
    ;
    Córdova Córdova, Edgar Patricio
    Al iniciar sus estudios superiores, los jóvenes se ven sometidos a presiones académicas, expectativas sociales y múltiples responsabilidades, generando niveles elevados de estrés que inciden tanto en su rendimiento académico como en su salud mental y bienestar general. Este proyecto de investigación ha perseguido el desarrollo de un sistema electrónico que emplee señales electrofisiológicas y técnicas de machine learning para identificar niveles de estrés en estudiantes universitarios en este entorno desafiante. Para alcanzar dicho objetivo, se ha llevado a cabo una revisión bibliográfica exhaustiva en bases de datos médicos y científicos, focalizándose en señales electrofisiológicas asociadas al estrés académico. Se han seleccionado sensores específicos, como el Grove GSR y Muscle Sensor V3, y todo el proceso se ha desarrollado en el microcontrolador ESP32 Tiny S3, aprovechando su capacidad y tamaño para crear un dispositivo portátil. Los datos procesados se almacenaron en un servidor web mediante peticiones PHP. Las métricas de evaluación del algoritmo de machine learning revelaron una alta precisión del 0.96, respaldada por un índice de 0.97 en el conjunto de entrenamiento, 0.97 en el conjunto de prueba y 0.9 en la etapa de validación con el método de validación cruzada. Estos resultados confirman que el algoritmo Random Forest gestiona de manera eficiente la clasificación y el entrenamiento, sobresaliendo en comparación con otros algoritmos evaluados. En cuanto a la confiabilidad, el sistema ha logrado un porcentaje del 93,68% en la lectura de datos, consolidando así su capacidad para detectar niveles de estrés y prevenir posibles colapsos en la salud de los estudiantes
  • Item type:Ítem,
    Sistema automático de decodificación de lengua de señas ecuatoriano a comunicación verbal.
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2023-09)
    Gavilanes Proaño, Wendy Patricia
    ;
    Brito Moncayo, Geovanni Danilo
    People with hearing and speech disabilities rely on sign language to express their ideas, emotions, and needs. This form of gestural communication employs hand movements and facial expressions to effectively convey messages. However, the lack of knowledge of this language on the part of the hearing population limits the opportunities for interaction and mutual understanding. For this reason, an automatic system capable of translating and learning the Ecuadorian sign language into verbal communication using artificial intelligence was developed. The project was developed based on the "Gabriel Román" Ecuadorian Sign Language Dictionary " to establish the basic vocabulary of the system, which consists of the Ecuadorian dactylological alphabet, numbers and basic words. An electronic glove for the right hand was built, with five Flex sensors, an MPU6050 inertial sensor and an Arduino Nano board, which were responsible for recording the movements of the hand and fingers, such as flexion, extension and inclination, these Data is processed using Python to create the database, in order to apply machine learning algorithms. The algorithms studied are k-Nearest Neighbors (KNN) and Random Forest, with training accuracies of 94,62% and 96,20% respectively. Finally, applying the Random Forest model, a graphical interface was created in Streamlit, where the user can visualize the translation of the sign language through text and an audio output.