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 - 10 de 12

Sistema de reconocimiento facial para control de acceso con Deep Learning en la Cooperativa de Ahorro y Crédito Sol en el área de cajas/bóveda.
(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software., 2026-07-08)
Yambay Miño, Santiago Estiven
;
Balarezo López, Julio Enrique
;
Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software.
Access control to the cash register and vault areas of Cooperativa de Ahorro y Crédito SOL presented security vulnerabilities due to the reliance on manual logs, which generated risks of identity impersonation, recording errors, and lack of traceability. Therefore, the main objective of this research was to develop an automated access validation application based on facial recognition using convolutional neural networks. The study applied a field and applied methodology with a mixed approach, using surveys, interviews, and observation sheets addressed to a sample of 12 employees in order to diagnose the initial situation. As a result, the proposed application mitigated four high-severity risks and fulfilled seven operational requirements. Furthermore, when comparing two technological models, the transfer learning program implemented with the DeepFace library showed better comparative performance than the local supervised learning classifier, since it used 100 reference photographs per authorized employee, achieving an accuracy of 98 percent, a precision of 96.15 percent, and a sensitivity of 100 percent. In contrast, the local model required 300 photographs and obtained 55 percent accuracy with 89 false negatives. Thus, it was concluded that the implementation of neural networks reduced dependence on physical records and automated biometric verification in real time, providing a more secure, traceable, and auditable access management process for the financial institution.
Sistema de identificación biométrica para el control de ingreso del personal en las instalaciones de la coordinación zonal 3 del servicio integrado de seguridad ecu 911
(2026-01)
Cunuhay Quirco Karina Mishell
;
Guevara Aulestia David Omar
;
Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Tecnologías de la Información
This project addresses the lack of an official system for controlling staff access to Zone 3 Coordination of SIS ECU 911. To respond to this problem, a mixed methodology was applied that included surveys, interviews, observation sheets, and a literature review in academic repositories such as SCOPUS, IEEE Xplore, and ScienceDirect. The technical requirements and operating conditions of facial recognition for use in biometric control were investigated. A comparative review of three models allowed for the analysis of essential aspects such as embeddings, robustness, training difficulty, and limitations, positioning InsightFace as the most suitable option due to its accuracy and efficiency. The use of hardware based on reused mobile phones was defined due to its versatility in integrating a camera and screen into a single device, complemented by free and open-source software and frameworks. Operational requirements included the initial capture of photographs for the template, protocols to ensure daily use, secure storage of information, legal compliance, and personal data protection, as well as contingency mechanisms to ensure system continuity. The results showed 89% institutional acceptance and 90% model accuracy, reducing human error and ensuring reliability. It is concluded that the proposal improves access control efficiency, complies with regulations, and promotes sustainability through technological reuse, contributing to the digital transformation of strategic processes.
Sistema integral de control y seguimiento personalizado para gimnasios, basado en inteligencia articial
(2025-07)
Guamán Coello Darío Armando
;
Manzano Villafuerte Víctor Santiago
;
Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones
The sustained growth of fitness centers in Ecuador has motivated the design of a customized intelligent control and monitoring system for gym users. This system integrates an ESP32 board as the processing and wireless communication core, along with an ECG sensor responsible for capturing cardiac signals during physical activity. Power is managed by a 7.4V Li-Po battery, stabilized by an LM7805 regulator to ensure a constant supply to the components. In addition, a Dahua HC4 camera is incorporated, enabling real-time video capture to validate user entry through facial recognition, ensuring secure and automated access. Advanced image processing runs on an NVIDIA Jetson Nano, selected for its high performance in computer vision tasks. The collected data is transmitted via Wi-Fi to a mobile app developed in Flutter, which allows the user to view personalized metrics, log routines, and access recommendations based on their physical performance. During development, Google Colab was used as the training platform for the YOLOv8-based model, and Roboflow was used to manage and label the visual data. This technological solution represents a breakthrough in the automation and personalization of sports environments, offering an intelligent and adaptive experience that improves user performance, safety, and motivation. The system is presented as an innovative tool in the context of data-driven wellness and fitness.
Sistema de control de acceso automatizado con inteligencia artificial para el monitoreo de estudiantes y docentes en los talleres tecnológicos de la FISEI
(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2025-02)
Barba Proaño Silvia Guadalupe
;
Brito Moncayo Geovanni Danilo
The present research work focuses on the development of an automated access control system utilizing artificial intelligence for monitoring students and teachers of the faculty in the technological workshops of the FISEI at the Technical University of Ambato. The project encompasses everything from analyzing technical and operational requirements to implementing an intelligent system that integrates specialized hardware and software. Integration schemes for the system were designed, which include the use of biometric capture devices and facial recognition cameras connected to an artificial intelligence platform. This system enables automatic identification and registration of user entries, ensuring efficient control. Additionally, parameters were established to manage realtime alerts and generate detailed reports on user attendance and duration in the workshops. The implementation of the system included the development of machine learning algorithms to optimize facial recognition and user authentication, as well as the integration of a user-friendly interface that facilitates its use by administrative personnel. Functional tests were conducted in both simulated and real environments, verifying the accuracy of recognition and the robustness of the system under various operational conditions. Finally, the system was validated through pilot tests in the technological workshops, demonstrating its effectiveness in access management and continuous monitoring, contributing to security, and optimizing the use of available resources at FISEI.
Sistema de reconocimiento facial utilizando visión artificial basado en una arquitectura iot, para el conteo de usuarios en las unidades de la Cooperativa de Transporte Público “Unión Ambateña”
(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2024-08)
Solís Santamaría, Alexis Adrián
;
Guamán Molina, Jesús Israel
Over the years, the transportation company Union Ambateña has seen it is necessary to use different control systems in each bus, in order to track the number of passengers who use the public transportation every single day and be able to know how much money they receive. However, it has been difficult to get accurate data due to limited technology. A system with IoT architecture is presented for detection, classification, and counting of people using the transportation service. An EZVIZ H6c 1080p Wi-Fi camera and an EXTREM 720p camera are used to capture real-time videos of people and faces inside each bus, which are processed on the NVIDIA Jetson Nano development board. The detection models count the total number of passengers boarding the bus and also detect and record the number of adults using the service. The system is developed with the YOLOv8 artificial vision algorithm, which handles adult detection, as well as detection of all types of people. The results of the user count obtained are displayed on the Node-RED platform, which is used with a local service to show the value of the final revenue report. The results are stored and managed on the Ubidots IoT platform, which allows for control of the transportation units and decision-making with real-time data.
Sistema de seguridad con tecnología Iot y reconocimiento facial para la Compañía de Taxis Patria Patriatax S.A.
(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Ingeniería en Electrónica y Comunicaciones, 2023-09)
Lema Amores, Cristian Daniel
;
Altamirano Meléndez, Santiago
The research project focuses on the design of a facial recognition-based security system for the taxi company Patriatax S.A.. located in the Latacunga city. This project arises due to the increase in crime in taxi cooperatives in the area, so it seeks to implement an effective method to reduce crime and victimization through facial recognition of the driver and the passenger. The importance of this system lies in its ability to obtain relevant information about passengers, such as possible legal issues, whether they are wanted criminals or have criminal records, which contributes to preventing dangerous situations for both passengers and the driver. Additionally, the facial recognition of the driver ensures that the vehicle is only used by the designated driver for that unit, increasing the safety of the passengers. An alcohol test is also incorporated, which can reduce the number of accidents caused by intoxicated drivers. The implementation of this system heavily relies on the existence of advanced facial recognition technology and IoT platforms that allow real-time data collection and visualization. The effects of implementing this system are highly significant, as it not only improves the quality of service provided by Patriatax S.A. taxi company but also increases the trust of users in public transportation. As a result, it is expected that the number of users of the taxi company's services will increase, positively impacting the safety and quality of transportation services and benefiting the confidence of the users.
Sistema para minimizar el riesgo durante la entrega de los estudiantes de educación inicial a los representantes usando técnicas de reconocimiento facial en la Unidad Educativa Cristiana New Life,
(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Tecnologías de la Información, 2022-09)
Calo Tisalema, Christian Fernando
;
Nogales Portero, Rubén Eduardo
The use of facial recognition systems has been in great demand in recent years as they offer greater security during the processes carried out in companies and organizations, and are even used by government entities focused on citizen security. They are also present in educational institutions for the control of personnel, or in the case of students for the registration of their attendance. The research project aims to develop a facial recognition system that reliably identifies the representatives or persons authorized to pick up students, in order to ensure a safe delivery of early childhood education students during dismissal. The current process is carried out manually, where teachers, based on their knowledge and experience, are in charge of delivering the students. The system was created in the Matlab development environment in its R2020a version, MySQL version 8.0 was used for the database manager and the facial recognition technique consisted in the application of Neural Networks, with the Alexnet pretrained network. The development process was carried out through the application of the agile methodology Extreme Programming (XP).
Algoritmos de procesamiento de señales para el reconocimiento facial y de voz empleando redes neuronales
(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Ingeniería en Electrónica y Comunicaciones, 2022-09)
Orozco Analuiza, Carlos Alexander
;
Pallo Noroña, Juan Pablo
The present titling work deals with the development of an access control system through facial and voice recognition, for the authentication of people in a home. Currently, the levels of insecurity have increased and this has led to an increase in theft and damage to real estate due to the low level of security in a home. The device developed in this project is based on a bimodal access biometric, through machine learning and neural networks, a subfield of Artificial Intelligence. The system has two authentication methods: facial and voice, for which neural network models designed by the researcher were used with the stages of: database formation, image and audio processing, and neural network design. He implements two methods of facial and voice authentication to avoid identity theft, a camera is responsible for capturing the person's face and performing recognition through the neural network, if the user is registered, the microphone is activated to capture the key of access and process it through the neural network, to record the data a LAMP server is used where the system information and user notifications are stored through the Telegram application. This project is aimed at controlling the access of people to a home, avoiding the use of traditional authentication methods.
Registro de asistencia de alumnos por medio de reconocimiento facial utilizando visión artificial
(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Maestría en Automatización y Sistemas de Control, 2019)
Bastidas Gavilanes, Jonny Rodolfo
;
Mendoza Chipantasi, Darío José
En algunos países desarrollados tienen sistemas de control de asistencia para el personal que trabaja en la industria, sector público y privado, los mismos que sirven para verificar la asistencia de cierto trabajador y salida del mismo. Esto ha llevado a diseñar sistemas de control para abrir o cerrar puertas. En todas las instituciones existe la necesidad de llevar un exhaustivo control de la asistencia del personal, conociendo el tiempo que ha dedicado para cada actividad a lo largo de su jornada laboral y para lo cual se utilizan diferentes tipos de metodologías que permitan controlar esto, acordes a las situaciones económicas y tecnológicas que presentan. Con un mercado cada vez más competitivo y globalizado, las empresas e industrias se han visto obligadas a desarrollar métodos más eficientes que los tradicionales en el control de asistencia de su personal. En la actualidad se tiene la versatilidad de la tecnología de visión artificial utilizada en tareas de verificación y comparación de imágenes, para en lo posterior realizar el control de asistencia de personal en empresas, industrias, sector educativo, etc. El presente proyecto fue realizado en busca de otra opción para hacer el registro de asistencia de los alumnos por medio del reconocimiento facial. Además se utilizó redes neuronales artificiales en especial se hizo un análisis con la red neuronal de Histograma de Gradientes orientados HOG y la red neuronal CNN que significa Convolución de redes Neuronales. Se deja planteado como proyecto para su posterior uso en la o las universidades, en caso particular se plantearía a la Universidad de las Fuerzas Armadas Espe extensión Latacunga. Las ventajas de utilizar este proyecto con la aplicación de redes neuronales artificiales es que están basadas en la estructura del sistema nervioso especialmente relacionadas con la funcionalidad del cerebro, una red neuronal artificial tiene la facilidad de aprender mediante un buen entrenamiento, esto consiste en ingresar datos a la entrada y obtener óptimos resultados a la salida. Una red neuronal maneja los datos internamente y los organiza de forma adecuada dejando libre al usuario de este trabajo. Esta red es tolerable a cualquier falla que se pueda originar porque su almacenamiento es de forma redundante y podría seguir trabajando aun si existiera alguna falla. En cuanto a la flexibilidad puede manejar cambios que se pueden originar en la información de entrada, dichos cambios puede ser ruido o perturbaciones. Y la ventaja más relevante es que si se trabaja con computadoras y algún dispositivo electrónico especial se puede obtener respuestas en tiempo real, porque la estructura de una red neuronal artificial es en paralelo
Sistema de reconocimiento facial con visión artificial para apoyar al ECU 911 con la identificación de personas en la lista de los más buscados
(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Ingeniería Electrónica y Comunicaciones, 2017-01)
Garcés Núñez, Alex Fernando
;
Jurado Lozada, Marco Antonio
El presente proyecto de investigación propone el desarrollo de un prototipo de sistema de reconocimiento facial destinado a la identificación y reconocimiento de personas en tiempo real, llevado a cabo en la dirección zonal 3 del ECU 911, para ser aplicado a la localización de individuos buscados por la justicia que se encuentran en una lista denominada “los más buscados”, con el objetivo principal de incrementar los índices de seguridad colectiva brindando un sistema robusto que pueda ser utilizado en diversos lugares concurridos como: terminales, transporte público, etc. El sistema posee un registro de almacenamiento en una base de datos con las personas que han sido identificadas por el sistema, el uso de una cámara conectada al sistema permite la adquisición de la imagen del rostro de las personas que pasen por el sistema, realizando un análisis de la imagen anteriormente adquirida mediante el uso de funciones y librerías para el procesamiento de imágenes, comparando las características faciales de la imagen ingresada por medio de un algoritmo de reconocimiento facial con las imágenes almacenadas en el sistema, permitiendo identificar a la persona buscada y de esta forma se envía una alerta de ubicación en tiempo real mediante el uso de coordenadas GPS tanto en latitud como en longitud, mostrándose esta información en un mapa en la interfaz de monitoreo, el mensaje de alerta enviado por el sistema se muestra en un correo manejado por el administrador del sistema. Por medio de un análisis de las técnicas existentes utilizadas en el reconocimiento facial, se estableció la aplicación de la técnica denominada Análisis de Componentes Principales (PCA), que es utilizada por medio de funciones para el reconocimiento facial, siendo aplicada por medio de la herramienta de programación Visual Studio, como un método que transforma variables correlacionadas en otro grupo de variables no correlacionadas denominadas componentes principales, mediante un algoritmo de reducción dimensional denominado eigenfaces, creando vectores para una mejor representación de un grupo de imágenes. ABSTRACT The present project of investigation proposes the development a facial recognition system prototype destined to the recognized and identification of people in real time, it was done in the zonal direction 3 of the ECU 911, to be applied in the location of wanted individuals by the justice, which are identified in a list call “the most wanted”, with the principal objective increases the percentage of collective security providing a robust system that will be used in diferent places like as terminals, public transportation, etc. The system has a data base with the people register that were identified by the recognize system, a camera connected to the miniPC allows the facial images adquisition who pass through the system, making a image analysis previous with the functions and libraries to do an image processing, doing a comparison between the facial characteristics in the input image and the storage image by a face recognition algorithm, allowing identify the person wanted, sending a location alert in real time through the use of GPS coordinates in latitude and longitude, showing this information on a map in the monitoring interface , the alert message is sent by the system and is shown in an e-mail administered by the recognition system manager. Doing an analysis of the existing techniques used in facial recognition systems, it was determined the application of Principal Component Analysis (PCA), used through the facial recognition functions, it was applied with visual studio programming tools, like a method which convert correlated variables in another group of uncorrelated variables called principal components, making use of an algorithm called eigenfaces,creating vectors for a better representation of the images group.

Ingeniería en Sistemas, Electrónica e Industrial

Examinar

Filtros

Ajustes

Ordenar por

resultados por página

Resultados de la búsqueda