Ingeniería en Sistemas, Electrónica e Industrial

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

Examinar

Filtros

2022 - 20265

Ajustes

Fecha de inicio: 2020Tema: search.filters.subject.PROCESAMIENTO DE IMÁGENES

Resultados de la búsqueda

Mostrando 1 - 5 de 5
  • Miniatura
    Item type:Ítem,
    Aplicativo web potenciado con IA para la programación de partidos y validación automatizada de datos en la Liga Deportiva Parroquial Huachi Chico
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software., 2026-07-06)
    Muyulema Pungaña, Jose Elias
    ;
    Jara Moya, Santiago David
    ;
    Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas Electrónica e Industrial. Carrera de Software.
    This research focuses on the development of an AI-powered web application for match scheduling and automated data validation in the Liga Deportiva Parroquial Huachi Chico, an organization that has been operating through manual processes. The study evaluated to what extent this solution reduces institutional operational times. A mixed-methods approach with census sampling (N = 65) was applied: a survey of 63 delegates (α = 0,810) and interviews with 2 board members. The diagnosis confirmed that 69.8 % consider manual fixture creation inefficient and 74.6 % report a lack of tools. To address this, image processing and scheduling algorithms were investigated; YOLOv8 and EasyOCR were selected for automatic identity validation, integrating them with Round Robin and Backtracking to optimize match scheduling. Based on these foundations, the application was developed under the RAD methodology using Laravel and Angular. Efficiency was determined through a controlled evaluation by macro-processes using the Time-on-Task metric (ISO 9241-11:2018) across five attempts. Registration decreased from 14.00 min to 2.25 min (83.93 %) including user interaction time; in contrast, the figures for fixture generation (from 150 min to 0.024 ms, >99.98 %) and scheduling (from 120 min to 8.95 ms, >99.99 %) corresponded exclusively to the computational time of the algorithm.
  • Miniatura
    Item type:Ítem,
    Sistema de reconocimiento inteligente de facturas aplicado a la gestión de inventarios para cota, estudio de arquitectura e ingeniería.
    (2026)
    Miranda Tustón Dallin Alexander
    ;
    Caiza Caizabuano José Rubén
    ;
    Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Software
    In the construction sector, automating processes leads to significant savings of time and resources, which is why it has become a priority for achieving better results. This project focuses on implementing a web-based inventory management system for the company COTA, integrating optical character recognition technologies and Artificial Intelligence for the automatic processing of invoices, along with a responsive web interface. This proposal addresses the manual handling of inventory and promotes the use of modern technologies. The implementation used the library provided by Ollama to communicate with its server, sending images accompanied by a specific prompt to extract the desired structure with key invoice data: product name, unit of measure, quantity, and unit price. For greater data security and integrity once extracted, the information is presented to the user, who can review each detail to edit, confirm, or reject it before storage. This implementation was carried out using the open-source model Qwen3-VL:2B, which provides an F1 Score of 85.58% for numerical data extraction using the exact matching method for evaluation, while for text extraction it achieved an accuracy of 94.92% using the Levenshtein Distance calculation. Overall, it offers a 66.35% reduction in time for this activity, as the AI is 2.97 times faster than data extraction.
  • Miniatura
    Item type:Ítem,
    Procesamiento de radiografía de tórax mediante morfología matemática para facilitar la identificación de problemas óseos
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2024-08)
    Pazmiño Sanguil, Mario Fernando
    ;
    Benalcázar Palacios, Freddy Geovanny
    Chest x-ray is the most frequently performed radiological analysis on patients; However, the assessment of bone pathologies through these studies has been lagged by doctors, so the present research work focuses on the detection of cervical rib pathologies and enchondroma or bone infarction, with the in order to provide assistance and support to doctors, so that they have a tool that allows them to make a more efficient and timely diagnosis of their patients. The study focuses on the development of an algorithm that allows determining whether or not the anomalies under analysis are suffering, and subsequently highlighting and displaying them for the knowledge of the doctor and the patient. To carry out the work, the information contained in the database provided by BIMCV (Medical Image Bank of the Valencian Community) was taken; the processing of the images was carried out with Mathematical Morphology, mainly based on the use of filters. The results obtained indicate a detection sensitivity greater than 90%, and a specificity greater than 95%, which proves the behavior of the developed algorithm, this is corroborated with the validation carried out by a Traumatologist. The determining factor for bone pathologies to be detected and highlighted is the establishment of detection thresholds, this is because x-rays have certain differences in positioning and image quality, in addition to the location, shape and size of the pathologies
  • Miniatura
    Item type:Ítem,
    Sistema electrónico de entrenamiento de salto de longitud mediante visión artificial aplicado a deportistas con discapacidad visual
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Ingeniería en Electrónica y Comunicaciones, 2024-02)
    Arias Gualpa, Oscar Eduardo
    ;
    Gordón Gallegos, Carlos Diego
    This research project describes the development of a training system for athletes with visual impairment supported by artificial vision. Initially, a study was carried out on the current state of the difficulties that visually impaired athletes are exposed to when doing any sport, and thanks to the advancement of artificial vision in the different application areas, an electronic system based on hardware and software that allows the long jump training process to be carried out, in such a way that the athlete can be monitored and controlled, avoiding complications and injuries during training. The main objective of the electronic training system is based on the processing of images, these images depend on deep learning (Deep Learning), which reaches different levels of hierarchical details, so that the information that flows upwards is united, creating abstractions. and higher and more complex representations. For example, with digital images, pixels are combined into edges, edges into outlines, outlines into shapes, and finally shapes into objects. Obtaining as a result the recognition of the long jump track and the athletes in it. The system consists of 3 stages, the first stage of image acquisition, consisting of the sony wcx550 webcam that allows obtaining images in real time. In the second stage, processing, stable results were obtained, thanks to the use of a Raspberry Pi B3+ single-board computer, which processes the information obtained in the image acquisition stage and helps to detect people, contour detection and data management for the alert management stage. The system sends detection alerts for presence on the runway, alerts for the jump performed and stores the number of tests performed. The system will provide security and confidence, at the time of training, both to the athlete with visual impairment, and to the coach.
  • Miniatura
    Item type:Ítem,
    Controlador para alimentación de peces empleando Deep Learning
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Maestría en Electrónica y Automatización, 2022)
    Cañar Yumbolema, Willam Patricio
    ;
    Galarza Zambrano, Eddie Egberto
    This degree project consists of the design and implementation of a controller for fish feeding using Deep Learning for which a Raspberry minicomputer and a lowcost Web camera were used, this significantly reduced the investment for project development. The main objective consists in the creation of a manually labeled dataset (set of images) of several zebra-type fish (Danio Rerio) located inside a fish tank uniformly illuminated by white LED light. In this case, it was decided to use two videos with the presence of 4 and 6 fish, respectively. Through the use of a computational algorithm, the sequence of images of the fish where their movements can be identified were obtained. This information is used to train a convolutional network using the ACF (Aggregated Channel Characteristics) image object detection algorithm. Once the location of the fish inside the fish tank is determined, the feeling of the school is identified through the implementation of three zones, that is, the developed algorithm will allow knowing if the fish are in a satisfaction zone, a normal zone or a normal zone. feeding. Finally, the FuzzySN, FuzzySH and FuzzyNH indices contain the feeling of the fish and are the inputs of a fuzzy controller which in turn contains the feeding rules based on the natural behavior of the fish; In this way, the developed system is capable of feeding the fish automatically. The minimum identification error reached was 29.5%, but the identification of the behavior of the school of fish had a success rate of 100%. The test carried out to validate the algorithm was given for a case of manual feeding by an operator, where the system was able to correctly identify the feeling of the school as satisfied.