Estudio de arquitecturas para la extracción y explotación de datos de defectos superficiales mediante técnicas de Deep Learning
Autor:
Saiz-Álvaro, Fátima Aurora
Fecha:
26/07/2018Palabra clave:
Tipo de Ítem:
masterThesisResumen:
En este trabajo se realiza un estudio de arquitecturas de extracción y explotación de datos
sobre defectos superficiales producidos en la laminación del acero mediante técnicas de Deep
Learning, así como el almacenamiento de los datos en una arquitectura de Big Data y su
explotación empleando herramientas de Visual Analytics que permiten tomar decisiones
ágiles. Para ello se adquieren los datos con técnicas de visión por computador y se realizan
experimentos para configurar la explotación de los datos empleando redes neuronales y se
comparan los resultados y precisiones obtenidos con los del Estado del Arte actual,
comprobando que son mejorados. Se diseña una arquitectura para almacenar los datos de la
captura que se adapta a las necesidades de producción, garantizando la escalabilidad, la
seguridad y la rapidez. Por último, se desarrollan visualizaciones enfocadas a diferentes roles
de personas en la producción que aportan conocimiento sobre el estado de la fabricación y
permiten mejorar el proceso.
Descripción:
In this work a study of data extraction and mining architectures applied to superficial defects
produced in the steel-rolling using Deep Learning techniques is carried out, as well as the
storage of the data in a Big Data architecture and its exploitation using Visual Analytics tools
that allow making agile decisions. For this purpose, the acquisition of data using computer
vision is performed. Then, some experiments to configure the ideal acquisition of the data
using neural networks are carried out. The obtained results and accuracies are compared with
those of the current State of the Art, surpassing them. An architecture is designed according
the production needs to store captured data. This architecture guarantees scalability, security
and speed. Finally, some visualizations focused on different people-roles in production
environment are developed to provide knowledge about the state of manufacturing that allows
to improve the process.
Ficheros en el ítem
Este ítem aparece en la(s) siguiente(s) colección(es)
Estadísticas de uso
Año |
2012 |
2013 |
2014 |
2015 |
2016 |
2017 |
2018 |
2019 |
2020 |
2021 |
2022 |
2023 |
2024 |
Vistas |
0 |
0 |
0 |
0 |
0 |
0 |
22 |
655 |
529 |
465 |
406 |
117 |
145 |
Descargas |
0 |
0 |
0 |
0 |
0 |
0 |
14 |
694 |
431 |
535 |
328 |
216 |
143 |
Ítems relacionados
Mostrando ítems relacionados por Título, autor o materia.
-
COVID-19 Detection in Chest X-ray Images using a Deep Learning Approach
Saiz, Fátima; Barandiaran, Iñigo (International Journal of Interactive Multimedia and Artificial Intelligence (IJIMAI), 06/2020)The Corona Virus Disease (COVID-19) is an infectious disease caused by a new virus that has not been detected in humans before. The virus causes a respiratory illness like the flu with various symptoms such as cough or ... -
The importance of preventive training actions for the reduction of workplace accidents within the Spanish construction sector
Romero Barriuso, Alvaro ; Villena Escribano, Blasa María; Rodríguez Saíz, A. (Safety Science, 02/2021)The degree of compliance with occupational risk-prevention legislation among Construction Sector firms within Spain, most of which are micro-SMEs and SMEs, is studied in this research. Likewise, a meticulous analysis is ... -
Vaccine Hesitancy on Social Media: Sentiment Analysis from June 2011 to April 2019
Piedrahita-Valdés, Hilary; Piedrahita Castillo, Diego ; Bermejo-Higuera, Javier ; Guillem-Saiz, Patricia; Bermejo Higuera, Juan Ramón ; Guillem-Saiz, Javier; Sicilia, Juan Antonio ; Machío-Regidor, Francisco (Vaccines, 01/2021)Vaccine hesitancy was one of the ten major threats to global health in 2019, according to the World Health Organisation. Nowadays, social media has an important role in the spread of information, misinformation, and ...