Publicación: Clasificación de operaciones de embalaje por parte de operarios para el OpenPack Challenge 2022
Cargando...
Fecha
2023
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial
Resumen
El Reconocimiento de la Actividad Humana (HAR, por sus siglas en inglés) es una disciplina dentro del aprendizaje automático que busca reconocer y clasificar actividades desempañadas por seres humanos utilizando para ello distintas fuentes de datos. El objetivo del Trabajo de Fin de Máster es desarrollar un modelo capaz de realizar Reconocimiento de la Actividad Humana en el marco del Open Pack Challenge 2022. OpenPack Challenge 2022 es una competición de reconocimiento de diez tipos distintos de actividades que se dan durante el proceso de embalaje por parte de operarios en un almacén. Los participantes que participan en la competición tratan de presentar el sistema que mejor realice la clasificación de cada una de estas actividades, que son una serie de movimientos que realizan los trabajadores en el desarrollo de su trabajo. La información acerca de cada uno de estos movimientos viene proporcionada por un conjunto de sensores (aceleración, temperatura, etc...) que los propios operarios portaban. Al final del proyecto, el resultado será un modelo que, tomando como entrada estos datos ordenados temporalmente, sea capaz de clasificar con un alto grado de precisión la clase (actividad) a la que pertenecen. A fecha de la realización del trabajo la competición ya ha finalizado, por lo que la realización del TFM servirá para comparar la solución desarrollada con las que alcanzaron mejor puntuación, y no para participar directamente.
Human Activity Recognition (HAR) is a discipline within machine learning that aims to recognize and classify activities performed by humans using various sources of data. The goal of the Master’s Thesis is to develop a model capable of performing Human Activity Recognition within the framework of the Open Pack Challenge 2022. The Open Pack Challenge 2022 is a competition to recognize ten different types of activities that occur during the packaging process by warehouse workers. Participants in the competition aim to present the system that best classifies each of these activities, which are a series of movements carried out by the workers in the course of their work. Information about each of these movements is provided by a series of sensors (acceleration, temperature, etc.) that the workers themselves wore. At the end of the project, the result will be a model that, taking these temporally ordered data as input, is capable of classifying with a high degree of accuracy the class (activity) to which they belong. As of the completion of the work, the competition has already concluded, so the completion of the Master’s Thesis will serve to compare the developed solution with those that achieved the highest scores, rather than participating directly.
Human Activity Recognition (HAR) is a discipline within machine learning that aims to recognize and classify activities performed by humans using various sources of data. The goal of the Master’s Thesis is to develop a model capable of performing Human Activity Recognition within the framework of the Open Pack Challenge 2022. The Open Pack Challenge 2022 is a competition to recognize ten different types of activities that occur during the packaging process by warehouse workers. Participants in the competition aim to present the system that best classifies each of these activities, which are a series of movements carried out by the workers in the course of their work. Information about each of these movements is provided by a series of sensors (acceleration, temperature, etc.) that the workers themselves wore. At the end of the project, the result will be a model that, taking these temporally ordered data as input, is capable of classifying with a high degree of accuracy the class (activity) to which they belong. As of the completion of the work, the competition has already concluded, so the completion of the Master’s Thesis will serve to compare the developed solution with those that achieved the highest scores, rather than participating directly.
Descripción
Categorías UNESCO
Palabras clave
Reconocimiento de la Actividad Humana, Aprendizaje profundo, Fusión de datos, Desafío
Citación
Centro
Facultades y escuelas::E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial