Desarrollo de Modelos Supervisados para Regresión
Fecha
2024-09-20
Autores
Título de la revista
ISSN de la revista
Título del volumen
Editor
Jaén: Universidad de Jaén
Resumen
El uso de Ciencia de Datos mediante técnicas de Inteligencia Artificial permite extraer
conocimiento de forma automática en contextos de datos masivos reduciendo costos,
en tiempo y recursos, e incrementando el nivel de conocimiento. Sin embargo, a día de
hoy es difícil encontrar técnicas y modelos que sean capaces de describir los
fenómenos que subyace bajo los datos en entornos de aprendizaje supervisado en
problemas de regresión, es decir, cuando el resultado de aplicar una técnica de
aprendizaje automático es un número (no una clase) dentro de un conjunto finito de
resultados.
Este Trabajo Fin de Grado se centra en el diseño e implementación de modelos
descriptivos para regresión, en concreto, en el desarrollo de modelos difusos evolutivos
que nos permitan describir este tipo de problemas, y su aplicación a problemas reales.
The use of Data Science through Artificial Intelligence techniques allows to extract knowledge automatically in massive data contexts reducing costs in time and resources and increasing the level of knowledge. However, nowadays it is difficult to find techniques and models that are able to describe the phenomena underlying the data in supervised learning environments in regression problems, i.e., when the result of applying a machine learning technique is a number (not a class) within a finite set of results. This Final Degree Project focuses on the design and implementation of descriptive models for regression, in particular, on the development of evolutionary fuzzy models that allow us to describe this type of problems, and their application to real problems.
The use of Data Science through Artificial Intelligence techniques allows to extract knowledge automatically in massive data contexts reducing costs in time and resources and increasing the level of knowledge. However, nowadays it is difficult to find techniques and models that are able to describe the phenomena underlying the data in supervised learning environments in regression problems, i.e., when the result of applying a machine learning technique is a number (not a class) within a finite set of results. This Final Degree Project focuses on the design and implementation of descriptive models for regression, in particular, on the development of evolutionary fuzzy models that allow us to describe this type of problems, and their application to real problems.
Descripción
Palabras clave
Tratamiento inteligente de la Información