Reglas discriminantes en el análisis multivariante y su adaptación a la alta dimensión
Loading...
Identifiers
Publication date
Authors
Advisors
Tutors
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Este trabajo trata sobre el análisis discriminante y la introducción de algunos métodos de
clasificación, tanto tradicionales como de creación más moderna. En el primer capítulo se presentan las nociones básicas de clasificación, así como dos reglas discriminantes clásicas: la lineal y la cuadrática. Además, se describen algunas generalizaciones de estas reglas, como las máquinas de vector soporte, que buscan suplir muchas de las deficiencias de los métodos más tradicionales. En el segundo capítulo se explican diversas técnicas de clasificación adaptadas al contexto del Big Data, donde la dimensión o, equivalentemente, el número de variables, es mayor que el tamaño de la muestra. Finalmente, el último capítulo ilustra el funcionamiento de estas reglas en conjuntos de datos simulados y mediante su aplicación a dos bases de datos reales
The aim of this project is to introduce discriminant analysis and some classification techniques, both traditional and modern. In the first chapter, basic notions for classification and two classic discrimination rules, linear and quadratic, are presented. Furthermore, this chapter also describes some generalizations of these rules, such as the support vector machines, that seek to make up for many of the deficiencies of the more traditional methods. The second chapter discusses several classifcation techniques in the Big Data context, where the dimension or, in other words, the number of variables, is bigger than the sample size. Finally, the last chapter illustrates the performance of these rules in simulated datasets and through their application on two real databases
The aim of this project is to introduce discriminant analysis and some classification techniques, both traditional and modern. In the first chapter, basic notions for classification and two classic discrimination rules, linear and quadratic, are presented. Furthermore, this chapter also describes some generalizations of these rules, such as the support vector machines, that seek to make up for many of the deficiencies of the more traditional methods. The second chapter discusses several classifcation techniques in the Big Data context, where the dimension or, in other words, the number of variables, is bigger than the sample size. Finally, the last chapter illustrates the performance of these rules in simulated datasets and through their application on two real databases
Description
Traballo Fin de Grao en Matemáticas. Curso 2021-2022
Keywords
Bibliographic citation
Relation
Has part
Has version
Is based on
Is part of
Is referenced by
Is version of
Requires
Sponsors
Rights
Atribución-NoComercial-CompartirIgual 4.0 Internacional



