Carregant...
Miniatura

Tipus de document

Treball de fi de grau

Data de publicació

Llicència de publicació

memòria: cc-by-nc-sa (c) Juan Luis Moral Pérez, 2016
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/103767

Estudio de imágenes de resonancia magnética funcional en reposo para la predicción de variables personales

Títol de la revista

Director/Tutor

ISSN de la revista

Títol del volum

Recurs relacionat

Resum

This project is focused on the creation of a classification system that separates a group of subjects according to their gender based on data from magnetic resonance images (MRI) in a resting state. The images from MRI in a resting state are a tool to measure the brain connectivity or functioning that is currently being used for many neuroscience studies. This project, in particular, uses the representation of facts based on the Network in a resting state to characterize the functional connectivity of the subjects for the visualization of the obtained results. As well as evaluating the accuracy of the classification system developed, another objective of the project is to determine which of the cerebral networks are more discriminative in the task of separating men and women. The mothodology utilized combines two types of automatic learning: unsupervised learning, as in the Independent Componentes Analysis and the Principal Components Analysis, and supervised learning, as is the K-NN and SVM classifiers. The results obtained are promising, because it finds a RSN that discriminates both sex and we also note that the Principal Component Analysis does not affect when classifying .

Descripció

Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2016, Director: Laura Igual Muñoz

Citació

Citació

MORAL PÉREZ, Juan luis. Estudio de imágenes de resonancia magnética funcional en reposo para la predicción de variables personales. [consulta: 23 de gener de 2026]. [Disponible a: https://hdl.handle.net/2445/103767]

Exportar metadades

JSON - METS

Compartir registre