Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/107266
Title: Estudio del conjunto de datos NHANES mediante el empleo de técnicas de aprendizaje no supervisado
Author: Sánchez Temporal, Raúl
Director: Prados Carrasco, Ferran  
Tutor: Subirats, Laia  
Abstract: The National Survey of Health and Nutrition Survey (NHANES) data set provided by the Center for Disease Control and Prevention (CDC) is a unique opportunity to conduct research and analysis that can help improve the health of people. This paper proposes the use of unsupervised learning techniques applied to NHANES data in order to detect patterns that adapt to patients based on their similarities by finding natural groups (clusters) for them. Specifically, the work focuses on the use of methods of grouping methods in density and hierarchical methods. In addition, a web interface is created that allows the classification of patients in the different clusters that are generated. For the development of the work, the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology is followed, which is widely adopted for data mining projects that describe the life cycle where the necessary tasks are defined for each phase.
Keywords: NHANES
machine learning
clustering
Document type: info:eu-repo/semantics/masterThesis
Issue Date: Jan-2020
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
rsancheztemTFM0120memoria.pdfMemoria del TFM9,01 MBAdobe PDFThumbnail
View/Open
rsancheztemTFM0120presentación.pdfPresentación del TFM8,46 MBAdobe PDFThumbnail
View/Open