Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/108266
Title: Estimación de la calidad del aire de Galicia mediante técnicas de machine-learning
Author: Camí Núñez, Víctor
Director: Casas-Roma, Jordi  
Tutor: Parada Medina, Raúl  
Abstract: The air quality and the harmful effect that a bad quality of the air has on human health is a topic which is getting more and more relevance. Due to this, lots of cities and regions have measurement systems of the different pollutant elements which are present in the air. These measurements are used to active the different anti-pollutant protocols that these regions have established. Due to the fact that the data about the different elements is accessible, it is possible to implement data mining techniques in order to create predictive models. These models must be able to predict concentrations of each element with sufficient anticipation in order to be able to active the anti-pollutant protocols or to apply the corrective measures to avoid high pollutant scenarios. The aim of this work is the generation of some predictive models using open data in order to predict the different concentrations of the pollutant elements in Galicia using the next data mining techniques: SVR, MLP and LSTM. Moreover, in this work has also been studied the effect on the predictions when the models tries to predict the concentrations with a higher number of days of anticipation in order to see the maximum number of days in advance which is possible to produce predictions with enough quality to be useful. Furthermore, it has been tried to generate a unified model for Galicia using only the data of some of its cities.
Keywords: machine learning
air quality
prediction
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 8-Jan-2020
Publication license: http://creativecommons.org/licenses/by-nc-sa/3.0/es/  
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
vcamiTFM0120memoria.pdfMemoria del TFM2,32 MBAdobe PDFThumbnail
View/Open

presentación_TFM_vcami.mp4

93,5 MBMP4View/Open