Publicación: Estudio y predicciones de calidad del aire en la ciudad de Madrid
Cargando...
Fecha
2022-07-01
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial
Resumen
Este trabajo fin de máster contiene toda la información del estudio realizado sobre los niveles de calidad del aire de la ciudad de Madrid y también la incidencia que puede tener el tráfico sobre los niveles de los distintos parámetros que determinan la calidad. En una primera fase de trabajo se ha realizado un análisis previo de los conjuntos de datos que pone a disposición de los ciudadanos el ayuntamiento de Madrid. Una vez realizado el análisis exploratorio de los datos, se realiza un tratamiento sobre ellos para adecuarlos a las necesidades de los siguientes pasos que se realizan en el trabajo. En la siguiente fase se realiza un trabajo de clasificación sobre los datos ya limpios y preparados en la fase anterior. Para ello se realizan estudios estadísticos sobre los datos, y se adecúan a las necesidades de los algoritmos de clasificación para trabajar de una manera óptima y obtener resultados mejores. Los algoritmos de clasificación utilizados son: Naive Bayes, KNN y Bosques Aleatorios. Para finalizar, se han vuelto a analizar los datos y realizar los ajustes necesarios para su representación gráfica. Para ello se ha utilizado ATOTI y con ella se han implementado varios tipos de gráficos relevantes, donde se puede ver cómo se comportan los datos para sacar conclusiones de los mismos. Con varias de estas gráficas se ha preparado un cuadro de mandos para poder publicar los datos de una manera conjunta.
This master's thesis contains all the information from the study carried out on air quality levels in the city of Madrid and, also, the impact that traffic can have on the levels of the different parameters that determine quality. In a first phase of work, a preliminary analysis of the data sets made available to citizens by the Madrid City Council has been carried out. Once the exploratory analysis of the data has been carried out, a treatment will be carried out on them to adapt them to the needs of the following steps that are carried out in the work. In the next phase, it is about carrying out a classification work on the data already cleaned and prepared in the previous phase. For this, statistical studies will be carried out on the data, adapting to the needs of the classification algorithms to work optimally and obtain better results. The classification algorithms used are next: Naive Bayes, KNN and Random Forests. To finish, the data has been re-analyzed and the necessary adjustments have been made for its graphical representation, for this ATOTI has been used and with it several types of relevant graphs have been implemented, where you can see how the data behaves to draw conclusions from the same. With several of these graphs, a dashboard has been prepared to be able to publish the data jointly.
This master's thesis contains all the information from the study carried out on air quality levels in the city of Madrid and, also, the impact that traffic can have on the levels of the different parameters that determine quality. In a first phase of work, a preliminary analysis of the data sets made available to citizens by the Madrid City Council has been carried out. Once the exploratory analysis of the data has been carried out, a treatment will be carried out on them to adapt them to the needs of the following steps that are carried out in the work. In the next phase, it is about carrying out a classification work on the data already cleaned and prepared in the previous phase. For this, statistical studies will be carried out on the data, adapting to the needs of the classification algorithms to work optimally and obtain better results. The classification algorithms used are next: Naive Bayes, KNN and Random Forests. To finish, the data has been re-analyzed and the necessary adjustments have been made for its graphical representation, for this ATOTI has been used and with it several types of relevant graphs have been implemented, where you can see how the data behaves to draw conclusions from the same. With several of these graphs, a dashboard has been prepared to be able to publish the data jointly.
Descripción
Categorías UNESCO
Palabras clave
calidad del aire, tráfico, aprendizaje automático, clasificación, visualización de datos, air quality, traffic, machine learning, classification, data visualization
Citación
Centro
Facultades y escuelas::E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial