Use this link to cite:
http://hdl.handle.net/2183/31977 Análisis de los datos del transporte público de Madrid y deducción de la parada de bajada para cada trayecto
Loading...
Identifiers
Publication date
Authors
Other responsabilities
Journal Title
Bibliographic citation
Type of academic work
Academic degree
Abstract
[Resumen] El objetivo de este trabajo de fin de grado es deducir las paradas de bajada para cada
trayecto en la red de transporte público de Madrid.
Para conseguir este objetivo, primero fue necesario realizar un proceso de análisis, limpieza
y transformación de los datos facilitados por el Consorcio Regional de Transportes de
Madrid. A continuación, se comenzó con el proceso deductivo aplicando diversos métodos. En
primer lugar se aplicaron reglas de decisión y después distintas técnicas de Inteligencia Artificial.
Por último, se realizó una comparativa entre los resultados obtenidos mediante ambos
métodos a partir de la cual pudimos obtener conclusiones.
Durante la investigación se utilizó SQL Server y SQL para llevar a cabo las reglas de decisión.
Para la ejecución de las técnicas de Inteligencia Artificial, se utilizó principalmente
Python y varias librerias para la gestión de datos y aplicación de técnicas de IA.
Se han conseguido resultados muy prometedores llegando a alcanzar un 87% de precisión
con el algoritmo de bajadas basado en reglas de decisión y un 75% de precisión con una de las
técnicas de Inteligencia Artificial implementadas.
[Abstract] This final dregee project aims to predict the alighting stop for each trip in the public transport network of Madrid. In order to accomplish this objective, it was necessary to carry out through an analysis, cleaning and transformation process of the data given by the Consorcio Regional de Transportes de Madrid. Next, was when the deductive process started by using different techniques. In the first place, we applied various decision rules, and then we used several artifical intelligence techniques. Lastly, we performed a comparison between the results obtained by these two different methods, and we were able to drew conclusions. Meanwhile, during the investigation process it was necessary to use SQL Server and SQL to implement the decision rules. To execute the artificial intelligence techniques, we mainly used Python combined with some software libraries for the data management and the implementation of the AI methods. We achieved very promising results reaching a precision of 87% with the decision rules algorithm and a precision of 75% with one of the artificial intelligence techniques implemented.
[Abstract] This final dregee project aims to predict the alighting stop for each trip in the public transport network of Madrid. In order to accomplish this objective, it was necessary to carry out through an analysis, cleaning and transformation process of the data given by the Consorcio Regional de Transportes de Madrid. Next, was when the deductive process started by using different techniques. In the first place, we applied various decision rules, and then we used several artifical intelligence techniques. Lastly, we performed a comparison between the results obtained by these two different methods, and we were able to drew conclusions. Meanwhile, during the investigation process it was necessary to use SQL Server and SQL to implement the decision rules. To execute the artificial intelligence techniques, we mainly used Python combined with some software libraries for the data management and the implementation of the AI methods. We achieved very promising results reaching a precision of 87% with the decision rules algorithm and a precision of 75% with one of the artificial intelligence techniques implemented.
Description
Editor version
Rights
Atribución-NoComercial-SinDerivadas 3.0 España







