Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/149566
Title: | Big Data – Análisis de tráfico y optimización de rutas con machine learning |
Author: | Margineanu, Gabriel Adrian |
Tutor: | Molina Casasnovas, Rubén |
Others: | Monzo, Carlos |
Abstract: | This project will analyze an open access dataset using Big Data systems and methodologies about the behavior of vehicular traffic in the city of Madrid from July 2022 to June 2023. The study will analyze the traffic data to create a heatmap with the areas with the most traffic during each hour, depending on the day. This analysis will be used to create machine learning or artificial intelligence models to optimize routes. In this way we will be able to predict the traffic that will occur along the route. Several algorithms will be trained, optimized to shorten the route to obtain the most environmentally friendly route or to find the fastest route. These models could be used to reduce operating costs for delivery and transport companies by reducing journey times and the amount of pollution. The project only uses traffic data for the city of Madrid for one year in order to not increase the hardware complexity required during processing. It only serves as a model to demonstrate the feasibility and study of the required systems. For the analysis, a virtualized environment with containers will be used with PySpark to load and analyze the data. The different machine learning models and algorithms will be created with Python libraries. |
Keywords: | big data machine learning optimization distributed computing |
Document type: | info:eu-repo/semantics/masterThesis |
Issue Date: | 8-Jan-2024 |
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 | Size | Format | |
---|---|---|---|---|
gmargineanuTFM0124memoria.pdf | Memoria del TFM | 5,42 MB | Adobe PDF | View/Open |
Share:
This item is licensed under aCreative Commons License