Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/147550
Title: | Detección de amenazas cercanas en la ciudad mediante el uso de redes sociales |
Author: | Arnedo Nieto, Daniel |
Tutor: | Crespo García, David |
Others: | Monzo, Carlos |
Abstract: | Social networks are an increasingly ingrained tool in today’s society to the point that they can significantly influence our lives to be in touch with family members and friends, receive breaking news, notifications of celebrities or events or even to acquire new and interesting cultural information. This project proposes to design a prototype capable of extracting useful information from social media publications to detect emergencies, anomalies, violent or alarming events that could endanger more civilians than those already involved. For this purpose, Twitter is chosen as a social reference network, from where information will be extracted from different publications. This information will be analyzed using several Machine Learning algorithms that will detect events that involve a certain degree of risk. This process will also be supported by graphical analysis to facilitate understanding of the data collected and exploited in a simple way without requiring complex knowledge in the Artificial Intelligence area. The aim of this design is to obtain a scalable product and easily integrated with other technologies to make possible to interconnect with a large number of people through any electronic device they carry on and receive alerts of detected events to avoid future risks. |
Keywords: | smart cities machine learning artificial intelligence |
Document type: | info:eu-repo/semantics/masterThesis |
Issue Date: | 9-Jan-2023 |
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 | |
---|---|---|---|---|
darnedonTFM0123memoria.pdf | Memoria del TFG | 2,09 MB | Adobe PDF | View/Open |
darnedonTFM0123presentacion.pdf | Presentación del TFG | 927,37 kB | Adobe PDF | View/Open |
Share:
This item is licensed under aCreative Commons License