Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/64115
Title: | Analysis of aviation safety and aviation accidents |
Authors: | Grech, Jamie |
Keywords: | Aeronautics Aeronautics -- Safety measures Aeronautics -- Safety measures -- Databases Data mining |
Issue Date: | 2020 |
Citation: | Grech, J. (2020). Analysis of aviation safety and aviation accidents (Bachelor's dissertation). |
Abstract: | Aviation is a key method of transport in modern society and statistically also one of the safest. Despite this, some incidents are bound to happen when tens of millions of commercial flights are carried out on a yearly basis. Data mining is a process used to find new interesting information from large databases. This makes it an invaluable tool in any field of research where data is recorded on a large scale and the field of aviation safety is no exception. A multitude of data mining techniques has already been applied in this field in previous research efforts, using a variety of databases, some of the most notable being the United States’ National Transportation Safety Board (NTSB) aviation database and NASA’s Aviation Safety Reporting System (ASRS) database. Such databases can contain either structured data, unstructured data such as reports written by airport staff, or a mix of the two. For the purpose of this project we will focus on finding interesting correlations and deviations by applying association rule mining and contrast set mining techniques to structured data as obtaining information from the unstructured data would require the use of various natural language processing techniques. The results of the research and experimentation carried out in this project suggest that recent advancements in contrast set mining techniques make it possible to find more interesting information from aircraft incident and accident report data than was found in previous research by allowing the use of a wider variety of more complex features. On the other hand, it shows that the use of more complex features makes the use of association rule mining less effective as it is usually used with data containing binary features. |
Description: | B.SC.ICT(HONS)ARTIFICIAL INTELLIGENCE |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/64115 |
Appears in Collections: | Dissertations - FacICT - 2020 Dissertations - FacICTAI - 2020 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
20BITAI005 - Grech Jamie.pdf Restricted Access | 1.01 MB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.