Expanding Aviation Knowledge Graph Using Deep Learning for Safety Analysis

Files
jing-et-al-2024-expanding-aviation-knowledge-graph-using-deep-learning-for-safety-analysis.pdf (1.67 MB)
Author(s)
Jing, Xiao
Sawant, Kshitij
Bendarkar, Mayank V.
Elias, Lidya R.
Advisor(s)
Editor(s)
Associated Organization(s)
Organizational Unit
Daniel Guggenheim School of Aerospace Engineering
The Daniel Guggenheim School of Aeronautics was established in 1931, with a name change in 1962 to the School of Aerospace Engineering
Organizational Unit
Series
Collections
Scholarly Events
Supplementary to:
Permanent Link
https://hdl.handle.net/1853/78776
Abstract
This study outlines the expansion and applications of Aviation Knowledge Graph (Aviation-KG), available openly, with a focus on aviation safety. Using Deep Learning (DL) Natural Language Processing (NLP) models like Aviation-BERT, this study emphasizes the expansion of Aviation-KG to encompass a broad range of aviation safety data. The approach integrates complex data structures with intelligent querying systems, creating a robust platform for detailed analysis of aviation incidents. This integration enables more effective analysis and processing of aircraft accident and incident data, contributing significantly to both retroactive and proactive risk management and the enhancement of aviation safety standards.
Sponsor
U.S. Federal Aviation Administration (FAA), Top-down Safety Risk Modeling for Facilitating Bottom-up Safety Risk Assessment project, Award Number 692M15-21-F-00225
Date
2024-07-27
Extent
Resource Type
Text
Resource Subtype
Rights Statement
Unless otherwise noted, all materials are protected under U.S. Copyright Law and all rights are reserved
Rights URI
https://rightsstatements.org/page/InC/1.0/?language=en