Abstract
The safety concept primarily examines the most fatal (resulting in dead passengers) accidents of aviation history in this study. The primary causes of most fatal accidents are; human, technical, and sabotage/terrorism factors. Although the aviation industry started with the first engine flight in 1903, the safety concept has been examined since the 1950s. The safety concept firstly examined the technical factors, and in the late 1970s, human factors started to analyze. Despite these primary causes, there have different factors that affect accidents. So, the study aims to determine the affecting factors of the most fatal accidents to classify the survivor/non-survivor passenger numbers. Logistic regression and discriminant analysis are used as multivariate statistical analyses to compare with the machine learning approaches showing the algorithms’ robustness. In this study, machine learning techniques have better performance than multivariate statistical methods in terms of accuracy, false-positive rate, and false-negative rate. In conclusion, the phase of flight, the primary cause, and total passenger numbers are determined as the most affected factors in machine learning and multivariate statistical models for classifying the accidents’ survivor/non-survivor passenger numbers.
Keywords: Machine learning; primary causes; fatal aviation accidents; classification of survivor/non-survivor passengers; multivariate statistical analysis.
Acknowledgements
Declaration of Competing Interest
The authors declare no potential conflicts of interest with respect to the research, authorship, and/or publication of this paper.
Author Contributions
Corresponding Author Tüzün Tolga İNAN: Data curation, Conceptualization, Investigation, Writing, Original draft preparation, Reviewing and Editing, Supervision, Resources
Scholarly Commons Citation
İNAN, T. T.
(2022).
Classifıcation of Survivor/Non-Survivor Passengers in Fatal Aviation Accidents: A Machine Learning Approach.
International Journal of Aviation, Aeronautics, and Aerospace,
9(1).
DOI: https://doi.org/10.15394/ijaaa.2022.1672
