Prediction of Injuries and Fatalities in Aviation Accidents through Machine Learning

This paper concerns application of various machine learning techniques to derive classification models for predicting conditions that increase the likelihood of aviation accidents involving fatalities and serious injuries. Machine learning classification techniques, including Decision Trees, K-Nearest Neighbors, Support Vector Machines (SVMs), and Artificial Neural Networks (ANNs) are applied to datasets derived from original data obtained from Federal Aviation Administration (FAA) Aviation Accident and Incident Records from 1975-2002. The accident data are filtered to focus on FAA Part 91 (General Aviation) accidents involving powered, fixed-wing, manufactured aircraft. The results demonstrate ANNs to yield the most accurate prediction levels for both fatal accidents and accidents involving severe injuries. The results also demonstrate that machine learning approaches may yield insightful information beyond what is available through traditional statistical analysis methodologies.

[1]  Douglas D Boyd,et al.  Causes and risk factors for fatal accidents in non-commercial twin engine piston general aviation aircraft. , 2015, Accident; analysis and prevention.

[2]  Olutayo V.A,et al.  Traffic Accident Analysis Using Decision Trees and Neural Networks , 2014 .

[3]  M. Hemalatha,et al.  A Perspective Analysis of Traffic Accident using Data Mining Techniques , 2011 .

[4]  Vitaly S. Guzhva,et al.  Impact of gender, age and experience of pilots on general aviation accidents. , 2011, Accident; analysis and prevention.

[5]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[6]  Ajith Abraham,et al.  Traffic Accident Analysis Using Decision Trees and Neural Networks , 2014 .

[7]  C F Booze,et al.  Epidemiologic investigation of occupation, age, and exposure in general aviation accidents. , 1977, Aviation, space, and environmental medicine.

[8]  Ajith Abraham,et al.  Traffic Accident Analysis Using Machine Learning Paradigms , 2005, Informatica.

[9]  Scott A. Shappell,et al.  A Human Error Analysis of Commercial Aviation Accidents Using the Human Factors Analysis and Classification System (HFACS) , 2001 .

[10]  G Li,et al.  Pilot-related factors in aircraft crashes: a review of epidemiologic studies. , 1994, Aviation, space, and environmental medicine.

[11]  David R. Hunter,et al.  Retrospective and Prospective Validity of Aircraft Accident Risk Indicators , 2001, Hum. Factors.

[12]  Kathleen L. McFadden,et al.  Comparing pilot-error accident rates of male and female airline pilots , 1996 .

[13]  S P Baker,et al.  Factors associated with pilot error in aviation crashes. , 2001, Aviation, space, and environmental medicine.

[14]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[15]  K L McFadden,et al.  Predicting pilot-error incidents of US airline pilots using logistic regression. , 1997, Applied ergonomics.

[16]  C E Billings,et al.  Human factors in aircraft incidents: results of a 7-year study. , 1984, Aviation, space, and environmental medicine.

[17]  D A Wiegmann,et al.  Human error analysis of commercial aviation accidents: application of the Human Factors Analysis and Classification system (HFACS). , 2001, Aviation, space, and environmental medicine.