Journal of Digital Convergence (디지털융복합연구)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of the Factors and Patterns Associated with Death in Aircraft Accidents and Incidents Using Data Mining Techniques

데이터 마이닝 기법을 활용한 항공기 사고 및 준사고로 인한 사망 발생 요인 및 패턴 분석

  • Kim, Jeong-Hun (Dept. of R&D, Korea Aerospace Industries) ;
  • Kim, Tae-Un (Dept. of Management Information Systems, Gyeongsang National University) ;
  • Yoo, Dong-Hee (Dept. of Management Information Systems, Gyeongsang National University)
  • 김정훈 (한국항공우주산업 개발본부) ;
  • 김태운 (경상대학교 경영정보학과) ;
  • 유동희 (경상대학교 경영정보학과)
  • Received : 2019.06.26
  • Accepted : 2019.09.20
  • Published : 2019.09.28
Download PDF
⟨ Previous Next ⟩

Abstract

This study analyzes the influential factors and patterns associated with death from aircraft accidents and incidents using data mining techniques. To this end, we used two datasets for aircraft accidents and incidents, one from the National Transportation Safety Board (NTSB) and the other from the Federal Aviation Administration (FAA). We developed our prediction models using the decision tree classifier to predict death from aircraft accidents or aircraft incidents and thereby derive the main cause factors and patterns that can cause death based on these prediction models. In the NTSB data, deaths occurred frequently when the aircraft was destroyed or people were performing dangerous missions or maneuver. In the FAA data, deaths were mainly caused by pilots who were less skilled or less qualified when their aircraft were partially destroyed. Several death-related patterns were also found for parachute jumping and aircraft ascending and descending phases. Using the derived patterns, we proposed helpful strategies to prevent death from the aircraft accidents or incidents.

본 연구에서는 데이터 마이닝 기법을 활용하여 항공기 사고와 준사고로 인한 사망 발생 요인들과 패턴들을 분석하고자 한다. 이를 위해, 항공기 사고와 준사고 데이터를 보유하고 있는 미국연방교통안전위원회(NTSB)와 미국연방항공청(FAA)의 데이터를 사용하였다. 다음으로 의사결정나무 알고리즘을 사용하여 항공기 사고 및 준사고에 따른 사망여부 예측모형들을 구축하였고 이를 토대로 사망 발생에 영향을 주는 주요 요인들과 패턴들을 도출하였다. NTSB 데이터의 경우 항공기가 완파되거나 고기동 또는 고위험 임무를 수행할 때 주로 사망이 발생하는 것을 알 수 있었다. FAA 데이터의 경우 항공기가 일부 파괴된 경우 조종사의 숙련도가 저조하거나 미인가 조종사의 경우 사망이 발생하였으며, 고공낙하점프와 지상운용단계에서 발생되는 다양한 사망관련 패턴들도 발견되었다. 또한 도출된 패턴들을 활용하여 사망 사고 예방을 위한 실용적인 방안들을 제시한 점에서 연구의 의의를 찾을 수 있다.

Keywords

References

  1. GAMA. (2016). 2016 General Aviation Statistical Databook & 2017 Industry Outlook, America, General Aviation Manufacturers Association.
  2. GOV. UK. (2015). Number of fatalities resulting from road accidents in Great Britain table. https://www.gov.uk/government/publications/annual-road-fatalities
  3. ICAO. International Investigation Standards. http://www.icao.org/icao/en/cat.htm
  4. S. B. Hong, W. Y. Kim & Y. C. Choi. (2012). The Trend Analysis about Aviation Accident and Incident in Korea Using the ECCAIRS Data. The journal of Korea Navigation Institute, 16(4), 687-696.
  5. W. Kim, S. Hong, M. Jie, G. Hong, D. Ahn & C. Choi. (2013). Analysis of Aviation Accident and Incident in Military Using the ECCAIRS 5. Journal of the Korean Society for Aviation and Aeronautics, 21(1), 80-86. https://doi.org/10.12985/ksaa.2013.21.1.080
  6. T. Roh & J. Park. (2014). An Explanatory Study on Air Accident Analyses and Strategy for Improvement in Air Safety. Journal of the Aviation Management Society of Korea, 12(4), 95-124.
  7. J. Chae. (2014). A study of the application of Big data analytics in Aviation Safety, master dissertation, Ewha Womans University, Seoul.
  8. A. Lukacova, F. Babic & J. Parali. (2014). Building the Prediction Model from Aviation Incident Data. IEEE 12th International Symposium on Applied Machine Intelligence and Information, 365-369.
  9. F. Gurbuz, L. Ozbakir & H. Yapici. (2009). Classification rule discovery for the aviation incidents resulted in fatality. Knowledge-based system, 22(8), 622-632. https://doi.org/10.1016/j.knosys.2009.06.013
  10. Z. Nareri, G. Donohue & L. Sherry. (2008). Analyzing Relationships Between Aircraft Accidents and Incidents - A data Mining Approach. In proceeding of Third International Conference on Research in Air Transportation, Virginia, US, 185-190.
  11. A. A. Christopher & S. A. alias Balamurugan. (2014). Prediction of warning level in aircraft accidents using data mining techniques. The Aeronautical Journal, 118(1206), 935-951. https://doi.org/10.1017/S0001924000009623
  12. A. D. Voogt & R. A. V. Doorn. (2007). Helicopter accident: Data-mining the NTSB database. European Rotorcraft Forum 33.
  13. K. Iwadare. (2015). Statistical Data Analyses on Aircraft Accidents in Japan: Occurrences, Causes and Countermeasures. American Journal of Operations Research, 5(3), 222-245. https://doi.org/10.4236/ajor.2015.53018
  14. NTSB. Aviation Accident Database. http://www.ntsb.gov/
  15. FAA. Accident and Incident Data System. http://www.asias.faa.gov/
  16. J. Lee. (2014). A Study on the Data Mining Preprocessing Tool For Efficient Database Marketing. Journal of Digital Convergence, 12(11), 257-264. https://doi.org/10.14400/JDC.2014.12.11.257
  17. J. Oh & S. Choi. (2018). An Analysis of the Characteristics of Companies Introducing Smart Factory System Using Data Mining Technique. Journal of the Korea Convergence Society, 9(5), 179-189. https://doi.org/10.15207/JKCS.2018.9.5.179
  18. J. Lee & H. Lee. (2018). Meltdown Threat Dynamic Detection Mechanism using Decision- Tree based Machine Learning Method. Journal of Convergence for Information Technology, 8(6), 209-215. https://doi.org/10.22156/CS4SMB.2018.8.6.209
  19. M. Park. (2018). Determinant of the Elderly Poverty Using Decision Tree Analysis. Journal of Digital Convergence, 16(7), 63-69. https://doi.org/10.14400/JDC.2018.16.7.063