Examination of Aircraft Accidents That Occurred in the Last 20 Years in the World

Abstract

Air transportation is a very preferred type of transportation for long-distance trips. This type of transportation has made great progress, especially in the last 20 years with the development of technology. Thanks to its fast and safe, passenger capacity is gradually increasing. Despite this situation, the mortality rate is quite high in the case of an aircraft accident. For this reason, hundreds of people can die in a single accident. In this study, aircraft accidents that occurred in the last 20 years in the world were examined. The data including the number of accidents, the number of deaths and the process of the flight where the accidents occurred were used. These data were analyzed using data mining algorithms such as multi-layer perceptron, k nearest neighborhood, Naive Bayes, J48 and regression methods. Accordingly, it was determined that the algorithm that gives the best results for error scale and performance analysis among five different algorithms is J48. Using this algorithm, the occurrence flight phase of aircraft accidents is classified in more detail. Thanks to this study, it has been revealed that choosing the J48 algorithm for the classification of similar data sets will give better results. Also, this study provides significant benefits in terms of getting to the center of the problems, as the stages of accidents are more detailed. Accordingly, it is possible to reduce accidents if policy makers carry out studies taking into account the stages in which accidents occur.

Keywords

• Aircraft accidents
• Accident analysis
• Air transportation

Dünyada Son 20 Yılda Meydana Gelen Uçak Kazalarının İncelenmesi

Abstract

Hava taşımacılığı uzun mesafeli yolculuklar için çok tercih edilen bir ulaşım türüdür. Bu tip ulaşım, özellikle son 20 yılda teknolojinin gelişmesiyle büyük ilerleme kaydetmiştir. Bu ulaşım türünün hızlı ve güvenli olması sayesinde yolcu kapasitesi giderek artmaktadır. Bu duruma rağmen, bir uçak kazası meydana gelmesi durumunda ölüm oranı oldukça yüksektir. Bu sebeple yüzlerce insan tek bir kazada ölebilmektedir. Bu çalışmada, son 20 yılda dünyada meydana gelen uçak kazaları incelenmiştir. Kaza sayıları, ölüm sayıları ve kazaların uçuşun hangi aşamasında meydana geldiğini içeren veriler kullanılmıştır. Bu veriler veri madenciliği algoritmaları olan çok katmanlı algılayıcı, k en yakın komşuluk, Naive Bayes, J48 ve regresyon yöntemleri kullanılarak analiz edilmiştir. Buna göre, beş farklı algoritmadan, hata ölçeği ve performans analizi için en iyi sonuçları veren algoritmanın J48 olduğu belirlenmiştir. Bu algoritma kullanılarak uçak kazalarının meydana gelme aşamaları daha detaylı halde sınıflandırılmıştır. Yapılan bu çalışma sayesinde benzer veri kümelerinin sınıflandırma işlemi için J48 algoritmasının tercih edilmesinin daha iyi sonuçlar vereceği ortaya konmuştur. Ayrıca bu çalışmada kazaların meydana geldiği aşamalar daha detaylandırıldığı için problemlerin merkezine inme adına önemli fayda sağlamaktadır. Bu doğrultuda politika yapıcılar kazaların meydana geldiği aşamaları dikkate alarak çalışmalar yürütürse kazaları azaltabilmek mümkündür.

Keywords

• Uçak kazaları
• Hava taşımacılığı
• Kaza analizi

References

1. [1] M. Terzioğlu, “Human errors as a cause of aircraft accidents can be reduced through crew resource management,” Master thesis, Department of Human Resources, Dokuz Eylul University, İzmir, Turkey, 2007.
2. [2] K. Dönmez, and S. Uslu, “A study on communication induced accidents and incidents in aviation,” The Journal of International Social Research, vol. 9, pp. 1074–1079, 2016.
3. [3] S. Metin, “Human factors in aviation accidents in last years,” in 1. National Aviation Medicine Congress, 2014, pp. 22–24.
4. [4] H. Kharoufah, J. Murray, G. Baxter, and G. Wild, “A review of human factors causations in commercial air transport accidents and incidents: From to 2000–2016,” Progress in Aerospace Sciences, vol. 99, pp. 1–13, 2018.
5. [5] V. Andersen, and T. Bove, “A feasibility study of the use of incidents and accidents reports to evaluate effects of team resource management in air traffic control,” Safety Science, vol. 35, pp. 87–94, 2000.
6. [6] V. Socha, L. Socha, S. Szabo, and V. Němec, “Air accidents, their investigation and prevention,” Economy, Society, Environment, vol. 4, pp. 1-9, 2014.
7. [7] C. V. Oster, J.S. Strong, and C.K. Zorn, “Analyzing aviation safety: Problems, challenges, opportunities,” Research in Transportation Economics, vol. 43, pp. 148–164, 2013.
8. [8] T. Lyu, W. Song, and K. Du, “Human factors analysis of air traffc safety based on HFACS-BN model,” Applied Sciences, vol. 9, pp. 1-19, 2019.

9. [9] M. Bazargan, and V.S. Guzhva, “Impact of gender, age and experience of pilots on general aviation accidents,” Accident Analysis and Prevention, vol. 43, pp. 962–970, 2011.
10. [10] W.C. Moon, K.E. Yoo, and Y.C. Choi, “Air traffic volume and air traffic control human errors,” Journal of Transportation Technologies, vol. 01, pp. 47–53, 2011.
11. [11] C. V. Oster, J.S. Strong, and C. Kurt Zorn, “Investigation of accidents related to air traffic control,” in 51st Annual Transportation Research Forum 2010, 2010, pp. 853–872.
12. [12] S. Uslu, and K. Dönmez, “Investigation of accidents related to air traffic control,” Mehmet Akif Ersoy University Journal of Social Sciences Institute, vol. 8, pp. 271–287, 2017.
13. [13] D.D. Boyd, “General aviation accidents related to exceedance of airplane weight/center of gravity limits,” Accident Analysis and Prevention, vol. 91, pp. 19–23, 2016.
14. [14] S.Z.Y.L. Cheng, R.M.A. Valdés, V.F.G. Comendador, and F.J.S. Nieto, “Detection of common causes between air traffic serious and major incidents in applying the convolution operator to heinrich pyramid theory,” Entropy, vol. 21, 2019.
15. [15] W. Kaleta, and J. Skorupski, “A fuzzy inference approach to analysis of lpv-200 procedures influence on air traffic safety,” Transportation Research Part C, vol. 106, pp. 264–280, 2019.
16. [16] G.W.H. Van Es, “A review of civil aviation accidents air traffic management related accidents : 1980-1999,” in 4th International Air Traffic Management R&D Seminar, 2001, pp. 1–10.
17. [17] J. Skorupski, “The simulation-fuzzy method of assessing the risk of air traffic accidents using the fuzzy risk matrix,” Safety Science, vol. 88, pp. 76–87, 2016.
18. [18] W.K. Lee, “Risk assessment modeling in aviation safety management,” Journal of Air Transport Management, vol. 12, pp. 267–273, 2006.
19. [19] M. Lower, J. Magott, and J. Skorupski, “Analysis of air traffic incidents using event trees with fuzzy probabilities,” Fuzzy Setsand Systems, vol. 293, pp. 50–79, 2016.
20. [20] L. Guerra, T. Murino, and E. Romano, “Airport system analysis : a probabilistic risk assessment model,” International Journal of Systems Applications, Engineering & Development, vol. 2, pp. 52–65, 2008.
21. [21] S.H. Stroeve, H.A.P. Blom, and G.J. (Bert) Bakker, “Systemic accident risk assessmenti air traffic by monte carlo simulation,” Safety Science, vol. 47, pp. 238–249, 2009.
22. [22] P. Brooker, “Air traffic management accident risk. part 1: the limits of realistic modelling,” Safety Science, vol. 44, pp. 419–450. 2006.
23. [23] P. Brooker, “Air traffic management accident risk. part 2: Repairing the deficiencies of ESARR4,” Safety Science, vol. 44, pp. 629–655, 2006.
24. [24] S.C. Kabasakal, “Human factor errors in aircraft maintenance, in: air force command,” in Aviation Safety Management Systems Symposium, 2017, pp. 127–177.
25. [25] H. İncekaş, “Increasing flight safety and preventing accident crimes android based checklist,” Master thesis, Department of Computer Engineering, İzmir Katip Çelebi University, İzmir, Turkey, 2017.
26. [26] Y.Ş. Murat and Z. Çakıcı, “An integration of different computing approaches in traffic safety analysis,” Transportation Research Procedia, vol. 22, pp. 265-274, 2017.
27. [27] Y.Ş. Murat and A. Şekerler, “Modelling traffic accident data by clustering approaches,” Technical Journal of Turkish Chamber of Civil Engineers , vol. 20, pp. 4759-4777, 2009.
28. [28] Y.Ş. Murat, “An entropy (shannon) based traffic safety level determination approach for black spots,” Procedia, Social and Behavioral Sciences, vol. 20, pp. 786-795, 2011.
29. [29] Anonymous. (2020, January 20). Number of flights performed by the global airline industry from 2004 to 2020 [Online]. Available: https://www.statista.com/statistics/564769/airline-industry-number-of-flights/.
30. [30] Anonymous. (2020, January 21). Airline accident statistics [Online]. Available: https://aviation-safety.net/statistics/period/stats.php.
31. [31] Anonymous. (2020, January 21). Waikato environment for knowledge analysis (WEKA) [Online]. Available: https://tr.wikipedia.org/wiki/Weka.
32. [32] Anonymous. (2020, January 19). Multilayer perceptron [Online]. Available: http://www.deeplearning.net/tutorial/mlp.html.
33. [33] Anonymous. (2020, January 19). Multilayer perceptron [Online]. Available: https://medium.com/@isikhanelif/multi-layer-perceptron-mlp-nedir-4758285a7f15.
34. [34] Anonymous. (2020, January 22). A beginner’s guide to multilayer perceptron [Online]. Available: https://pathmind.com/wiki/multilayer-perceptron.
35. [35] M.C. Mihǎescu, “Classification of learners using linear regression,” in 2011 Federated Conference on Computer Science and Information Systems (FedCSIS), 2011, pp. 717–721.
36. [36] Anonymous. (2020, February 4). Linear regression [Online]. Available: https://tr.wikipedia.org/wiki/Regresyon_analizi.
37. [37] Anonymous. (2020, February 1). Instance based learning [Online]. Available: https://en.wikipedia.org/wiki/Instance-based_learning.
38. [38] Anonymous. (2020, January 17). Nearest neighbor and server-side library [Online]. Available: https://www.ibm.com/develop erworks/library/os-weka3/index.html.
39. [39] Ü. Çavuşoğlu, and S. Kaçar, “Performance analysis of data mining algorithms for abnormal traffic detection,” Academic Platform Journal of Engineering and Science, vol. 7-2, pp. 205-216, 2019.
40. [40] K. Atmaca. (2020, January 10). Naive Bayesian algorithm [Online]. Available: https://kenanatmaca.com/naive-bayesian-algoritmasi/.
41. [41] Anonymous. (2020, January 10). Naive Bayesian algorithm [Online]. Available: http://kod5.org/naive-bayes-algoritmasi/.
42. [42] G.S. Eraldemir, M.T. Arslan, and E. Yildirim, “Comparison of random forest and J48 decision tree,” in International Advanced Researches & Engineering Congress, 2017, pp. 1250–1256.
43. [43] A.M. Hormann, “Programs for machine learning. Part II,” Information and Control, vol. 7, pp. 55-57, 1964.
44. [44] K.R. Pradeep, and N.C. Naveen, “Predictive analysis of diabetes using J48 algorithm of classification techniques,” in 2nd Int. Conf. on Contemporary Computing and Informatics, 2016, pp. 347–352.
45. [45] P. Paranjape, M. Dhabu, and P. Deshpande, “A novel classifier for multivariate instance using graph class signatures,” Frontiers of Computuer Sciences, vol. 14, 2020.
46. [46] S. Aljawarneh, M.B. Yassein, and M. Aljundi, “An enhanced J48 classification algorithm for the anomaly intrusion detection systems,” Cluster Computing, vol. 22, pp. 1–17, 2019.
47. [47] T.C. Smith, and E. Frank, “Introducing machine learning concepts with WEKA,” in: Stat. Genomics Methods Protocol, pp. 353–378, 2016.
48. [48] J. Alcala-Fdez, S. Garcia, A. Fernandez, J. Luengo, S. Gonzalez, J.A. Saez, I. Triguero, J. Derrac, V. Lopez, L. Sanchez, and F. Herrera. (2019, December 25). Comparison of KEEL Versus Open Source Data Mining Tools: Knime and Weka [Online]. Access: https://pdfs.semanticscholar.org/74e5/4fbedd3f6b155fb59cc448883a9693858db4.pdf.
49. [49] R.R. Bouckaert, E. Frank, M.A. Hall, G. Holmes, B. Pfahringer, P. Reutemann, and I.H. Witten, “WEKA - experiences with a java open-source project,” Journal of Machine Learning Research, vol. 11, pp. 2533–2541, 2010.
50. [50] Z.H. Zhou, “Learnware: on the future of machine learning,” Frontiers of Computuer Sciences, vol. 10, pp. 589–590, 2016.
51. [51] B. Çığsal, and D. Ünal, “Comparison of data mining classification algorithms determining the default risk,” Scientific Programming, 2019, pp. 1-8.
52. [52] Anonymous. (2020, February 4). What is root mean square error (RMSE)? [Online]. Available: https://www.statisticshowto.com/probability-and-statistics/regression-analysis/rmse-root-mean-square-error/.
53. [53] A. Saxena, and M.K. Jat, “Analysing performance o SLEUTH model calibration using brute force and genetic algorithm–based methods,” Geocarto International, vol. 35, pp. 256–279, 2020.
54. [54] E. Ardıl, “Software error estimation with flexible computing approach,” Master thesis, Department of Computer Engineering, Trakya University, Tekirdağ, Turkey, 2009.
55. [55] C. Sammut, and G.I. Webb, “Mean absolute error,” in Encyclopedia of Machine Learning and Data Mining, 1st ed., Boston, MA: Springer US, 2010, pp. 1-652.
56. [56] A.P. Akgüngör, and E. Doğan, “Developed using different methods traffic accident prediction models and analysis,” International Journal of Engineering Research and Development, vol. 2, pp. 16–22, 2010.
57. [57] Anonymous. (2020, October 20). Plot matrix [Online]. Available: https://machinelearningmastery.com/better-understand-machine-learning-data-weka/.
58. [58] E. V. Venkatesan, “Performance analysis of decision tree algorithms for breast cancer classification,” Indian Journal of Science and Technology, vol. 8, pp. 1-8, 2015.