VERİ MADENCİLİĞİ VE HAVACILIKTAKİ UYGULAMALARI: BUGÜNE VE GELECEĞE KISA BİR BAKIŞ

Öz

İçinde yaşadığımız çağda, hayatımızın her alanına giren teknolojiler sayesinde, her gün çok büyük miktarda sayısal veri üretilmektedir. Bu büyük verinin hem depolanması hem de analizi, yeni araçlara ve tekniklere ihtiyacı da arttırmaktadır. Bu açılardan ele alındığında, veri madenciliği farklı tipte veri havuzlarına uygulanabilmesi, her türlü veriyi uygun yöntemlerle işleyebilmesi, geçmiş davranışlardan geleceğe yönelik çıkarımlar yapılmasını sağlayabilmesi gibi özellikleri sayesinde çok farklı sektörlerde ve disiplinlerde kullanılabilmektedir. Gerek operasyonel (havaalanı, havayolu, hava trafiği, vb.) gerekse teknik konular (uçak sistemleri, bakım, kaza/olay incelemeleri, vb.) açısından bakıldığında havacılık sektörü de veri madenciliğinin çok farklı konularda uygulanabileceği büyük bir veri havuzu sunmaktadır. Bu çalışmanın amacı, öncelikle yakın bir geçmiş içinde veri madenciliğinin havacılık alanındaki uygulamalarını ve bu uygulamaların çeşitliliğini incelemektir. Sonuç olarak ise havacılık alanında veri madenciliği ve büyük veri analizi çalışmalarının yoğunlaştığı ve keşfedilmeye açık alanların bir değerlendirmesi sunulmaktadır

Anahtar Kelimeler

• Veri madenciliği, büyük veri, havacılık

DATA MINING AND ITS APPLICATIONS TO AVIATION: A BRIEF LOOK AT THE PRESENT AND FUTURE

Abstract

In the era we live in, thanks to the technologies that enter every field of our lives, digital data are produced in great quantities every day. Both the storage and analysing issues of this large data increase the need for new tools and techniques. With these points of view, because its features, such as being applicable to different types of data repositories, able to process all kinds of data with appropriate methods and able to predict future from past behavior, data mining can be applied in many different sectors and disciplines. Aviation sector also offers a huge data pool where data mining can be implemented in many different ways, both in terms of operational (airport, airline, air traffic, etc.) and technical issues (aircraft systems, maintenance, accident/incident investigations, etc.). The aim of this study is primarly, to examine the data mining applications and the diversity of these in aviation. As a result, an assesment of on which fields data mining and large data analysis works are concentrated and open areas of discovery with the standpoint of data mining in aviaition

Keywords

• Data mining, big data, aviation

Kaynakça

1. Ahmed, T., Calders, T., Pedersen, T.B. (2015). Mining risk factors in RFID baggage tracking data, 16th IEEE International Conference on Mobile Data Management, pp.
2. 242. Akartunalı, K., Boland, N., Evans, I., Wallace, M., Waterer, H. (2013a). Airline planning benchmark problems - part I: characterising networks and demand using limited data, Computers and Operations Research, vol. 40, pp. 775-792, DOI: 10.1016/j.cor.2012. 02.012.
3. Akartunalı, K., Boland, N., Evans, I., Wallace, M., Waterer, H. (2013b). Airline planning benchmark problems - part II: passenger groups, utility and demand allocation, Computers and Operations Research, vol. 40, pp. 793-804, DOI: 10.1016/j.cor.2012. 03.005.
4. Asgary, A., Ansari, S., Duncan, R., Pradhan, S. (2015). Mapping potential airplane hazards and risks using airline traffic data, International Journal of Disaster Risk Reduction, vol. 13, pp. 276-280, DOI: 10. 1016/j.ijdrr.2015.07.002.
5. Baluch, M., Bergstra, T., El-Hajj, M. (2017). Complex analysis of United States flight data using a data mining approach, CCWC’2017
6. Communication Workshop and Conference, DOI: 10.1109/ CCWC.2017.7868414.
7. and Bastos, P., Lopes, I., Pires, L. (2014). Application of data mining in a maintenance system for failure prediction, Safety, Reliability and Risk Analysis: Beyond the Horizon, Steenbergen et al. (Eds), pp. 933-940, Taylor & Francis Group, London, ISBN 978-1-138- 00123-7.
8. Bloedorn, E. (2000). Mining aviation safety data: a hybrid approach, MITRE.

9. Bushmann, S., Matthias, T., Döllner, J. (2014). Real- time animated visualization of massive air- traffic trajectories, International Conference on Cyberworlds, pp. 174-181.
10. Chandramohan, A.M., Mylaraswamy, D., Xu, B. (2014). Big data ınfrastructure for aviation data International
11. Computing in Emerging Markets, October 15-17, India, DOI: 10.1109/CCEM.2014. 7015483. IEEE Cloud Conference on
12. Christopher, A.B.A, Balamurugan S.A, (2013). Data mining approaches for aircraft accidents prediction: an empirical study on Turkey airline, Emerging
13. Communication and Nanotechnology, India, March 25-26, DOI: 10.1109/ICE-CCN. 2013.6528602 Conference
14. on Computing, Christopher, A.B.A, Shunmughavel, V., A., Vivekanandam,
15. Markkandeyan, S., Sivakumar, V. (2016). Large-scale data analysis on aviation accident database using different data mining Anderson, techniques, The
16. Aeronautical Journal, vol. 120, no. 1234, pp. 1849-1866, DOI: 10.1017/aer.2016.107.
17. Duvvuri, M.D., Borra, S.K., Yarlagadda, P., Jaume, S. (2017) Transportation analytics: a study of aviation accidents and flight incidents, International Journal of Data Analysis and Information systems, vol. 90, no. 1, pp. 11- 23.
18. Grampella, M., Lo, P., Matini, G., Scotti, D., (2017). The impact of technology progress on aviation noise and emissions, Transportation Research Part A: Policy and Practice, vol. 103, pp. 525-540.
19. Han, J., Kamber, M., Pei, J., (2012). Data mining concepts and techniques, 3rd Edition, Elsevier.
20. Hemmati, H., Arefin, S.S., Siddiqui, T.R. (2017). Analytic-based safety monitoring and verification, SMC’2017 IEEE International Conference
21. Cybernetics, Canada, October 5-8, pp. 3608- 3613. Man
22. and Jing, T., Long, F., Shi, X. (2016). Research of aircraft integrated drive generator fault diagnostic decision based on attribute reduction in rough sets, AUS’2016 IEEE/CSAA International conference on Aircraft Utility Systems, China, October 10- 12, pp. 393-397.
23. Li, Z., Bi, J., Zhang, J., Li, Q. (2017). Analysis of airport departure baggage check-in process based on passanger behavior, ISCID2017 10th
24. Computational Intelligence and Design, China, December 9-10. Symposium on Liu, J., Cui, M. (2017). The analysis of civil aviation ıncident ınformation based on knowledge map,
25. Conference on Transportation Information and Safety, Canada, August 8-10, pp. 679- 684.
26. International Loro, M.N., Lacaille, J. (2016). Datamining turbofan engine performance to ımprove fuel efficiency, Future Technologies Conference, USA, December 6-7.
27. Luca, M., Abbondati, F., (2016). Preliminary study on runway pavement friction decay using data mining, Transportation Research Procedia, vol. 14, pp. 3751-3760.
28. Lukacova, A., Babic, F., Paralic, J. (2014). Building the prediction model from the aviation ıncident data, SAMI2014 12th IEEE International
29. Machine Intelligence and Informatics, Slovakia, January 23-25. on Applied Mack, D.L.C., Biswas, G., Koutsoukos, X.D., Mylaraswamy,
30. bayesian network structures to augment aircraft diagnostic reference models, IEEE Transactions on Automation Science and Engineering, vol. 14, no. 1, DOI: 10.1109/ TASE.2016.2542186.
31. Learning Manna, S., Biswas, S., Kundu, R., Rakshit, S., Gupta, P., Barman, S. (2017). A statistical approach to predict flight delay using gradient
32. ICCIDS’2017 International Conference on Computational Intelligence in Data Science, India, June 2-3. decision tree, Pagels, D.A., (2015). Aviation data mining, Scholarly
33. Minnesota, Morris, Undergraduate Journal, vol.2, no. 1. University
34. of Pan, D. (2017). Hybrid data-driven anomaly detection method to improve UAV operating reliability, Prognostics and System Health Management Conference, China, July 9-12, DOI: 10.1109/PHM.2017.8079281.
35. Qian, S., Zhou, S., Chang, W. (2017). An ımproved aircraft hard landing prediction model based on panel data clustering, CCDC’2017 29th Chinese Control and Decision Conference, China, May 28-30, pp. 438-443, DOI: 10.1109/CCDC.2017.7978134.
36. Qu, D., Yang, B., Gao, T., Yuan, L., Chen, X. (2017). ARINC664 bus function test and ıts fault ınjection based on ethernet card, IICIEA’2017 12th IEEE Conference on Industrial Electronics and Applications, Cambodia, June 18-20.
37. Rashid, H.S.J., Place, C.S., Braithwaite, G.R., (2013). Investigating the investigations: a retrospective
38. maintenance error causation, Cognition, Technology & Work, vol. 15, pp. 171–188. Ravizza, S, Chen, J., Atkin, J.A.D., Stewart, P., Burke, E.K. (2014). Aircraft taxi time prediction:
39. Applied Soft Computing, vol. 14, pp. 397- 406, DOI: 10.1016/j.asoc.2013.10.004.
40. Roldan, J.J., del Cerro J., Barrientos, A. (2017). Using process mining to model multi-UAV Missions through the experience, IEEE Intelligent Systems, vol. 32, no. 4, pp. 40-47, DOI: 10.1109/MIS.2017.3121547.
41. Rui, M., Pedro, C., Roberto, H. (2017). Crawling public massive data to solve air traffic data issues, CIST’2017 12th Iberian Conference on Information Systems and Technologies, Portugal, June 21-24.
42. Seifert, J.W. (2004). Data mining: an overview, CRS Report
43. Research Service, The Library of Congress. Congressional Seyfioğlu, M.S., Demirezen, M.U. (2017). A hierarchical approach for sentiment analysis and categorization of Turkish written customer relationship management data, FedCSIS2017 Federated Conference on Computer Science and Information Systems, Czech Republc, September 3-6.
44. Sharma, S., Sabitha, A.S. (2016). Flight crash investigation using data mining techniques, IICIP’2016
45. Conference on Information Processing, August 12-14, India, DOI: 10.1109/IICIP. 2016.7975390.
46. International Veresnikov, G.S., Skryabin, A.V., (2017). The development of data mining methods criteria to identify failures of aircraft control surface actuator, Knowledge
47. Information and Engineering Systems, Marseille, France, pp. 1-8, September 6-8.
48. Wang, Y., Andoh-Baidoo, F., Jun, S., (2013). Factors that influence transportation security funding: a data mining analysis on U.S. airport improvement grants, 46th Hawaii International
49. Sciences, Wailea, Maui, HI, USA, pp.1-9. on
50. System Wenjing, C., Shenghong, X. (2017). A workflow based multi-UAV cooperation architecture, ICIM’2017 3rd International Conference on Information Management, China, April 21- 23, pp. 496-499, DOI: 10.1109/INFOMAN. 2017.7950435.
51. Xiangmin, G., Li, M. (2017). Departure capacity predict,on for hub airport in thunderstorm based on data mining method, CCDC’2017 29th
52. Conference, China, May 28-30. and Decision Xin, Z., Ming-qing, X., Yi-wang-lang, X., Han-qiao, Wei, C. (2016). Method for predicting aviation equipment failures based on degradation-track similarity, IEEE Chinese Guidence,
53. Conference, China, August 12-14, pp. 1472- 1477. and Control Yuan, W., Zhou, L., Guan, D., Han, G., Shu, L. (2017). Anomaly detection for civil aviation pilot using step-sensors, IEEE Access (Special Section on Intelligent System for the Internet of Things), vol.5, pp. 11236- 11243, 2717494.
54. Zhi, Y., Xiantai, G., Weidong, J. Haowen, X., Lingyuan, Z. (2017). Reverse engineering for UAV control protocol based on detection data, ICMIP’2017 2nd
55. International Conference on Multimedia and Image Processing, China, March 17-19, pp. 301- 304, DOI: 10.1109/ICMIP.2017.30.
56. Zhu, D., Ni, Y. (2013). The application of data mining in the civil aviation accident analysis, Applied Mechanics and Materials, vol.
57. 4028/www.scientific.net/AMM.241-244. 3000. 3000-3004,
58. DOI: Zou, Y., Meng, Z. (2017). Leader-follower formation control of multiple vertical takeoff and landing UAVs: distributed estimator design and accurate trajectory tracking,
59. International Conference on Control and Automaton, Macedonia, July 3-6, pp. 764- 769, DOI: 10.1109/ICCA.2017.8003156.