The Journal of Bigdata (한국빅데이터학회지)

Korea Bigdata Society (한국빅데이터학회)
권호 표지
DOI QR코드

DOI QR Code

Comparison of Clustering Techniques in Flight Approach Phase using ADS-B Track Data

공항 근처 ADS-B 항적 자료에서의 클러스터링 기법 비교

  • Received : 2021.11.26
  • Accepted : 2021.12.13
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Deviation of route in aviation safety management is a dangerous factor that can lead to serious accidents. In this study, the anomaly score is calculated by classifying the tracks through clustering and calculating the distance from the cluster center. The study was conducted by extracting tracks within 100 km of the airport from the ADS-B track data received for one year. The wake was vectorized using linear interpolation. Latitude, longitude, and altitude 3D coordinates were used. Through PCA, the dimension was reduced to an axis representing more than 90% of the overall data distribution, and k-means clustering, hierarchical clustering, and PAM techniques were applied. The number of clusters was selected using the silhouette measure, and an abnormality score was calculated by calculating the distance from the cluster center. In this study, we compare the number of clusters for each cluster technique, and evaluate the clustering result through the silhouette measure.

항공안전관리에서 항공기 경로 이탈은 큰 사고로 이어질 수 있는 위험한 요인이다. 본 연구에서는 항공기 경로 이탈 문제를 예방하기 위해 클러스터링을 통해 항적을 분류하고, 클러스터 중심과의 거리를 계산하여 이상 점수를 산출하고자 한다. 1년 동안 수신된 ADS-B 항적 자료에서 공항을 기준으로 근방 100km 이내 항적을 추출하여 연구를 진행했다. 항적은 선형 보간법을 이용하여 벡터화하였다. 위도·경도·고도 3차원 좌표 자료를 사용하였다. PCA를 통해 전체 데이터 분산 90% 이상을 나타내는 축으로 차원을 축소하였고, k-평균 군집화, 계층적 군집화, PAM 기법을 적용하였다. 클러스터 개수는 실루엣 측도를 사용하여 선택하였고, 클러스터 중심과의 거리를 계산하여 이상 점수를 산출하였다. 본 연구에서는 각 클러스터 기법별로 클러스터 개수를 비교해보고, 실루엣 측도를 통해 클러스터링 결과를 평가하고자 한다.

Keywords

Acknowledgement

본 연구는 국토교통부의 '빅데이터 기반 항공안전관리 기술 개발 및 플랫폼 구축(21BDAS-B158275-02)' 연구의 지원에 의하 여 이루어진 연구로서, 관계부처에 감사드립니다.

References

  1. Basora, Luis, Xavier Olive, and Thomas Dubot. "Recent advances in anomaly detection methods applied to aviation." Aerospace 6.11 (2019): 117. 
  2. Cortes, Corinna, and Vladimir Vapnik. "Support-vector networks." Machine learning 20.3 (1995): 273-297. 
  3. Eckstein, Adric. "Automated flight track taxonomy for measuring benefits from performance based navigation." 2009 Integrated Communications, Navigation and Surveillance Conference. IEEE, 2009. 
  4. Ester, Martin, et al. "A density-based algorithm for discovering clusters in large spatial databases with noise." kdd. Vol. 96. No. 34. 1996. 
  5. Han, Jiawei, Jian Pei, and Micheline Kamber. Data mining: concepts and techniques. Elsevier, 2011. 
  6. Kaufman, Leonard, and Peter J. Rousseeuw. "Partitioning around medoids (program pam)." Finding groups in data: an introduction to cluster analysis 344 (1990): 68-125. 
  7. Li, Lishuai, et al. "Anomaly detection in on-board-recorded flight data using cluster analysis." 2011 IEEE/AIAA 30th Digital Avionics Systems Conference. IEEE, 2011. 
  8. Olive, Xavier, and Luis Basora. "Identifying anomalies in past en-route trajectories with clustering and anomaly detection methods." ATM Seminar 2019. 2019. 
  9. Piciarelli, Claudio, Christian Micheloni, and Gian Luca Foresti. "Trajectory-based anomalous event detection." IEEE Transactions on Circuits and Systems for video Technology 18.11 (2008): 1544-1554.  https://doi.org/10.1109/TCSVT.2008.2005599
  10. WEATHER-RELATED AVIATION ACCIENT STUDY, Aviation Safety Information Analysis and Sharing, 2010. 
  11. Wrong Runway Departure, Aviation Safety Information Analysis and Sharing, 2007. 
  12. Zhang, Daqing, et al. "iBAT: detecting anomalous taxi trajectories from GPS traces." Proceedings of the 13th international conference on Ubiquitous computing. 2011.