Journal of Navigation and Port Research (한국항해항만학회지)

Korean Institute of Navigation and Port Research (한국항해항만학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Data Clustering of Light Buoy Using DBSCAN(I)

DBSCAN을 이용한 등부표 위치 데이터 Clustering 연구(I)

  • Gwang-Young Choi (Korea Maritime and Ocean university Institute of Maritime Industry) ;
  • So-Ra Kim (Ocean Science and Technology School, Korea Maritime and Ocean university) ;
  • Sang-Won Park (Logistics amd Maritime industry research department of Korea maritime institute) ;
  • Chae-Uk Song (Division of Navigation Convergence Studies, Korea Maritime and Ocean University)
  • 최광영 (한국해양대학교 해사산업연구소 ) ;
  • 김소라 (한국해양대학교 해양과학기술전문대학원 ) ;
  • 박상원 (한국해양수산개발원 물류해사산업연구소 ) ;
  • 송재욱 (한국해양대학교 항해융합학부 )
  • Received : 2023.05.31
  • Accepted : 2023.07.03
  • Published : 2023.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The position of a light buoy is always flexible due to the influence of external forces such as tides and wind. The position can be checked through AIS (Automatic Identification System) or RTU (Remote Terminal Unit) for AtoN. As a result of analyzing the position data for the last five years (2017-2021) of a light buoy, the average position error was 15.4%. It is necessary to detect position error data and obtain refined position data to prevent navigation safety accidents and management. This study aimed to detect position error data and obtain refined position data by DBSCAN Clustering position data obtained through AIS or RTU for AtoN. For this purpose, 21 position data of Gunsan Port No. 1 light buoy where RTU was installed among western waters with the most position errors were DBSCAN clustered using Python library. The minPts required for DBSCAN Clustering applied the value commonly used for two-dimensional data. Epsilon was calculated and its value was applied using the k-NN (nearest neighbor) algorithm. As a result of DBSCAN Clustering, position error data that did not satisfy minPts and epsilon were detected and refined position data were acquired. This study can be used as asic data for obtaining reliable position data of a light buoy installed with AIS or RTU for AtoN. It is expected to be of great help in preventing navigation safety accidents.

등부표는 조류, 바람 등 외력에 영향을 받아 위치가 항상 유동적이고 위치는 항로표지용 AIS 또는 RTU를 통해 확인할 수 있다. 위치 확인이 가능한 등부표의 최근 5년간(2017~2021년) 위치 데이터 분석 결과 위치 오류 데이터는 평균 15.4%로 나타났으며 항해 안전사고예방 및 관리를 위해서는 위치 오류 데이터를 검출하고 정제된 위치 데이터 획득이 필요하다. 본 연구에서는 항로표지용 AIS 또는 RTU를 통해 획득한 위치 데이터를 DBSCAN Clustering하여 위치 오류 데이터를 검출하고 정제된 위치 데이터를 획득하고자 한다. 이를 위하여 위치 오류가 가장 많은 서해 해역 중 RTU가 설치된 군산항 1호 등부표의 21년도 위치 데이터를 Python library를 사용하여 DBSCAN Clustering 하였다. DBSCAN Clustering에 필요한 minPts는 2차원 데이터에 일반적으로 사용하는 값을 적용하였고 epsilon은 k-NN(최근접 이웃)알고리즘을 사용하여 값을 산출 및 적용하였다. DBSCAN Clustering 결과 minPts와 epsilon을 만족하지 못하는 위치 오류 데이터를 검출하였고 정제된 위치 데이터를 획득할 수 있었다. 본 연구는 항로표지용 AIS 또는 RTU가 설치된 등부표의 신뢰성 있는 위치 데이터를 획득할 수 있는 기초 자료로 활용할 수 있으며 항해 안전사고 예방에도 큰 도움이 될 것으로 판단된다.

Keywords

Acknowledgement

이 논문은 2023년 해양수산부 재원으로 해양과학기술진흥원의 지원을 받아 수행된 연구임(해양 디지털 항로표지 정보협력시스템 개발(3/5) (20210650)).

References

  1. Beyer, et. al.(1998), " When Is "Nearest Neighbor" Meaningful?", Database Theory-ICDT'99(LNCS), Vol. 1540, pp. 217-235. 
  2. Choi, E. S. and Park, N. J.(2021)," Application and Development of Machine Learning Training Program based on Understanding K-NN Algorithm", Journal of The Korean Association of Information Education, Vol. 25, pp. 175-184.  https://doi.org/10.14352/jkaie.2021.25.1.175
  3. Ester, M., Kr i e gel, H. P., Sander, J. and Xu, X.(1996), "A density-based algorithm for discovering clusters in large spatial databases wi t h noise," In Kdd, Vol. 96, No. 34. 
  4. Gug, S. G., Jeong, T. G., Park, H. R. and Kim, J. R.(2013), "A Study on Operation Analysis and Imorovement Method of Aids to Navigation AIS in Korean West Coast", KINPR, Vol. 37, No. 4, pp. 391-400. 
  5. Jeong, T. G. and Gug, S. G.(2013), "Theory of Marne Aids to Navigation", Sejong Publisher, pp. 13, p. 676. 
  6. Jun, J. C., Cheong, H. T., Park, J. S., Kang, Y. M. and Han, S. H.(2011), "Integrated Navigation Management System for Supporting Heterogeneous AIS AtoN", Journal of Korean Institute of Next Generation Computing, Vol. 7, No. 3, pp. 28-38. 
  7. Kim, T. G., Moon, B. S. and Gug, S. G.(2020), "A Study on the Sea Area Dynamic Stability of LL-26(M) Light Buoy", KINPR, Vol. 44, No. 3, pp. 166-173. 
  8. Lee, M. H., Jeon, I. H. and Jeon, C. M.(2017), "Clustering Public Transit Stops using an improved DBSCAN Algorithm", Vol. 82, pp. 97-106.  https://doi.org/10.7319/kogsis.2017.25.4.097
  9. Ministry of Ocean and Fisheries(2006), Aids to Navigation annual report, pp. 123-125, pp. 162-164. 
  10. Ministry of Ocean and Fisheries(2014), "Harbour and Fishery Design Criteria", pp. 1428-1447. 
  11. Ministry of Ocean and Fisheries(2015), "The 2nd Basic plan of Aids to Navigation", pp. 3-38 - 3-52. 
  12. Moon, B. S., Yoo, Y. J., Kim, M. J. and Kim, T. G.(2022), "A Study on the Seperated Position of Floating Light Buoy Equipment with AtoN AIS and RTU", KINPR, Vol. 46, No. 3, pp. 313-320. 
  13. National Geographic Information Institute(2022), http://www.ngii.go.kr/kor/main.do 
  14. Onel Harrison(2018). "Machine Learning Basics with the K-Nearest Neighbors Algorithm". http://towardsdatascience.com 
  15. Wen, Y., Sui, Z., Zhou, C., Xiao, C., Chen, Q., Han, D., and Zhang, Y.(2020), "Automatic ship route design between two ports: A data-driven method,"in Applied Ocean Research, 96.