Journal of the Korean Society of Marine Environment & Safety (해양환경안전학회지)

The Korean Society of Marine Environment and safety (해양환경안전학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis and Prediction Methods of Marine Accident Patterns related to Vessel Traffic using Long Short-Term Memory Networks

장단기 기억 신경망을 활용한 선박교통 해양사고 패턴 분석 및 예측

  • Jang, Da-Un (Graduate School of Maritime Transportation System, Mokpo National Maritime University) ;
  • Kim, Joo-Sung (Division of Navigation Science, Mokpo National Maritime University)
  • 장다운 (목포해양대학교 해상운송시스템학과) ;
  • 김주성 (목포해양대학교 항해학부)
  • Received : 2022.07.19
  • Accepted : 2022.08.29
  • Published : 2022.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Quantitative risk levels must be presented by analyzing the causes and consequences of accidents and predicting the occurrence patterns of the accidents. For the analysis of marine accidents related to vessel traffic, research on the traffic such as collision risk analysis and navigational path finding has been mainly conducted. The analysis of the occurrence pattern of marine accidents has been presented according to the traditional statistical analysis. This study intends to present a marine accident prediction model using the statistics on marine accidents related to vessel traffic. Statistical data from 1998 to 2021, which can be accumulated by month and hourly data among the Korean domestic marine accidents, were converted into structured time series data. The predictive model was built using a long short-term memory network, which is a representative artificial intelligence model. As a result of verifying the performance of the proposed model through the validation data, the RMSEs were noted to be 52.5471 and 126.5893 in the initial neural network model, and as a result of the updated model with observed datasets, the RMSEs were improved to 31.3680 and 36.3967, respectively. Based on the proposed model, the occurrence pattern of marine accidents could be predicted by learning the features of various marine accidents. In further research, a quantitative presentation of the risk of marine accidents and the development of region-based hazard maps are required.

해양사고 예방을 위해서는 사고의 원인과 결과에 대한 분석 및 진단뿐만 아니라, 사고의 발생 패턴과 변화 추이를 예측함으로써 정량적 위험도를 제시할 필요성이 있다. 선박교통과 관련된 해양사고 예측은 선박의 충돌위험도 분석 및 항해 경로 탐색 등 선박교통의 흐름에 관한 연구가 주로 수행되었으며, 해양사고의 발생 패턴에 대한 분석은 전통적인 통계 분석에 따라 제시되었다. 본 연구에서는 해양사고 통계 자료 중 선박교통관련 사고의 월별, 시간대별 발생 현황 데이터를 활용하여 해양사고 발생 예측 모델을 제시하고자 한다. 국내 해양사고 발생 현황 중 월별, 시간대별 데이터 집계가 가능한 1998년부터 2021년까지의 통계자료 중 선박교통 관련 데이터를 분류하여 정형 시계열 데이터로 변환하였으며, 대표적인 인공지능 모델인 순환 신경망 기반 장단기 기억 신경망을 통하여 예측 모델을 구축하였다. 검증데이터를 통하여 모델의 성능을 검증한 결과 RMSE는 초기 신경망 모델에서 월별 52.5471, 시간대별 126.5893으로 나타났으며, 관측값으로 신경망 모델을 업데이트한 결과 RMSE는 월별 31.3680, 시간대별 36.3967로 개선되었다. 본 연구에서 제안한 신경망 모델을 기반으로 다양한 해양사고의 특징 데이터를 학습하여 해양사고 발생 패턴을 예측할 수 있을 것이다. 향후 해양사고 발생 위험의 정량적 제시와 지역기반의 위험지도 개발 등에 관한 추가 연구가 필요하다.

Keywords

Acknowledgement

This research was a part of the project titled 'Development of cloud-based next-generation VTS Integration platform', funded by the Korea Coast Guard.

References

  1. Bae, S. W. and J. S. Yu(2018), Predicting the Real Estate Price Index Using Machine Learning Methods and Time Series Analysis Model, Housing Studies Review, Vol. 26, No. 1, pp. 107-133.
  2. Hochreiter, S. and J. Schmidhuber(1997), Long Short-Term Memory, Neural Computation, Vol. 9, No. 8, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  3. Hyun, S., B. K. Lee, G. W. Kim, and B. J. Chu(2009), A Comparative Study on Disaster Response Systems of Local Governments: Focusing on the Cases of Marine Pollution Accidents in Korea and Japan, Korean Public Administration Review, 43(3), pp. 273-306.
  4. International Maritime Organization(2020), International Convention for the Safety of Life at Sea 1974 Amended 2020; International Maritime Organization: London, UK.
  5. Jeong, J. Y. and C. Y. Jung(2012), Empirical Study on the Performance Analysis and Function of Jindo Coastal Vessel Traffic Service, Journal of the Korean Society of Marine Environment & Safety, Vol. 18, No. 4, pp. 308-315. https://doi.org/10.7837/kosomes.2012.18.4.308
  6. Jung, C. H.(2018), A Study on the Improvement of Safety by Accidents Analysis of Fishing Vessels, Jounal of Fisheries and Marine Sciences Education, Vol. 30, No. 1, pp. 176-186. https://doi.org/10.13000/JFMSE.2018.02.30.1.176
  7. Jung, C. H., H. Y. Kim, and C. H. Lee(2017), A Proposal of Marine Accident Prevention Policy through the Statistical Analysis, Journal of Korean Maritime Police Science, Vol. 7, No. 3, pp. 159-181.
  8. Kim, J. H. and J. Y. Kim(2021), Covid19 trends predictions using time series data, Journal of the Korea Institute of Information and Communication Engineering, Vol. 25, No. 7, pp. 884-889. https://doi.org/10.6109/JKIICE.2021.25.7.884
  9. Kim, J. S.(2013), A Basic Study on the VTS Operator's Minimum Safe Distance, Journal of the Korean Society of Marine Environment & Safety, Vol. 19, No. 5, pp. 476-482. https://doi.org/10.7837/kosomes.2013.19.5.476
  10. Kim, J. S.(2014), A study on Cognitive Work Analysis of VTS operation and effective utilization, M.S. thesis, Mokpo maritime university.
  11. Korean Maritime Safety Tribunal(2022), Status of Marine Accidents, https://www.kmst.go.kr/web/stcAnnualReport.do?menuIdx=126 (Accessed July 2022).
  12. Korean Statistical Information Service(2022), Annual Marine Accident Statistics, https://kosis.kr/statHtml/statHtml.do?orgId=146&tblId=DT_MLTM_1348 (Accessed July 2022).
  13. Lee, J. and J. Song(2021), An Empirical Study on Prediction of the Art Price using Multivariate Long Short Term Memory Recurrent Neural Network Deep Learning Model, The Journal of the Korea Contents Association, Vol. 21, No. 6, pp. 552-560. https://doi.org/10.5392/JKCA.2021.21.06.552
  14. Lee, L. N. and J. S. Kim(2022), Development of Priority Index for Intelligent Vessel Traffic Monitoring System in Vessel Traffic Service Areas, Applied Sciences, Vol. 12, No. 8, pp. 3807. https://doi.org/10.3390/app12083807
  15. Lee, L. N., J. S. Kim, H. H. Lee, J. S. Lee, and H. Namgung(2022), Analysis of User Requirements for Development of Vessel Traffic Services Cloud System, Journal of the Korean Society of Marine Environment & Safety, Vol. 28, No. 2, pp. 314-323. https://doi.org/10.7837/kosomes.2022.28.2.314
  16. Lee, M. K., Y. S. Park, E. B. Lee, and S. J. Na(2019), A Study on the Improvement plan of Marine Accident Investigation Method, Journal of Korean Maritime Police Science, Vol. 9, No. 1, pp. 111-129.
  17. Olah, C.(2015), Understanding LSTM Networks, http://colah.github.io/posts/2015-08-Understanding-LSTMs/ (Accessed July 2022).
  18. Park, B. S. and Y. S. Ahn(2007), Statistical Analysis of Marine Accidents by ANOVA, Journal of the Korean Society of Marine Environment & Safety, Vol. 13, No. 3, pp. 191-198.
  19. Roh, H. R.(2014), Cases Analysis of Maritime Accidents and Countermeasure of Korea Coast Guard: Focus on the Passenger Ship Accidents, Korean Journal of Public Safety and Criminal Justice, Vol. 23, No. 4, pp. 127-160.
  20. Roh, J. Y. and S. H. Bae(2021), Forecasting of Traffic Accident Occurrence Pattern Using LSTM, The Journal of The Korea Institute of Intelligent Transportation Systems, Vol. 20, No. 3, pp. 59-73.
  21. Roh, Y. J. and S. H. Bae(2021), Forecasting of Traffic Accident Occurrence Pattern Using LSTM, The journal of the Korea Institute of Intelligent Transportation Systems, Vol. 20, No. 3, pp. 59-73. https://doi.org/10.12815/kits.2021.20.3.59
  22. Shin, D. H. and S. H. Ji(2020), A Critical Review of the Act on Vessel Traffic Services, Journal of the Korean Society of Marine Environment & Safety, Vol. 26, No. 4, pp. 336-345. https://doi.org/10.7837/kosomes.2020.26.4.336
  23. Shin, D. H., K. H. Choi, and C. B. Kim(2017), Deep Learning Model for Prediction Rate Improvement of Stock Price Using RNN and LSTM, The Journal of Korean Institute of Information Technology, Vol. 15, No. 10, pp. 9-16. https://doi.org/10.14801/jkiit.2017.15.10.9
  24. Shin, D. S., S. H. Im, C. W. Choi, J. O. Lee, and H. C. Park(2021). Marine Accident Prediction Model Based on Artificial Neural Network. Transportation Technology and Policy, Vol. 18, No. 2, pp. 43-50.
  25. Sun, R., J. Yoo, J. Bang, J. H. Song, and B. M. So(2021), LSTM Model Design for Short-Term Prediction of Wind Power Generation Using Actual Data from a Wind Condition Measuring Instrument, The Journal of Next-generation Convergence Technology Association, Vol. 5, No. 6, pp. 1018-1026. https://doi.org/10.33097/JNCTA.2021.05.06.1018
  26. Youn J. and T. J. Lee(2022), LSTM-based Fire and Odor Prediction Model for Edge System, KIPS Transactions on Computer and Communication Systems, Vol. 11, No. 2, pp. 67-72. https://doi.org/10.3745/KTCCS.2022.11.2.67