Predicting the Frequency of Marine Accidents by Navigators’ Watch Duty Time in South Korea Using LSTM
Source abstract
Abstract
Despite the development of advanced technology, marine accidents have not decreased. To prevent marine accidents, it is necessary to predict accidents in advance. With the recent development of artificial intelligence (AI), AI technologies such as deep learning have been applied to create and analyze predictive models in various fields. The purpose of this study is to develop a model for predicting the frequency of marine accidents using a long-short term memory (LSTM) network. In this study, a prediction model was developed using marine accidents from 1981 to 2019, and the proposed model was evaluated by predicting the accidents in 2020. As a result, we found that marine accidents mainly occurred during the third officer’s duty time, representing that the accidents are highly related to the navigator’s experience. In addition, the proposed LSTM model performed reliably to predict the frequency of marine accidents with a small mean absolute percentage error (best MAPE: 0.059) that outperformed a traditional statistical method (i.e, ARIMA). This study could help us build LSTM structures for marine accident prediction and could be used as primary data to prevent the accidents by predicting the number of marine accidents by the navigator’s watch duty time.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Maritime Navigation and Safety · Marine and Coastal Research · Risk and Safety Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
LINC 3.0 Project Group, Mokpo National Maritime University, Mokpo 58628, Republic of Korea
Funding
Maritime Safety Audit for Offshore Windfarm in Anma Island, Yeonggwang
References (33)
Show source-provided references
1. A Study on the Improvement of Vessel Traffic Control of Korean Port in Restricted Visibility10.30887/jkmps.2021.11.3.145 ↗
2. A Study on the Advancement of Maritime Search and Rescue
3. Korean Maritime Safety Tribunal (KMST) (2022, November 16). Statistics of Marine Accidents. Available online: http://www.kmst.go.kr/eng/page.do?menuIdx=227.
4. A Study on the Prediction of the Frequency of Marine Accidents Using Markov Chain
5. An Analysis on the Models of Occurrence Probability of Marine Casualties
6. Statistical analysis of marine accidents by ANOVA
7. A fundamental study on advanced VTS system through statistic analyzing traffic accidents in VTS area10.5394/KINPR.2009.33.8.519 ↗
8. Wang, S., Yin, J., and Khan, R.U. (2020). The multi-state maritime transportation system risk assessment and safety analysis. Sustainability, 12.10.3390/su12145728 ↗
9. Bayesian networks for maritime traffic accident prevention: Benefits and challenges10.1016/j.aap.2014.09.017 ↗
10. Analysis of Seafarers’ Behavioral Error on Collision Accidents
11. A comparative study of the performance of the traffic accident prediction model at the intersection of the four districts using nonlinear regression analysis, artificial neural network, and structural equation
12. A study for development of expressway traffic accident prediction model using deep learning10.12815/kits.2018.17.4.14 ↗
13. Ren, H., Song, Y., Liu, J., Hu, Y., and Lei, J. (2017). A Deep Learning Approach to the Prediction of Short-Term Traffic Accident Risk. arXiv.10.1109/ITSC.2018.8569437 ↗
14. Development of a global road safety performance function using deep neural networks10.1016/j.ijtst.2017.07.004 ↗
15. Benoit, F. (2022, November 16). Road Accidents in Switzerland Forecasting-A Brief Comparison between Facebook Prophet and LSTM Neural Networks. Available online: https://towardsdatascience.com/road-accidents-in-switzerland-forecasting-a-brief-comparison-between-facebook-prophet-and-lstm-6514f585681.
16. Sameen, M., and Pradhan, B. (2017). Severity prediction of traffic accidents with recurrent neural networks. Appl. Sci., 7.10.3390/app7060476 ↗
17. Forecasting of Traffic Accident Occurrence Pattern Using LSTM10.12815/kits.2021.20.3.59 ↗
18. Atak, Ü., and Arslanoğlu, Y. (2021). Machine learning methods for predicting marine port accidents: A case study in container terminal. Ships Offshore Struct., 1–8.10.1080/17445302.2021.2003067 ↗
19. Kim, J.H., Kim, J., Lee, G., and Park, J. (2021). Machine learning-based models for accident prediction at a Korean container port. Sustainability, 13.10.3390/su13169137 ↗
20. Conflux LSTMs network: A novel approach for multi-view action recognition10.1016/j.neucom.2019.12.151 ↗
21. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
22. Crisóstomo de Castro Filho, H., Abílio de Carvalho Júnior, O., Ferreira de Carvalho, O.L., Pozzobon de Bem, P., dos Santos de Moura, R., Olino de Albuquerque, A., Rosa Silva, C., Guimarães Ferreira, P.H., Fontes Guimarães, R., and Trancoso Gomes, R.A. (2020). Rice Crop Detection Using LSTM, Bi-LSTM, and Machine Learning Models from Sentinel-1 Time Series. Remote Sens., 12.10.3390/rs12162655 ↗
23. Bouktif, S., Fiaz, A., Ouni, A., and Serhani, M.A. (2018). Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches. Energies, 11.10.3390/en11071636 ↗
24. Hosseini, M.-P., Lu, S., Kamaraj, K., Slowikowski, A., and Venkatesh, H.C. (2019). Deep learning architectures. Deep Learning: Concepts and Architectures, Springer.10.1007/978-3-030-31756-0_1 ↗
25. A review of recurrent neural networks: LSTM cells and network architectures10.1162/neco_a_01199 ↗
26. Bengio, Y. (2012). Practical recommendations for gradient-based training of deep architectures. Neural Networks: Tricks of the Trade, Springer.10.1007/978-3-642-35289-8_26 ↗
27. Ketkar, N. (2017). introduction to keras. Deep Learning with Python, Apress. [1st ed.].10.1007/978-1-4842-2766-4 ↗
28. Namin, A.H., Leboeuf, K., Muscedere, R., Wu, H., and Ahmadi, M. (2009, January 24–27). Efficient hardware implementation of the hyperbolic tangent sigmoid function. Proceedings of the 2009 IEEE International Symposium on Circuits and Systems, Taipei, Taiwan.10.1109/ISCAS.2009.5118213 ↗
29. Kingma, D.P., and Ba, J.L. (2015, January 7–9). Adam: A Method for Stochastic Optimization. Proceedings of the International Conference on Learning Representations 2015, San Diego, CA, USA.
30. Box, G.E.P., and Jenkins, G.M. (2015). Time Series Analysis: Forecasting and Control/Holden Day, San Francisco, California, 1970, John Wiley & Sons.
31. Cao, S., Wang, F., Tam, W., Tse, L.A., Kim, J.H., Liu, J., and Lu, Z. (2013). A hybrid seasonal prediction model for tuberculosis incidence in China. BMC Med. Inform. Decis. Mak., 13.10.1186/1472-6947-13-56 ↗
32. Smith, T.G. (2022, October 27). Pmdarima: ARIMA Estimators for Python. Available online: http://www.alkaline-ml.com/pmdarima.
33. (2022, October 27). Scikit-Learn (Version 1.1.3) Sklearn.Model_Selection.GridSearchCV. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html.