Browse > Article
http://dx.doi.org/10.9708/jksci.2022.27.03.001

Prediction of drowning person's route using machine learning for meteorological information of maritime observation buoy  

Han, Jung-Wook (Republic of Korea Navy 6th air wing)
Moon, Ho-Seok (Dept. of Defense Science, Korea National Defense University)
Abstract
In the event of a maritime distress accident, rapid search and rescue operations using rescue assets are very important to ensure the safety and life of drowning person's at sea. In this paper, we analyzed the surface layer current in the northwest sea area of Ulleungdo by applying machine learning such as multiple linear regression, decision tree, support vector machine, vector autoregression, and LSTM to the meteorological information collected from the maritime observation buoy. And we predicted the drowning person's route at sea based on the predicted current direction and speed information by constructing each prediction model. Comparing the various machine learning models applied in this paper through the performance evaluation measures of MAE and RMSE, the LSTM model is the best. In addition, LSTM model showed superior performance compared to the other models in the view of the difference distance between the actual and predicted movement point of drowning person.
Keywords
Maritime distress accident; Maritime observation buoy; Machine learning; Prediction of drowning person's route; Surface layer current; LSTM;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 http://www.khoa.go.kr/oceangrid/khoa/koofs.do
2 Y. Noh and K. Cho, "A Text Content Classification Using LSTM For Objective Category Classification", Journal of the Korea Society of Computer and Information 26(5), pp. 39-46, MAY. 2021. DOI: 10.9708/jksci.2021.26.05.039   DOI
3 Korea Cost Guard, "2019 Maritime Distress Accident Statistical Yearbook", pp. 2, JUL. 2020.
4 Korea Cost Guard, "Act On The Search And Rescue, Etc. In Waters Article 2". AUG. 2019
5 Korea Hydrographic and Oceanographic Agency Ministry of Oceans and Fisheries Republic of Korea, "Research planning in the establishment of a system for predicting changes in ocean currents according to climate change, Result report", pp. 3-12, DEC. 2016
6 http://www.khoa.go.kr/oceangrid/gis.category/refrence/distribution.do
7 C. Ryu, J. Kim, D. Seol and D. Kang, "Oil Spill Behavior Forecasting Model in South-eastern Coastal Of Korea", Journal of the Korean Society for Maritime Environment & Energy 1(2), pp. 52-59, AUG. 2018
8 Y. Jeon, M. Hong, M. Park and Y. Choi, "Path Prediction and Suggestion of Efficient Collection Points for Maritime Plastic Debris Based on Betweenness Centrality Analysis", Journal of the Korean Society of Environmental Engineers 37(7), pp. 426-431, JUL. 2015. DOI: 10.4491/KSEE.2015. 37.7.426   DOI
9 C. Lee, G. Kim and Y. Kim, "Performance Comparision of Machine Learning Based on Neural Networks and Statistical Methods for Prediction of Drifter Movement", Journal of the Korea Convergence Society vol. 8, No. 10, pp. 45-52, OCT. 2017. DOI: 10.15207/JKCS.2017.8.10.045   DOI
10 C. Lee and Y. Kim, "Ensemble Design of Machine Learning Techniques: Experimental Verfication by Prediction of Drifter Trajectory", Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, vol. 8, No. 3, pp. 57-67, MAR. 2018. DOI: 10.35873/ajmahs.2018.8.3.006   DOI
11 Faraway. J, "Linear Models with R 2nd Edition", A Chanpman & Hall/CRC, pp.13, 2015
12 M. Heo, "Applied Data Analysis Using R", Freeaca, pp.239-248, OCT. 2014
13 Russom. P, "Big Data Analytics", TDWI Research, pp. 6, Fourth Quater. 2011
14 M. Heo, "Applied Data Analysis Using R", Freeaca, pp.221-238, OCT. 2014
15 Hyndman. R.J and Athanasopoulos. G, "Forecasting: Principles and Practice, 2nd edition", OText, pp. 11.2, MAY. 2018
16 http://ratsgo.github.io/natural%20language%20processing/2017/08/09/mnlstm/
17 ICAO and IMO, "International Aeronautical And Maritime Search And Rescue Manual Volume II Mission Co-ordination", pp. N-19, 2016