보간기법을 적용한 AIS 데이터 기반 선박 경로 예측 딥러닝 연구
Deep Learning Research on Vessel Trajectory Prediction Based on AIS Data with Interpolation Techniques
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
해상 운송의 대부분을 차지하고 있는 선박의 경로를 예측하는 연구는 해상의 위험을 사전에 탐지하여 사고를 예방할 수 있다. 도로와 달리 해상에는 신호체계가 따로 존재하지 않고, 교통 관리가 어렵기에 해상 안정성을 위해 선박 경로 예측은 필수적이다. 그러나 선박의 경로 데이터셋의시간 간격은 통신 장애로 인해 불규칙하다. 본 연구는 이 문제를 해결하기 위해 선박 경로 예측에 적합한 보간법을 사용하여 데이터의 시간 간격을 조정하는 방법을 제시한다. 또한, 선박의 경로를 예측하기 위한 선박 경로 예측 딥러닝 모델을 개발하였다. 본 연구의 모델은 선박의 실시간경로 정보를 담고 있는 AIS 데이터를 통해 선박의 이동패턴을 파악하여 이후에 위치할 선박의GPS 좌표를 예측하는 LSTM 모델이다. 본 논문은 선형 보간법을 사용한 데이터 전처리 방법과선박 경로 예측에 적합한 딥러닝 모델을 제시하고, 실험을 통해 MSE 0.0131, Accuracy 0.9467로본 논문에서 제시하는 방법의 예측 성능이 우수함을 나타낸다.
Abstract
The research on predicting the routes of ships, which constitute the majority of maritime transportation, can detect potential hazards at sea in advance and prevent accidents. Unlike roads, there is no distinct signal system at sea, and traffic management is challenging, making ship route prediction essential for maritime safety. However, the time intervals of the ship route datasets are irregular due to communication disruptions. This study presents a method to adjust the time intervals of data using appropriate interpolation techniques for ship route prediction. Additionally, a deep learning model for predicting ship routes has been developed. This model is an LSTM model that predicts the future GPS coordinates of ships by understanding their movement patterns through real-time route information contained in AIS data. This paper presents a data preprocessing method using linear interpolation and a suitable deep learning model for ship route prediction. The experimental results demonstrate the effectiveness of the proposed method with an MSE of 0.0131 and an Accuracy of 0.9467.
참고문헌 (16)
- E. Smirni, "Workload-Aware Load Balancing for Cluster Web Servers", IEEE Trans. on Parallel and Distributed Systems, 16(3), pp.219~232 (2005)[DOI]
- T. Blu, "Linear interpolation revitalized", IEEE Transactions on Image Processing, 13(5), pp.710~719 (2004)[DOI]
- S. A. Dyer, "Cubic-spline interpolation. 1", IEEE Instrumentation & Measurement Magazine, 4(1), pp.44~46 (2001)[DOI]
- S. Hochreiter, "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997)[DOI]
- Suo, Y., "A Ship Trajectory Prediction Framework Based on a Recurrent Neural Network", Sensors, 20, pp.5133~ (2020)[DOI]
- C. Wang, "Vessel trajectory prediction based on AIS data and bidirectional GRU", 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL), pp.260~264 (2020)
- S. Capobianco, "Deep Learning Methods for Vessel Trajectory Prediction Based on Recurrent Neural Networks", IEEE Transactions on Aerospace and Electronic Systems, 57(6), pp.4329~4346 (2021)[DOI]
- K. Donandt, "Short-term Inland Vessel Trajectory Prediction with Encoder-Decoder Models", 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), pp.974~979 (2022)
- C. Wang, "Vessel trajectory prediction based on AIS data and bidirectional GRU", 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL), pp.260~264 (2020)
- Murray, Brian, "An AIS-based deep learning framework for regional ship behavior prediction", Reliability Engineering & System Safety, 215, pp.107819~ (2021)[DOI]
- Jonghee Kim, "A New Vessel Path Prediction Method using Long Short-term Memory", The transactions of The Korean Institute of Electrical Engineers, 69(7), pp.1131~1134 (2020)[DOI]
- Yang, Sun, "An approach to ship behavior prediction based on AIS and RNN optimization model", International Journal of Transportation Engineering and Technology, 6(1), pp.16~ (2020)[DOI]
- Shaheen, H., "Soft Computing: Theories and Applications" (2022), Springer
- H. Qian, "RobustScaler : QoS-Aware Autoscaling for Complex Workloads", 2022 IEEE 38th International Conference on Data Engineering (ICDE), pp.2762~2775 (2022)
- Z. Zhang, "Improved Adam Optimizer for Deep Neural Networks", 2018 IEEE, 2018, 1~2
- Kalyan Das, "Mean squared error of empirical predictor", Ann. Statist, 32(2), pp.818~840 (2004)[DOI]