DOI QR코드

DOI QR Code

A New Vessel Path Prediction Method Based on Anticipation of Acceleration of Vessel

가속도 예측 기반 새로운 선박 이동 경로 예측 방법

  • Kim, Jonghee (School of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Jung, Chanho (Dept. of Electrical Engineering, Hanbat National University) ;
  • Kang, Dokeun (The 3rd R&D Institute - 4th Directorate, Agency for Defense Development) ;
  • Lee, Chang Jin (The 5th R&D Institute - 1st Directorate, Agency for Defense Development)
  • Received : 2020.11.10
  • Accepted : 2020.12.14
  • Published : 2020.12.31

Abstract

Vessel path prediction methods generally predict the latitude and longitude of a future location directly. However, in the case of direct prediction, errors could be large since the possible output range is too broad. In addition, error accumulation could occur since recurrent neural networks-based methods employ previous predicted data to forecast future data. In this paper, we propose a vessel path prediction method that does not directly predict the longitude and latitude. Instead, the proposed method predicts the acceleration of the vessel. Then the acceleration is employed to generate the velocity and direction, and the values decide the longitude and latitude of the future location. In the experiment, we show that the proposed method makes smaller errors than the direct prediction method, while both methods employ the same model.

선박의 이동 경로를 예측하는 기존의 방법들은 일반적으로 위도와 경도를 직접 예측한다. 하지만, 위도와 경도를 직접 예측할 경우, 예측 모델이 출력 가능한 범위가 상당히 넓어서 예측 오차가 매우 크게 발생할 수 있다. 또한, 순환 신경망 모델 기반의 예측에서는 이전 예측 위치도 다음 위치를 예측하기 위해 사용되기 때문에 오차가 누적되는 현상도 쉽게 발생할 수 있다. 이에 따라, 제안하는 방법에서는 위도와 경도를 직접 예측하지 않고, 선박의 가속도를 예측하여, 향후 속도와 방향을 결정하고, 그 결과로 위도와 경도가 예측되는 방법을 제안한다. 실험 결과에서는 같은 순환 신경망 모델을 사용했을 때, 제안하는 방법이 기존의 직접적으로 위도와 경도를 예측하는 방법에 비해 더 적은 오차를 발생시킴을 보인다.

Keywords

References

  1. D-D. Nguyen, C. L. Van, and M. I. Ali, "Vessel trajectory prediction using sequence-to-sequence models over spatial grid," in Proc. of the 12th ACM International Conference on Distributed and Event-based Systems, pp.258-261, 2018. DOI: 10.1145/3210284.3219775
  2. M. Gao, G. Shi, and S. Li, "Online prediction of ship behavior with automatic identification system sensor data using bidirectional long short-term memory recurrent neural network," Sensors, vol.18, no.12, pp. 4211-4226, 2018. DOI: 10.3390/s18124211
  3. X. Zhou, Z. Liu, F. Wang, Y. Xie, and X. Zhang, "Using Deep Learning to Forecast Maritime Vessel Flows," Sensors, vol.20, no.6, pp.1761-1777, 2020. DOI: 10.3390/s20061761
  4. Z. Yuan, J. Liu, Y. Liu, and Z. Li, "A novel approach for vessel trajectory reconstruction using AIS data," in Proc. of the 29th International Ocean and Polar Engineering Conference, pp. 4554-4559, 2019.
  5. P. Dijt and P. Mettes, "Trajectory Prediction Network for Future Anticipation of Ships," in Proc. of the 2020 International Conference on Multimedia Retrieval, pp.73-81, 2020. DOI: 10.1145/3372278.3390676
  6. Jonghee Kim, Chanho Jung, Dokeun Kang, and Chang Jin Lee, "A New Vessel Path Prediction Method using Long Short-term Memory," The Transactions of The Korean Institute of Electrical Engineers, vol.69, no.7, pp.1131-1134, 2020. DOI: 10.1080/20464177.2019.1665258
  7. Jonghee Kim, Chanho Jung, Dokeun Kang, and Chang Jin Lee, "A Noise Reduction Method for Vessel Path Prediction," Korea Computer Congress, 2020. DOI: 10.3390/s20185133
  8. A. Graves, S. Fernández, and J. Schmidhuber. "Multi-dimensional recurrent neural networks," International conference on artificial neural networks, pp.549-558, 2007. DOI: 10.1007/978-3-540-74690-4_56