Tianyu Wang
ABSTRACT
Track prediction has always been a hot topic in the field of navigation, and plays an important role in ensuring the safety of ship navigation and improving the efficiency of marine traffic control. In this paper, a two-hidden-layer extreme learning machine trajectory prediction model is proposed, which can greatly shorten the prediction time while improving the prediction accuracy. Firstly, the DBSCAN clustering algorithm is used to cluster ship trajectories, and then the two-layer ELM trajectory prediction model is trained for different clusters. Finally, the experimental results are compared with the prediction results of the traditional ELM model and the widely used LSTM and GRU models in the past, which verifies the advantages of the tow-layer ELM model in terms of accuracy and speed of track prediction.
- Mao Chenhao, Pan Chen, Yin Bo, etc. Prediction of Ship Navigation Trajectory Based on Gaussian Process Regression. J. Technological innovation and application, 2017, 215(31): 28-29,31.Google Scholar
- Liu Xiling, Ruan Qunsheng, Gong Ziqiang. A New Prediction Model for GPS Positioning Trajectory of Ship Navigation. J. Journal of Jiangnan University (Natural Science Edition), 2014, 13(6): 686-692.Google Scholar
- Jiang Baichen, Guan Jian, Zhou Wei, etc. Ship Trajectory Prediction Algorithm Based on Polynomial Kalman Filter. J. Signal Processing, 2019, 35(5): 741-746. DOI: 10. 16798/j. issn. 1003-0530. 2019. 05. 002.Google Scholar
- Zhen Rong, Jin Yongxing, Hu Qinyou, etc. Ship Navigation Behavior Prediction Based on AIS Information and BP Neural Network. J. China Navigation, 2017, 40(2): 6-10.Google Scholar
- Hu Yuke, Xia Wei, Hu Xiaoxuan, Sun Haiquan, Wang Yunhui. Ship Track Prediction Based on Recurrent Neural Network. J. System Engineering and Electronic Technology, 2020,42(04): 871-877.Google Scholar
- Chen Kaida, Zhu Yongsheng, Yan Ke, etc. Ship Track Prediction Based on LSTM. J. Ship and Marine Engineering, 2019, 48(6): 121-125.Google Scholar
- KIM J S. Vessel Target Prediction Method and Dead Reckoning Position Based on SVR Seaway Model. J. International Journal of Fuzzy Logic & Intelligent Systems, 2017, 17(4): 279-288. DOI: 10. 5391/IJFIS. 2017. 17. 4. 279.Google ScholarCross Ref
- Li Nan, Sun Boxin, Jiao Qingyu, Zhang Lei. Track Prediction of Terminal Area Based on GA-BP Neural Network. C//Proceedings of World Transportation Engineering Technology Forum (WTC2021) (Part 2). 2021: 396-405. DOI: 10. 26914/c.cnkihy.2021.010262.Google Scholar
- Hu Dan, Meng Xin, Lu Shuai, Xing Lining. Application of a Parallel LSTM-FCN Model in Ship Track Prediction. J/OL. Control and Decision: 1-7[2022-02-10]. DOI: 10.13195 /j.kzyjc.2020.1795.Google Scholar
- Chen Yingyu, Suo Yongfeng, Yang Shenhua.Ship Track Prediction Based on Grey Wolf Optimization Support Vector Regression. J. Journal of Shanghai Maritime University, 2021, 42(04): 20-25+46. DOI: 10.13340/j.jsmu. 2021. 04. 004.Google Scholar
- Huang G B, Zhu Q Y, Siew C K. Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks. C// IEEE International Joint Conference on Neural Networks. IEEE, 2005.Google Scholar
- Zl A, Chu K, Kp A. A Novel Error-Output Recurrent Two-layer Extreme Learning Machine for Multi-step Time Series Prediction. J. Sustainable Cities and Society, 2020.Google Scholar
- Li Jihan, Li Xiaoli, Wang Kang, Cui Guimei. Prediction of Atmospheric PM (2.5) Concentration Based on PCA-OS-ELM. J. Journal of Beijing Institute of Technology, 2021, 41(12): 1262-1268. DOI: 10.15918/j.tbit1001-0645.2020.199.Google Scholar
- Tang Ting, Yuan Huimei. RUL prediction of lithium-ion battery based on improved ELM. J. Battery, 2021,51(06): 548-552. DOI: 10.19535/j.1001-1579.2021.06.002.Google Scholar
- Ester M, Kriegel H P, Sander J, A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. AAAI Press, 1996.Google Scholar
- F Itakura. Minimum Prediction Residual Principle Applied to Speech Recognition. J. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1975, 23(1): 67-72.Google ScholarCross Ref
Index Terms
- Ship Track Prediction Model Based on Improved ELM
Recommendations
Tool Cutting Force Prediction Model Based on ALO-ELM Algorithm
Aiming at the problems of low learning efficiency, slow convergence speed, and low prediction accuracy of traditional data-driven model applied to tool cutting force prediction, a prediction method of tool cutting force based on ant lion optimizer (ALO) ...
Ship Track Prediction Based on DLGWO-SVR
To improve the accuracy of ship track prediction, the improved Grey Wolf Optimizer (GWO) and Support Vector Regression (SVR) models are incorporated for ship track prediction. The hunting strategy of dimensional learning was used to optimize the move ...
Prediction of Ship Motion Attitude Based on Combined Model
icWCSN '23: Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor NetworksDue to the influence of sea conditions, six dimensional movements, including heave, roll, pitch, sway, surge and yaw, are easy to be produced while ships sailing. These motions seriously affect the safety of its sailing, so the prediction of ship ...
Comments