基于特征注意力机制的RNN-Bi-LSTM船舶轨迹预测Ship Trajectory Prediction of RNN-Bi-LSTM Based on Characteristic Attention Mechanism
赵程栋,庄继晖,程晓鸣,李宇航,郭东平
摘要(Abstract)：
【目的】为更准确预测船舶轨迹，基于RNN、Bi-LSTM和注意力机制，研究一种结合特征注意力机制的RNN-Bi-LSTM的船舶轨迹预测模型。【方法】基于AIS数据构建基于循环神经网络(RNN)与双向长短时记忆网络(Bi-LSTM)的混合神经网络模型，并在混合模型中加入特征注意力机制对数据特征进行权重分配，提升模型对船舶轨迹预测精度。【结果】使用实际运行的船舶AIS数据，对模型的有效性和实用性进行验证，测试集均方误差为2.751×10~(-5)、均方根误差为5.245×10~(-3)，在连续弯道预测中的均方误差为4.359×10~(-6)、均方根误差为2.088×10~(-3)。【结论】结合特征注意力机制的RNN-Bi-LSTM相较于传统的预测神经网络，船舶轨迹预测精度更高，尤其在弯道预测中也表现出较好的符合度。
关键词(KeyWords)： AIS信息;循环神经网络;双向长短时记忆网络;特征注意力机制;船舶轨迹预测
基金项目(Foundation):
作者(Author): 赵程栋,庄继晖,程晓鸣,李宇航,郭东平
参考文献(References)：
- [1]姜佰辰,关键,周伟,等.基于多项式卡尔曼滤波的船舶轨迹预测算法[J].信号处理,2019,35(5):741-746.
- [2]周艳萍,曾宪群,蔡玲.改进灰色模型的船舶航行轨迹自动预测研究[J].舰船科学技术,2021,43(20):34-36.
- [3]何静.利用卡尔曼滤波预测船舶航行轨迹异常行为[J].舰船科学技术,2017,39(2):16-18.
- [4]李永,成梦雅.LSTM船舶航迹预测模型[J].计算机技术与发展,2021,31(9):149-154.
- [5]王研婷.基于CNN和LSTM的船舶航迹预测[D].大连:大连海事大学,2020.
- [6]ZHANG S,WANG L,ZHU M D,et al.A Bi-directional LSTM ship trajectory prediction method based on attention mechanism[C]//2021 IEEE 5th Advanced Information Technology,Electronic and Automation Control Conference.IEEE,2021:1987-1993.
- [7]赵梁滨.基于AIS数据和循环神经网络的船舶轨迹异常检测[D].大连:大连海事大学,2019.
- [8]WANG C,FU Y H.Ship trajectory prediction based on attention in bidirectional recurrent neural networks[C]//2020 5th International Conference on Information Science,Computer Technology and Transportation,ISCTT,2020:529-533.
- [9]SUO Y F,CHEN W K,CLARAMUNT C,et al.A ship trajectory prediction framework based on a recurrent neural network[J].Sensors (Basel,Switzerland),2020,20(18):5133.
- [10]权波,杨博辰,胡可奇,等.基于LSTM的船舶航迹预测模型[J].计算机科学,2018,45(S2):126-131.
- [11]丁孟真.基于AIS数据的船舶轨迹预测方法研究[D].兰州:兰州大学,2020.
- [12]LUONG T,PHAM H,MANNING C D.Effective approaches to attention-based neural machine translation[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.Stroudsburg,PA,USA:Association for Computational Linguistics,2015:1412-1421.
- [13]LI C K,HOU Y H,WANG P C,et al.Joint distance maps based action recognition with convolutional neural networks[J].IEEE Signal Processing Letters,2017,24(5):624-628.
- [14]ZHANG Z Y,NI G X,XU Y G.Ship trajectory prediction based on LSTM neural network[C]//2020 IEEE 5th Information Technology and Mechatronics Engineering Conference.IEEE,2020:1356-1364.
- [15]胡玉可.基于循环神经网络的船舶轨迹预测方法研究[D].合肥:合肥工业大学,2020.
- [16]龚志猛,冷文浩,孟斌.潜航器轨迹跟踪与航向预测算法[J].船舶工程,2019,41(2):56-61.
- [17]黄妙芬,王江颖,邢旭峰,等.基于LSTM网络的海水石油污染含量遥感预测模型[J].广东海洋大学学报,2021,41(5):67-73.