基于改进Seq2Seq的短时AIS轨迹序列预测模型

doi:10.11896/jsjkx.190800060

计算机科学 ›› 2020, Vol. 47 ›› Issue (9): 169-174.doi: 10.11896/jsjkx.190800060

• 计算机图形学&多媒体 • 上一篇下一篇

基于改进Seq2Seq的短时AIS轨迹序列预测模型

游兰¹, 韩雪薇¹, 何正伟^2,3,4, 肖丝雨¹, 何渡⁵, 潘筱萌¹

1 湖北大学计算机与信息工程学院武汉430062
2 武汉理工大学航运学院武汉430063
3 武汉理工大学内河航运技术湖北省重点实验室武汉430063
4 国家水运安全工程技术研究中心武汉430063
5 湖北省科技信息研究院武汉430071

收稿日期:2019-08-24 发布日期:2020-09-10
通讯作者: 何正伟(www.hzw@whut.edu.cn)
作者简介:yoyo@hubu.edu.cn
基金资助:
湖北省自然科学基金面上项目(2019CFB757);国家水运安全工程技术研究中心开放基金(A2019011);内河航运技术湖北省重点实验室基金(NHHY2017001);湖北省教育厅科学研究计划重点项目(D20161001);中央高校基本科研业务费专项资金(2019III050GX,2019III007GX)

Improved Sequence-to-Sequence Model for Short-term Vessel Trajectory Prediction Using AIS Data Streams

YOU Lan¹, HAN Xue-wei¹, HE Zheng-wei^2,3,4, XIAO Si-yu¹, HE Du⁵, PAN Xiao-meng¹

1 School of Computer Science & Information Engineering,Hubei University,Wuhan 430062,China
2 School of Navigation,Wuhan University of Technology,Wuhan 430063,China
3 Hubei Key Laboratory of Inland Shipping Technology,Wuhan University of Technology,Wuhan 430063,China
4 National Engineering Research Center for Water Transportation Safely,Wuhan 430063,China
5 Hubei Engineering Research Center for Education Information,Wuhan 430071,China

Received:2019-08-24 Published:2020-09-10
About author:YOU Lan,born in 1978,Ph.D,associate professor.Her main research interests includespatio-temporal data,deep learning and knowledge engineering.
HE Zheng-wei,born in 1977, Ph.D,associated professor.His main research interests include traffic big data processing and mining, maritime information systems and traffic environment simulation,artificial intelligence application technology,deep learning and smart navigation.
Supported by:
Hubei Province Natural Science Foundation Item (2019CFB757),Open Fund of National Engineering Research Center for Water Transport Safety (A2019011),Fund of Hubei Key Laboratory of Inland Shipping Technology (NHHY2017001),Key Project of Scientific Research Plan of Hubei Ministry of Education (D20161001) and Fundamental Research Funds for the Central Universities (2019III050GX,2019III007GX).

摘要/Abstract

摘要： 采用深度学习进行船舶轨迹序列预测对于智能航运具有重要意义。船舶自动识别系统(Automatic Identification System,AIS)蕴藏着大量船舶轨迹特征,基于AIS数据预测船舶轨迹是近年智能航运研究的热点之一。文中提出了一种基于改进Seq2Seq的短时AIS轨迹序列预测模型,该模型使用门控循环单元网络将历史时空序列编码为一个上下文向量,用以保留轨迹空间点间的时序关系,同时缓解梯度下降的问题。通过使用门控循环单元网络作为解码器来预测船舶轨迹的时空序列。实验采用了大规模真实船舶AIS数据,选取两类典型河段(重庆弯曲河段和武汉顺直河段)为实验区域,以评估和验证模型的有效性和适用性。实验证明,该模型能够有效提高短时轨迹序列预测的准确性和效率,为智能航船碰撞预警提供了一种有效可行的方法。

关键词: 轨迹预测, 序列到序列模型, 循环神经网络, 船舶自动识别系统, 时空数据挖掘

Abstract: Using deep learning to predict the vessel trajectory is of great significance for the intelligent shipping.AIS (Automatic Identification System) data contain a huge amount of information about vessel trajectory features.The prediction of ship trajectories based on AIS data becomes one of the research hotspots in the intelligent shipping realm.In this paper,an improved sequence-to-sequence model using AIS data streams is proposed for the short-term vessel trajectory prediction.The proposed model utilizes a GRU network to encode the historical spatio-temporal sequence into a context vector,which not only preserves the sequential relationship among those trail points,but also is helpful for the alleviation of the gradient descent problem.Meanwhile,a GRU network is used as a decoder to output target trail points sequence.In this paper,a large scale of real AIS data are used in the experiments.The Chongqing section and the Wuhan section of the Yangzi River are selected as typical experimental areas,which is for the evaluation of the validity and applicability of the model.Experimental results show that the proposed model improves the accuracy and efficiency of short-term ship trajectory prediction.The proposed model provides an effective solution for the intelligent shipping warning in the future.

Key words: Trajectory prediction, Sequence-to-sequence model, Recurrent neural network, Automatic identification system, Spatio-temporal data mining

中图分类号:

TP183

游兰, 韩雪薇, 何正伟, 肖丝雨, 何渡, 潘筱萌. 基于改进Seq2Seq的短时AIS轨迹序列预测模型[J]. 计算机科学, 2020, 47(9): 169-174.

YOU Lan, HAN Xue-wei, HE Zheng-wei, XIAO Si-yu, HE Du, PAN Xiao-meng. Improved Sequence-to-Sequence Model for Short-term Vessel Trajectory Prediction Using AIS Data Streams[J]. Computer Science, 2020, 47(9): 169-174.

参考文献

[1] PALLOTTA G,VESPE M,BRYAN K.Vessel Pattern Know-ledge Discovery from AIS Data:A Framework for Anomaly Detection and Route Prediction[J].Entropy,2013,15(6):2218-2245.
[2] IALA.An Overview of AIS[M/OL].[2019-08-31].https://www.iala-aism.org/product/an-overview-of-ais-1082/.
[3] TU E,ZHANG G,RACHMAWATI L,et al.Exploiting AIS data for intelligent maritime navigation:a comprehensive survey from data to methodology[J].IEEE Transactions on Intelligent Transportation Systems,2017,19:1559-1582.
[4] PERERA L P,OLIVEIRA P,SOARES C G.Maritime TrafficMonitoring Based on Vessel Detection,Tracking,State Estimation,and Trajectory Prediction[J].IEEE Transactions on Intelligent Transportation Systems,2012,13(3):1188-1200.
[5] CAVENEY D.Numerical integration for future vehicle pathprediction[C]//Proceedings of the 2007 American Control Conference.IEEE,2007:3906-3912.
[6] SEMERDJIEV E,MIHAYLOVA L,SCIENCE C.Variable-and fixed-structure augmented interacting multiple model algorithms for manoeuvring ship tracking based on new ship models[J].International Journal of Applied Mathematics,2000,10(3):591-604.
[7] GREWAL M S.Kalman filtering[M].Springer,2011.
[8] PERERA L P,SOARES C G.Ocean vessel trajectory estimation and prediction based on extended kalman filter[C]//Proceedings of the The Second International Conference on Adaptive and Self-Adaptive Systems and Applications.Citeseer,2020:14-20.
[9] QUAN B,YANG B C.Prediction Model of Ship TrajectoryBased on LSTM[J].Computer Science,2018,45(S2):136-141.
[10] NGUYEN D D,VAN C L,ALI M I.Vessel Trajectory Prediction using Sequence-to-Sequence Models over Spatial Grid[C]//Proceedings of the 12th ACM International Conference on Distributed and Event-based Systems.Hamilton,New Zealand,2018:258-261.
[11] ALAHI A,GOEL K,RAMANATHAN V,et al.Social lstm:Human trajectory prediction in crowded spaces[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:961-971.
[12] FFRANCISCO A,NAVARRO F,et al.Predicting aircraft trajectory:U.S,9020662[P].2015-04-28.http://www.freepatentsonline.com/9020662.html.
[13] WIEST J,HÖFFKEN M,KRESEL U,et al.Probabilistic trajectory prediction with Gaussian mixture models[C]//Proceedings of the 2012 IEEE Intelligent Vehicles Symposium.IEEE,2012:141-146.
[14] YAN Z X.Traj-ARIMA:a spatial-time series model for net-work-constrained trajectory[C]//Proceedings of the Procee-dings of the Third International Workshop on Computational Transportation Science.ACM,2010:11-16.
[15] ZHENG Y.Trajectory data mining:an overview[J].ACMTransactions on Intelligent Systems Technology,2015,6(3):29.
[16] CHO K,VAN MERRIËNBOER B,GULCEHRE C,et al.Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP).2014.
[17] SUTSKEVER I,VINYALS O,LE Q V.Sequence to sequence learning with neural networks[C]//Proceedings of the Advances in Neural Information Processing Systems.NIPS,2014:3104-3112.
[18] KINGMA D P,BA J.Adam:A Method for Stochastic Optimization[C]//Proceedings of the the 3rd International Conference for Learning Representations.ICLR,2015:1139-1154.
[19] SRIVASTAVA N,HINTON G E,KRIZHEVSKY A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research,2014,15:1929-1958.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于改进Seq2Seq的短时AIS轨迹序列预测模型

Improved Sequence-to-Sequence Model for Short-term Vessel Trajectory Prediction Using AIS Data Streams

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	李亚男, 胡宇佳, 甘伟, 朱敏. 基于深度学习的miRNA靶位点预测研究综述[J]. 计算机科学, 2021, 48(1): 209-216.
[2]	庄世杰, 於志勇, 郭文忠, 黄昉菀. 基于Zoneout的跨尺度循环神经网络及其在短期电力负荷预测中的应用[J]. 计算机科学, 2020, 47(9): 105-109.
[3]	王鹏, 苏伟, 张久文, 刘映杰, 王臻睿. 基于船舶自动识别系统与人工神经网络的船舶载重预测[J]. 计算机科学, 2020, 47(6A): 49-53.
[4]	赫磊, 邵展鹏, 张剑华, 周小龙. 基于深度学习的行为识别算法综述[J]. 计算机科学, 2020, 47(6A): 139-147.
[5]	倪海清, 刘丹, 史梦雨. 基于语义感知的中文短文本摘要生成模型[J]. 计算机科学, 2020, 47(6): 74-78.
[6]	张志扬, 张凤荔, 陈学勤, 王瑞锦. 基于分层注意力的信息级联预测模型[J]. 计算机科学, 2020, 47(6): 201-209.
[7]	李太松,贺泽宇,王冰,颜永红,唐向红. 基于循环时间卷积网络的序列流推荐算法[J]. 计算机科学, 2020, 47(3): 103-109.
[8]	励益韬, 孙未未. 基于循环神经网络的轨迹压缩算法[J]. 计算机科学, 2020, 47(10): 102-107.
[9]	刘长赟,杨宇迪,周丽华,赵丽红. 带有时间标签的流行社交位置发现[J]. 计算机科学, 2019, 46(7): 186-194.
[10]	陈俊航, 徐小平, 杨恒泓. 基于Seq2seq模型的推荐应用研究[J]. 计算机科学, 2019, 46(6A): 493-496.
[11]	毛莺池, 曹海, 何进锋. 面向大坝变形监测的时空一体化预测算法[J]. 计算机科学, 2019, 46(2): 223-229.
[12]	敬颉, 陈潭, 杜文丽, 刘志康, 尹皓. 自动驾驶场景中增强深度学习的时空特征提取方法[J]. 计算机科学, 2019, 46(11A): 1-4.
[13]	肖锐, 蒋家琪, 张云春. 多义词语义拓扑及有监督的词义消歧研究[J]. 计算机科学, 2019, 46(11A): 13-18.
[14]	杨佳宁, 黄向生, 李宗翰, 荣灿, 刘道伟. 基于双层栈式长短期记忆的电网时空轨迹预测[J]. 计算机科学, 2019, 46(11A): 23-27.
[15]	张旭东, 杜家浩, 黄宇方, 石东贤, 缪永伟. 基于多尺度层级LSTM网络的时间序列预测分析[J]. 计算机科学, 2019, 46(11A): 52-57.