基于改进Seq2Seq的短时AIS轨迹序列预测模型

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

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

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. https://doi.org/10.11896/jsjkx.190800060

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. https://doi.org/10.11896/jsjkx.190800060

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.

相关文章 15

[1]	黎嵘繁, 钟婷, 吴劲, 周帆, 匡平. 基于时空注意力克里金的边坡形变数据插值方法 Spatio-Temporal Attention-based Kriging for Land Deformation Data Interpolation 计算机科学, 2022, 49(8): 33-39. https://doi.org/10.11896/jsjkx.210600161
[2]	彭双, 伍江江, 陈浩, 杜春, 李军. 基于注意力神经网络的对地观测卫星星上自主任务规划方法 Satellite Onboard Observation Task Planning Based on Attention Neural Network 计算机科学, 2022, 49(7): 242-247. https://doi.org/10.11896/jsjkx.210500093
[3]	郁舒昊, 周辉, 叶春杨, 王太正. SDFA:基于多特征融合的船舶轨迹聚类方法研究 SDFA:Study on Ship Trajectory Clustering Method Based on Multi-feature Fusion 计算机科学, 2022, 49(6A): 256-260. https://doi.org/10.11896/jsjkx.211100253
[4]	喻昕, 林植良. 解决一类非光滑伪凸优化问题的新型神经网络 Novel Neural Network for Dealing with a Kind of Non-smooth Pseudoconvex Optimization Problems 计算机科学, 2022, 49(5): 227-234. https://doi.org/10.11896/jsjkx.210400179
[5]	安鑫, 代子彪, 李阳, 孙晓, 任福继. 基于BERT的端到端语音合成方法 End-to-End Speech Synthesis Based on BERT 计算机科学, 2022, 49(4): 221-226. https://doi.org/10.11896/jsjkx.210300071
[6]	时雨涛, 孙晓. 一种会话理解模型的问题生成方法 Conversational Comprehension Model for Question Generation 计算机科学, 2022, 49(3): 232-238. https://doi.org/10.11896/jsjkx.210200153
[7]	李昊, 曹书瑜, 陈亚青, 张敏. 基于注意力机制的用户轨迹识别模型 User Trajectory Identification Model via Attention Mechanism 计算机科学, 2022, 49(3): 308-312. https://doi.org/10.11896/jsjkx.210300231
[8]	肖丁, 张玙璠, 纪厚业. 基于多头注意力机制的用户窃电行为检测 Electricity Theft Detection Based on Multi-head Attention Mechanism 计算机科学, 2022, 49(1): 140-145. https://doi.org/10.11896/jsjkx.210100177
[9]	曾伟良, 陈漪皓, 姚若愚, 廖睿翔, 孙为军. 时空图注意力网络在交叉口车辆轨迹预测的应用 Application of Spatial-Temporal Graph Attention Networks in Trajectory Prediction for Vehicles at Intersections 计算机科学, 2021, 48(6A): 334-341. https://doi.org/10.11896/jsjkx.200800066
[10]	曾友渝, 谢强. 基于改进RNN和VAR的船舶设备故障预测方法 Fault Prediction Method Based on Improved RNN and VAR for Ship Equipment 计算机科学, 2021, 48(6): 184-189. https://doi.org/10.11896/jsjkx.200700117
[11]	尹久, 池凯凯, 宦若虹. 基于ATT-DGRU的文本方面级别情感分析 Aspect-level Sentiment Analysis of Text Based on ATT-DGRU 计算机科学, 2021, 48(5): 217-224. https://doi.org/10.11896/jsjkx.200500076
[12]	王习, 张凯, 李军辉, 孔芳, 张熠天. 联合自注意力和循环网络的图像标题生成 Generation of Image Caption of Joint Self-attention and Recurrent Neural Network 计算机科学, 2021, 48(4): 157-163. https://doi.org/10.11896/jsjkx.200300146
[13]	陈千, 车苗苗, 郭鑫, 王素格. 一种循环卷积注意力模型的文本情感分类方法 Recurrent Convolution Attention Model for Sentiment Classification 计算机科学, 2021, 48(2): 245-249. https://doi.org/10.11896/jsjkx.200100078
[14]	吕明琪, 洪照雄, 陈铁明. 一种融合时空关联与社会事件的交通流预测方法 Traffic Flow Forecasting Method Combining Spatio-Temporal Correlations and Social Events 计算机科学, 2021, 48(2): 264-270. https://doi.org/10.11896/jsjkx.200300098
[15]	李艾玲, 张凤荔, 高强, 王瑞锦. 基于自适应时间戳与多尺度特征提取的轨迹下一足迹预测模型 Trajectory Next Footprint Prediction Model Based on Adaptive Timestamp and Multi-scale Feature Extraction 计算机科学, 2021, 48(11A): 191-197. https://doi.org/10.11896/jsjkx.201200015

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed