中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
An unsupervised learning method with convolutional auto-encoder for vessel trajectory similarity computation

文献类型：期刊论文

作者Liang, Maohan2,5; Liu, Ryan Wen2,5; Li, Shichen1; Xiao, Zhe4; Liu, Xin3; Lu, Feng5
刊名OCEAN ENGINEERING
出版日期2021-04-01
卷号225页码:16
关键词Automatic identification system (AIS) Trajectory similarity Trajectory clustering Convolutional neural network (CNN) Convolutional auto-encoder (CAE)
ISSN号0029-8018
DOI10.1016/j.oceaneng.2021.108803
通讯作者Liu, Ryan Wen(wenliu@whut.edu.cn) ; Lu, Feng(luf@lreis.ac.cn)
英文摘要To achieve reliable mining results for massive vessel trajectories, one of the most important challenges is how to efficiently compute the similarities between different vessel trajectories. The computation of vessel trajectory similarity has recently attracted increasing attention in the maritime data mining research community. However, traditional shape- and warping-based methods often suffer from several drawbacks such as high computational cost and sensitivity to unwanted artifacts and non-uniform sampling rates, etc. To eliminate these drawbacks, we propose an unsupervised learning method which automatically extracts low-dimensional features through a convolutional auto-encoder (CAE). In particular, we first generate the informative trajectory images by remapping the raw vessel trajectories into two-dimensional matrices while maintaining the spatio-temporal properties. Based on the massive vessel trajectories collected, the CAE can learn the low-dimensional representations of informative trajectory images in an unsupervised manner. The trajectory similarity is finally equivalent to efficiently computing the similarities between the learned low-dimensional features, which strongly correlate with the raw vessel trajectories. Comprehensive experiments on realistic data sets have demonstrated that the proposed method largely outperforms traditional trajectory similarity computation methods in terms of efficiency and effectiveness. The high-quality trajectory clustering performance could also be guaranteed according to the CAE-based trajectory similarity computation results.
资助项目State Key Laboratory of Resources and Environmental Information System ; National Key R&D Program of China[2018YFC1407404]
WOS研究方向Engineering ; Oceanography
语种英语
WOS记录号WOS:000631882800024
出版者PERGAMON-ELSEVIER SCIENCE LTD
资助机构State Key Laboratory of Resources and Environmental Information System ; National Key R&D Program of China
源URL[http://ir.igsnrr.ac.cn/handle/311030/162122]  
专题中国科学院地理科学与资源研究所
通讯作者Liu, Ryan Wen; Lu, Feng
作者单位1.Wuhan Univ Technol, Sch Comp Sci & Technol, Wuhan 430063, Peoples R China
2.Wuhan Univ Technol, Sch Nav, Hubei Key Lab Inland Shipping Technol, Wuhan 430063, Peoples R China
3.AIST, AIRC RWBC OIL, Tokyo 1350064, Japan
4.ASTAR, Inst High Performance Comp, CO, Singapore 118411, Singapore
5.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China
推荐引用方式
GB/T 7714		 Liang, Maohan,Liu, Ryan Wen,Li, Shichen,et al. An unsupervised learning method with convolutional auto-encoder for vessel trajectory similarity computation[J]. OCEAN ENGINEERING,2021,225:16.
APA Liang, Maohan,Liu, Ryan Wen,Li, Shichen,Xiao, Zhe,Liu, Xin,&Lu, Feng.(2021).An unsupervised learning method with convolutional auto-encoder for vessel trajectory similarity computation.OCEAN ENGINEERING,225,16.
MLA Liang, Maohan,et al."An unsupervised learning method with convolutional auto-encoder for vessel trajectory similarity computation".OCEAN ENGINEERING 225(2021):16.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。