VesNet: A Vessel Network for Jointly Learning Route Pattern and Future Trajectory
Abstract
1 Introduction
2 Related Works
2.1 Human Mobility Prediction
2.2 Vessel Trajectory Prediction
2.3 Moving Trajectory Clustering
2.4 Multi-task Learning
3 Problem Formulation
4 Methodology
4.1 Route Pattern Extraction
4.1.1 Data Preprocessing.
4.1.2 Port Extraction.
4.1.3 Trajectory Clustering.
4.2 VesNet
4.2.1 Recurrent Neural Networks.
4.2.2 Seq2seq Structure.
4.2.3 Attention Mechanism.
4.2.4 VesNet Structure.
4.2.5 VesNet Training.
5 Experimental Setup
5.1 Dataset Description
Timestamp | MMSI | Lat (degree) | Lon (degree) | Speed (knot) | Course (degree) | Vessel type |
---|---|---|---|---|---|---|
2017/12/14 12:42 | 205451000 | 57.7413 | 10.4010 | 9.31 | 59.1 | RORO |
2017/12/14 12:48 | 205451000 | 57.7539 | 10.4419 | 9.16 | 64.0 | RORO |
2017/12/14 13:02 | 205451000 | 57.7840 | 10.5772 | 9.52 | 73.3 | RORO |
2017/12/14 13:13 | 205451000 | 57.8118 | 10.6563 | 9.41 | 52.8 | RORO |
2017/12/14 13:23 | 205451000 | 57.8204 | 10.7460 | 9.83 | 102.4 | RORO |
5.2 Experimental Settings
5.3 Evaluation Metrics
5.4 Baselines
5.5 Implementations
6 Performance Evaluation
6.1 Overall Performance
6.2 Route Pattern Classification Performance
Method | 5 min | 10 min | 30 min | 60 min | 120 min | |||||
---|---|---|---|---|---|---|---|---|---|---|
Recall | Precision | Recall | Precision | Recall | Precision | Recall | Precision | Recall | Precision | |
VesNet | 0.4409 | 0.5601 | 0.4837 | 0.5938 | 0.6835 | 0.7925 | 0.7066 | 0.8121 | 0.7344 | 0.8216 |
6.3 Prediction Error Distribution
6.4 Case Study
6.5 Parameter Tuning
6.6 Ablation Study
7 Conclusions
References
Index Terms
- VesNet: A Vessel Network for Jointly Learning Route Pattern and Future Trajectory
Recommendations
Vessel Trajectory Prediction using Sequence-to-Sequence Models over Spatial Grid
DEBS '18: Proceedings of the 12th ACM International Conference on Distributed and Event-based SystemsIn this paper, we propose a neural network based system to predict vessels' trajectories including the destination port and estimated arrival time. The system is designed to address DEBS Grand Challenge 2018, which provides a set of data streams ...
Online Long-Term Trajectory Prediction Based on Mined Route Patterns
Multiple-Aspect Analysis of Semantic TrajectoriesAbstractIn this paper, we present a Big data framework for the prediction of streaming trajectory data by exploiting mined patterns of trajectories, allowing accurate long-term predictions with low latency. In particular, to meet this goal we follow a two-...
Clustering and aggregating clues of trajectories for mining trajectory patterns and routes
In this paper, we propose a new trajectory pattern mining framework, namely Clustering and Aggregating Clues of Trajectories (CACT), for discovering trajectory routes that represent the frequent movement behaviors of a user. In addition to spatial and ...
Comments
Information & Contributors
Information
Published In
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 960Total Downloads
- Downloads (Last 12 months)960
- Downloads (Last 6 weeks)151
Other Metrics
Citations
Cited By
View allView Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in