Gan, S, Liang, S, Li, K orcid.org/0000-0001-6657-0522 et al. (2 more authors) (2016) Ship trajectory prediction for intelligent traffic management using clustering and ANN. In: Proceedings of the 2016 UKACC 11th International Conference on Control (CONTROL). 2016 UKACC 11th International Conference on Control (CONTROL), 31 Aug - 02 Sep 2016, Belfast, UK. IEEE ISBN 978-1-4673-9891-6
Abstract
Yangtze River is the world's busiest inland waterway. Ships need to be guided when passing through controlled waterways based on their trajectory predictions. Inaccurate predicted trajectories lead to non-optimal traffic signalling which may cause significant traffic jam. For the existing intelligent traffic signalling systems (ITSSs), ships are supposed to travel exactly along the mid-line of the Yangtze River, which has caused many problems and issues. Over the last few years, traffic data have been growing exponentially, and we have gone into big data ear. This trend allows us to predict the ship travel trajectories using big historical data. In this paper, the historical trajectories are grouped by the popular K-Means clustering algorithm firstly, and then Artificial Neural Network (ANN) models are built using the above clustering results and other known factors (i.e. ship speed, loading capacity, self-weight, maximum power and water level) to predict the ships' trajectories. The experimental results show that the developed model is in good agreement with the actual data with more than 70% accuracy. It will also help to generate the optimal traffic commands for Yangtze River traffic control.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Keywords: | intelligent traffic signalling; k-means clustering; artificial neural networks (ANN); ship trajectory prediction; data driven |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Electronic & Electrical Engineering (Leeds) > Institute of Communication & Power Networks (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 05 Nov 2019 16:02 |
Last Modified: | 05 Nov 2019 16:02 |
Status: | Published |
Publisher: | IEEE |
Identification Number: | 10.1109/control.2016.7737569 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:153026 |