Extracting Maritime Traffic Networks from AIS Data Using Evolutionary Algorithm
- PDF / 2,753,610 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 87 Downloads / 264 Views
RESEARCH PAPER
Extracting Maritime Traffic Networks from AIS Data Using Evolutionary Algorithm Dominik Filipiak • Krzysztof We˛cel Witold Abramowicz
•
Milena Stro´z_ yna
•
Michał Michalak
•
Received: 5 February 2020 / Accepted: 19 June 2020 The Author(s) 2020
Abstract The presented method reconstructs a network (a graph) from AIS data, which reflects vessel traffic and can be used for route planning. The approach consists of three main steps: maneuvering points detection, waypoints discovery, and edge construction. The maneuvering points detection uses the CUSUM method and reduces the amount of data for further processing. The genetic algorithm with spatial partitioning is used for waypoints discovery. Finally, edges connecting these waypoints form the final maritime traffic network. The approach aims at advancing the practice of maritime voyage planning, which is typically done manually by a ship’s navigation officer. The authors demonstrate the results of the implementation using Apache Spark, a popular distributed and parallel computing framework. The method is evaluated by comparing the results with an on-line voyage planning application. The evaluation shows that the approach has the capacity to generate a graph which resembles the realworld maritime traffic network.
Accepted after one revision by Christof Weinhardt. D. Filipiak (&) K. We˛cel M. Stro´z_ yna W. Abramowicz Department of Information Systems, Poznan´ University of Economics and Business, Aleja Niepodległos´ci 10, 61-875 Poznan´, Poland e-mail: [email protected] K. We˛cel e-mail: [email protected] M. Stro´z_ yna e-mail: [email protected] W. Abramowicz e-mail: [email protected]
Keywords Maritime traffic network Vessel routing Route planning AIS Maritime traffic graph Waypoint discovery Graph discovery Artificial intelligence Genetic algorithm
1 Introduction In the maritime domain, a safe and efficient vessel operation requires a prescient berth to berth voyage planning, resulting in a route that consists of waypoints and legs. A waypoint is a single coordinate within a route, at which a vessel stops or changes its course. Despite the existence of a number of supporting bridge systems, such a voyage is normally planned manually by the ship’s crew. This task might be supported by additional checking facilities, e.g., warning about unsafe water depths. Such support is especially important in areas with a high traffic density. In addition, navigators who are unfamiliar with a sea area do not necessarily have information about past experience and best practices in the considered area. This problem can be addressed by an assistance system that supports the navigator in planning a safe and efficient route before the voyage starts, by providing a network of typical traffic routes based on past behavior of other, similar ships that were traveling in a given area. In this paper we show that such a network can be extracted automatically based on past trajectories of ships using v
Data Loading...
