Extraction of Key Factors of Ship Following Behavior based on Rough Set Theory

Bo Tu, Yihua Liu, Xinyue Li and Shiyu Tu
Additional contact information
Bo Tu: Shanghai Maritime University, China
Yihua Liu: Shanghai Maritime University, China
Xinyue Li: Shanghai Maritime University, China
Shiyu Tu: Shanghai Maritime University, China

European Journal of Engineering and Technology Research, 2022, vol. 7, issue 3, 55-62

Abstract: In order to clarify the main influencing factors of ship following behavior, an algorithm for extracting key factors of ship following behavior based on ship AIS data in straight channel waters is proposed. After the statistical analysis of the obtained ship following trajectory data, the correlation of each influencing factor of ship following behavior and the importance of their influence on the ship following distance are analyzed by applying the rough set dependency and importance assignment methods, and the attribute simplification algorithm based on the rough set dependency and the decision rule algorithm based on the rough set attribute simplification are used to mine the strong correlation rules between each influencing factor and the following distance. Finally, set the straight section of the south channel of the Yangtze River estuary as the study water for case study. The results show that the average ship speed is 9.41 knots, the average space of ship is 2110 m, the average bow time is 450s, and the average relative speed is 0 knot; the weights of ship speed, ship length, relative speed, ship type, density and pilot class in the factors affecting ship following behavior are 0.1953, 0.0836, 0.2092, 0.2265, 0.1852 and 0.1058, respectively; the correlation between ship speed and relative speed is large, no strong correlation rule was found with others; ship following behavior should focus on ship speed and density, and the distance of [1000, 2000 m) is the key concern interval.

Keywords: AIS data; association rules; attribute importance; MASS; rough set theory; ship following behavior (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
https://eu-opensci.org/index.php/ejeng/article/view/62804 Abstract page (text/html)
https://eu-opensci.org/index.php/ejeng/article/download/62804/12821 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:epw:ejeng0:v:7:y:2022:i:3:id:62804

DOI: 10.24018/ejeng.2022.7.3.2804

Access Statistics for this article

More articles in European Journal of Engineering and Technology Research from European Open Science
Bibliographic data for series maintained by Support ().