Research on decision-making model of ship approaching channel based on SVM classification algoritm

Zhiming Wang; Mengyuan Wang

doi:10.1117/12.2668606

16 February 2023 Research on decision-making model of ship approaching channel based on SVM classification algoritm

Zhiming Wang, Mengyuan Wang

Proceedings Volume 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022); 125913M (2023) https://doi.org/10.1117/12.2668606
Event: 6th International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 2022, Guangzhou, China

Abstract

In view of the complex constraints of ships choosing entry and exit channels, which are likely to cause ship congestion and low entry efficiency, the support vector machine algorithm is used to establish a classification model suitable for ship navigation channels to realize decision-making management and control of ships choosing entry and exit channels. By deleting the missing values and irrelevant features of AIS data, eight related factors related to ship size and sailing state were selected as input variables of support vector machine, and a two-classification model of waterway based on SVM was established. Using precision and recall as indicators to evaluate model performance and comparing the results of three machine learning classification algorithms: random forest, logistic regression, and support vector machine, it is found that the support vector machine model has the highest accuracy, reaching 92%, and the AUC is 94. %. The research results show that the ships navigable in the two channels have obvious differences, and the SVM model can better select the seaworthy channel.

Citation Download Citation

Zhiming Wang and Mengyuan Wang "Research on decision-making model of ship approaching channel based on SVM classification algoritm", Proc. SPIE 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 125913M (16 February 2023); https://doi.org/10.1117/12.2668606

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available