Research on ship traffic flow prediction based on GTO-CNN-LSTM

Runzhen Ding; Haibo Xie; Cheng Dai; Guanzhou Qiao

doi:10.1117/12.3015728

20 February 2024 Research on ship traffic flow prediction based on GTO-CNN-LSTM

Runzhen Ding, Haibo Xie, Cheng Dai, Guanzhou Qiao

Proceedings Volume 13064, Seventh International Conference on Traffic Engineering and Transportation System (ICTETS 2023); 130640B (2024) https://doi.org/10.1117/12.3015728
Event: 7th International Conference on Traffic Engineering and Transportation System (ICTETS 2023), 2023, Dalian, China

Abstract

To gain a more accurate understanding of maritime traffic flow, this paper proposes a ship traffic flow prediction method based on GTO-CNN-LSTM. The method utilizes ship traffic flow data, which is preprocessed and used as input for CNN-LSTM. By establishing a connection between the input and output through high-dimensional mapping, ship traffic flow is predicted. To further optimize the chosen model, the Artificial Gorilla Troop optimizer (GTO) is employed to adjust the model's hyperparameters, selecting the optimal ones for maximizing the model's performance. The method is validated using actual data from the vicinity of the Port of Los Angeles. The results demonstrate that the model achieves a prediction accuracy of 95.82%. The experiment confirms that the CNN-LSTM prediction model optimized with the GTO exhibits higher accuracy.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Runzhen Ding, Haibo Xie, Cheng Dai, and Guanzhou Qiao "Research on ship traffic flow prediction based on GTO-CNN-LSTM", Proc. SPIE 13064, Seventh International Conference on Traffic Engineering and Transportation System (ICTETS 2023), 130640B (20 February 2024); https://doi.org/10.1117/12.3015728

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