Path optimization results under different conditions: GL-SSL model’s dynamic path planning in smart port multimodal transportation, showcasing path optimization at port nodes under normal conditions, peak transportation periods, and adverse weather conditions.

<p>Path optimization results under different conditions: GL-SSL model’s dynamic path planning in smart port multimodal transportation, showcasing path optimization at port nodes under normal conditions, peak transportation periods, and adverse weather conditions.</p>

Saved in:

Bibliographic Details
Main Author:	Jiangjiang He (9676377) (author)
Other Authors:	Weixun Chen (14095413) (author), Jiaren Sun (634396) (author), Lin Zhu (192179) (author)
Published:	2025
Subjects:	Science Policy Infectious Diseases Biological Sciences not elsewhere classified Information Systems not elsewhere classified practical application potential multiple public datasets multimodal data fusion key performance metrics including ais data global shipping data enabling efficient optimization deep learning models model fully exploits units </ b div >< p smart port multi port transport networks labor cost ), transport cost supervised learning smart ports path optimization ssl model model ’ 200 cost training loss traditional algorithms term memory temporal variations substantially better structured information strong robustness ssl ). results show rapid convergence peak traffic path planning paper addresses lstm ), findings highlight equipment wear equipment failures dynamic environments delay rate complex scenarios adverse weather
Tags:	Add Tag No Tags, Be the first to tag this record!

Path optimization results under different conditions: GL-SSL model’s dynamic path planning in smart port multimodal transportation, showcasing path optimization at port nodes under normal conditions, peak transportation periods, and adverse weather conditions.

Similar Items