Основные понятия
Hierarchical trajectory representation improves vessel behavior clustering.
Аннотация
The article introduces PC-HiV, a method for predictive clustering of vessel behavior based on hierarchical trajectory representation. It aims to capture behavioral evolution discrepancies between vessel types and within emission control areas. The proposed method outperforms existing methods in terms of purity score. Experiments on real AIS datasets demonstrate the effectiveness of PC-HiV in capturing behavioral evolution.
Structure:
- Introduction to vessel trajectory clustering.
- Proposed method: PC-HiV for predictive clustering.
- Experiments and results analysis.
- Case studies showcasing the effectiveness of PC-HiV.
- Limitations and future directions.
Статистика
Results show that our method outperforms NN-Kmeans and Robust DAA by 3.9% and 6.4% of the purity score.
Цитаты
"PC-HiV first uses hierarchical representations to transform every trajectory into a behavioral sequence."
"Experiments on real AIS datasets demonstrate PC-HiV’s superiority over existing methods."