TrajReducer: a cross-dimension indexer-based reducer for vessel destination prediction
Bibliographic record
Abstract
• The paper proposed TrajReducer, a framework that enhances prediction accuracy and computational efficiency by indexing the trajectories through spatial clustering with cross-dimensional metadata ranking. • The TrajReducer optimized the prediction performance by 0.249. • Comparative studies validate the proposed model outperforms state-of-the-arts. Maritime shipping underpins over 80 % of global trade, making accurate vessel destination prediction essential for optimizing port operations and strategic decision-making. Traditional prediction methods relying solely on spatial-temporal data often struggle with computational inefficiency and limited accuracy, particularly with partial trajectory information. To address these challenges, we propose TrajReducer, a framework that enhances prediction accuracy and computational efficiency by indexing the trajectories through spatial clustering with cross-dimensional metadata ranking. By clustering past trajectories based on spatial characteristics and applying metadata ranking on static and dynamic vessel attributes, TrajReducer selectively narrows comparison to relevant trajectories, achieving significant computational savings. The trajectories of traveling vessels will be compared to historical ones selected by the TrajReducer. We define similarity as the likelihood that two trajectories have the same destination. The destination of the most similar past trajectory is predicted to be the destination port of the traveling vessel. Experimental results demonstrate the consistent performance of TrajReducer, with high top-1 accuracy and low average prediction distance error (APDE) at various travel stages, along with a high Reduce Ratio indicating advanced efficiency. Compared to existing models, TrajReducer offers superior accuracy, balancing prediction quality and efficiency. This efficient framework holds substantial implications for maritime operations, enabling precise port scheduling, optimized resource allocation, and enhanced maritime traffic management, ultimately supporting sustainable practices in global shipping.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".