Interactive exploration of movement data: A case study of geovisual analytics for fishing vessel analysis
Bibliographic record
Abstract
The analysis of large movement datasets is a challenging task, because of their size and spatial complexity. This paper presents an interactive geovisual analytics approach named Hybrid Spatio-Temporal Filtering that integrates filtering of multiple movement characteristics, geovisual representations of the data, and multiple coordinated views to enable analysts to focus on movement patterns that are of interest. In particular, we propose a novel technique that combines the fractal dimension and velocity of movement paths to filter out uninteresting records through an iterative signature-building process. In order to allow analysts to explore the data at different scales of the movement path length, fractal dimension estimation is performed using an adjustable moving window technique. These tools are provided in conjunction with a probability-based zonal incursion tool to visually represent when the movement nears areas of interest. The outcome is a geovisual analytics system that allows analysts to specify a hybrid filter consisting of the desired movement path complexity, the length of the paths to consider, and the velocity range that represents specific types of behaviors. This filtering of the data supports analysts in identifying movement paths that match their specified interests, resulting in a reduction in the amount of data shown to the analyst. The utility of the approach was validated through field trials, wherein fisheries enforcement officers analyzed and explored fishing vessel movement data using the prototype system. The participants responded positively to the features of the system and the support it provided for their data analysis activities. The combination of fractal dimension, velocity, and temporal filtering helped them to effectively identify subsets of data that conformed to particular behavioral patterns of interest.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 source (direct Gemma or distilled Codex), 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".