Understanding Traffic Patterns using Clustered Semantic Trajectories and Local Geographic Units
Bibliographic record
Abstract
Revealing traffic behavior from GPS data is a possibility to create a current and detailed data basis for city and traffic planning. Currently, traffic planning is mostly done by surveys or simulations, which may be costly, slow and not flexible enough. The concept of semantic trajectories has become relevant in recent years. Enriching GPS trip data with additional data helps to gain more insights into traffic behavior and can even reveal trip purposes of the drivers. This paper introduces a combination of a data-driven city segmentation with semantic trajectories. We show that enriching GPS trip data with additional information and analyzing the destination areas of these trajectories in detail helps to understand the journey and to reveal possible trip purposes. Multiple data sources are used, such as Points of Interest (POI), OD-points and whole trajectories of cars, vans and trucks. A fully automated clustering approach is introduced, which results in an interpretable city segmentation. The results are added to the trajectories before they are clustered. As a result, trajectories are clustered into four groups which can be interpreted as differences in the travel purpose as well as the start and end point of the trips. The method is demonstrated for the city of Frankfurt am Main, with trajectories, that either start, end, or pass through the city. By comparing the segmented city area with land-use maps and by interpreting a random sample of the clustered GPS trajectories, the plausibility of results is discussed.
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 | 0.000 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.006 | 0.006 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".