Mining Microscopic Data of Vehicle Conflicts and Collisions to Investigate Collision Factors
Bibliographic record
Abstract
Road collisions lead to great human and financial costs for society. Although some progress has been made, this worldwide issue needs more attention, as the costs increase. Proactive methods for road safety analysis that do not depend on collision occurrences are needed. Collection and analysis of microscopic data (road user trajectories) about all traffic events with and without a collision are the only ways to gain insight into collision factors and processes; that is, the chains of events that lead to collisions. The first phase of the project reported in this paper used microscopic data extracted from video sensors and data mining techniques to identify patterns in the traffic event database. Decision trees, the k-means algorithm, and the hierarchical agglomerative clustering method were used to analyze the relationship between interaction attributes and outcome (collision or not) and identify groups of interactions with similar attributes. This approach was demonstrated on a data set collected in Kentucky of 295 traffic events and contained 213 conflicts and 82 collisions. The decision tree confirmed the importance of evasive action in the interaction outcome. Three clusters were found from speed indicators extracted from road users' trajectories: the cluster containing the fewest collisions had the lowest speeds of the three. This result hints at the existence of conflicts that are dissimilar from most collisions and may therefore not be suitable for surrogate safety analysis.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.006 | 0.005 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".