Pedestrian Collision Prediction Models for Urban Intersections
Bibliographic record
Abstract
In more recent safety analysis methods, collision prediction models can be used for identifying intersections with promise of safety improvement and for evaluating the effects of treatment. Considerable effort has been directed at developing collision prediction models, but little has been directed at pedestrian collisions. Collisions involving motor vehicles and pedestrians pose a significant safety problem, principally in urban areas, where the levels of vehicle-pedestrian conflicts are high. Data from Toronto, Canada, are used in the development of pedestrian collision prediction models for three- and four-legged urban intersections, with and without signal control. These models, which relate safety to pedestrian and vehicle traffic volumes, can be used to identify locations that might be targeted for treatment and to help evaluate treatment effects. Models are developed by using pedestrian and vehicular volumes and vehicle volumes only. It is seen that the use of pedestrian volume information results in a much richer model, emphasizing the importance of collecting this information in routine traffic counting programs. An important issue for collision prediction models is transferability to other jurisdictions. This is especially important in the case of pedestrian collision models, because many jurisdictions may not have data sets containing sufficient collisions and pedestrian volume counts with which to calibrate reliable models. Data from the city of Hamilton, Ontario, were used to test the transferability of the Toronto four-legged signalized intersection model. The test was successful: the recalibrated Toronto models predicted collision numbers that were very close to those predicted by the model calibrated directly for the Hamilton data.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| 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".