Comparison between Surrogate Safety Assessment Model and Real-Time Safety Models in Predicting Field-Measured Conflicts at Signalized Intersections
Bibliographic record
Abstract
Traffic simulation models are frequently used to evaluate the safety of signalized intersections, especially when testing unconventional designs or investigating the effects of emerging technologies such as connected and autonomous vehicles. In this approach, vehicle trajectories extracted from traffic simulation are usually analyzed using the surrogate safety assessment model (SSAM) to estimate the number and severity of traffic conflicts. However, recent research has shown that evaluating safety using SSAM has several limitations. First, a rigorous calibration procedure must be applied to the simulation model to obtain reliable conflict results. Second, simulation models in many cases do not accurately represent actual driving behavior. Subsequently, they often fail to capture the actual mechanisms generating near-misses. This paper presents a new procedure, alternative to SSAM, for evaluating the safety of signalized intersections. The procedure combines simulated vehicle trajectories with real-time safety models to predict rear-end conflicts. The conflict prediction is based on dynamic traffic parameters, such as traffic volume and shock wave characteristics, repeatedly measured over a short time interval (a few seconds). To validate the proposed procedure, its performance was investigated in predicting traffic conflicts extracted from 54 hours of real-world video data at two signalized intersections in the city of Surrey, British Columbia. The predicted conflict results were compared with SSAM. Overall, the results showed that the proposed procedure outperforms SSAM in relation to accuracy of conflict prediction. Lastly, a case study of using the proposed procedure in evaluating the safety impact of a recently developed connected-vehicles application is presented.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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".