Modeling car and heavy commercial vehicle crashes on two-lane rural highways using the Poisson-Tweedie regression approach
Bibliographic record
Abstract
This article develops vehicle type–based crash-prediction models for cars and heavy commercial vehicles (HCVs) as a function of the curve geometry and vehicle-based design consistency criteria under heterogeneous traffic conditions on two-lane, two-way rural highways, specifically in hilly terrains. A National Highway (NH-953) connecting Netrang and Rajpipla in India was selected. There are 38 curves in the study section, each having a different curve geometry. Speed data were collected using the radar gun for cars and HCVs. The geometric design consistency was evaluated using Criterion I (the difference between operating and design speeds). The results show that 53% of the curves for cars have good consistency, compared to 32% and 29% of the curves for HCVs, which have fair and poor consistency, respectively. The Poisson-Tweedie regression technique, which provides a unified framework to model over-dispersed, under-dispersed, zero-inflated, count-data, and multiple-response variables, was used to develop the crash prediction models. The results revealed that crashes (cars and HCVs) decrease as the curve radius, deflection angle, and length increase. Similarly, as the tangent length increases, the difference between operating and design speeds increases, making inconsistent highway alignment, resulting in increased chances of crashes. The results of the present study can help highway authorities to evaluate highway alignment consistency and develop corresponding proactive strategies to improve highway safety.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".