Developing Collision Prediction Models with Weather and Driver Characteristics Related Variables
Bibliographic record
Abstract
This study analyzed and modeled the days of week variation of motor vehicle collision frequencies for the City of Edmonton, Canada, for a period of seven years (2003-2009). First, the study developed collision prediction models (CPMs) using the generalized linear modeling approach with a negative binomial (NB) error structure. These NB CPMs established a relationship between daily collision frequency and two weather related collision contributing factors, namely number of daylight hours, and number of snowfall hours. Daily collision frequency was found to be negatively associated with number of daylight hours. However, number of snowfall hours showed a positive correlation with collision frequency. Consistent spikes in collision frequency were also observed on Friday compared to other days of week. Weekend (Saturday and Sunday) and holiday showed less collision frequencies compared to Wednesday. However, Monday, Tuesday and Thursday were not significantly different from Wednesday with respect to collision occurrences. Next, the study developed a multinomial logistic (MNL) model to estimate the conditional probability of different age and gender categories of drivers involved in collision for each day of week considering collision had happened. The MNL model showed that male drivers were more likely to be involved in collisions on weekdays except Thursday, weekend, and holiday. Besides, drivers aged below 20 are the most vulnerable group during Friday-Sunday, weekend, and were followed by drivers aged between 20-30 and 30-40, respectively. On Tuesday and Thursday, drivers aged between 40-50 were least likely to be involved in collision with respect to drivers aged 60 and above.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 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".