Investigation of the Influence of Boundary Data Assignment on the Development of Multimodal Macro-level Collision Prediction Models (CPMs)
Bibliographic record
Abstract
Developing reliable collision prediction models (CPMs) at the Traffic AnalysisZones (TAZs) aggregation level requires accurate assignment for boundary geocoded data between adjacent TAZs.Traffic Analysis Zones (TAZs) are spatial divisions within a region commonly used for traffic analysis purpose.The boundaries of TAZs are frequently set to match the centerline of major roadway segments.Collision counts data has shown that significant proportion of collisions occur frequently on these major roadways.Consequently, the way in which collisions, and also other geocoded data, along TAZs' boundaries are assigned into adjacent zones is of interest because it has direct impact on the prediction ability of macro-level CPMs.In this study, data for 422 TAZs from the City of Ottawa was used to develop macro-level CPMs.Geocoded data on TAZ's boundary were assigned between adjacent TAZs using ten different assignment methods.Negative binomial regression (NB) was applied to develop CPMs for total, nonfatal injury, property damage only (PDO), bike-involved, and pedestrian-involved collisions.Many explanatory variables expected to have an effect on the roadway safety performance at the TAZ's level were aggregated to the TAZ's level.These independent variables were categorized into four data categories including roadway characteristics, socio-economic and demographic characteristics, exposure, and Transportation Demand Management (TDM) variables.In addition, Zero-inflated regression was used to model fatal collisions as a function of Vehicle Kilometre Travelled (VKT) and total lane kilometre (TLKM).Results of the developed models show that different geocoded boundary data assignment methods do affect the accuracy of developed CPMs results significantly.It was found that allocating boundary data to TAZs evenly improved modelTable C.4 Uncorrelated Independent Variables Combinations Models Independent Variables Combination Roadway characteristics, where the roadway classified based on roadway classes, and exposure variables.
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 | 0.021 | 0.072 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".