Identifying and Labeling Potentially Risky Driving: A Multistage Process Using Real-World Driving Data
Bibliographic record
Abstract
Every year, over 50 million people are injured and 1.35 million die in traffic accidents. Risky driving behaviors are responsible for over half of all fatal vehicle accidents. Identifying risky driving behaviors within real-world driving (RWD) datasets is a promising avenue to reduce the mortality burden associated with these unsafe behaviors, but numerous technical hurdles must be overcome to do so. Herein, we describe the implementation of a multistage process for classifying unlabeled RWD data as potentially risky or not. In the first stage, data are reformatted and reduced in preparation for classification. In the second stage, subsets of the reformatted data are labeled as potentially risky (or not) using the Iterative-DBSCAN method. In the third stage, the labeled subsets are then used to fit random forest (RF) classification models—RF models were chosen after they were found to be performing better than logistic regression and artificial neural network models. In the final stage, the RF models are used predictively to label the remaining RWD data as potentially risky (or not). The implementation of each stage is described and analyzed for the classification of RWD data from vehicles on public roads in Ann Arbor, Michigan. Overall, we identified 22.7 million observations of potentially risky driving out of 268.2 million observations. This study provides a novel approach for identifying potentially risky driving behaviors within RWD datasets. As such, this study represents an important step in the implementation of protocols designed to address and prevent the harms associated with risky driving.
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 | 0.008 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".