Uncertainty estimation on road safety analysis using bayesian deep neural networks
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Deep neural networks have been successfully used in many different areas of traffic engineering, such as crash prediction, intelligent signal optimization and real-time road surface condition monitoring. The benefits of deep neural networks are often uniquely suited to solve certain problems and can offer improvements in performance when compared to traditional methods. In collision prediction, uncertainty estimation is a critical area that can benefit from their application, and accurate information on the reliability of a model’s predictions can increase public confidence in those models. Applications of deep neural networks to this problem that consider these effects have not been studied previously. This paper develops a Bayesian deep neural network for crash prediction and examines the reliability of the model based on three key methods: layer-wise greedy unsupervised learning, Bayesian regularization and adapted marginalization. An uncertainty equation for the model is also proposed for this domain for the first time. To test the performance, eight years of car collision data collected from Highway 401, Canada, is used, and three experiments are designed.
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.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it