Detecting Incidents on Uninterrupted Flow Facilities: Bayesian-Monte Carlo Models
Bibliographic record
Abstract
Incidents on freeways and other major highways during high traffic volume conditions cause capacity bottlenecks. If incidents are detected quickly and are managed promptly, traffic delay can be reduced, and secondary accidents can be avoided. There are opportunities to capture real-time data and use these in incident detection algorithms designed specifically for alerting the traffic management centre about an incident to be the likely cause of a rapid drop in speed and formation of stationary and/or moving queues. Although over the years, a number of algorithms have been developed for this purpose, further advances are needed for reducing false alarms and improve the accuracy and speed of detecting incidents.An original incident detection model based on Bayesian, Montecarlo, and reliability methods was formulated, calibrated and verified for uninterrupted flow facilities. The inputs to the model were obtained from Montecarlo simulation and archived Highway 401 (Greater Toronto Area) incident and detector-based traffic flow data. The detectors served as a proxy for road-side units (RSU) of a future connected infrastructure-vehicle system.The incident detection model is built into an algorithm with the capability to identify patterns of traffic flow caused by incidents under high traffic volume conditions. The model and algorithm are designed to work with data obtainable from highway sensors/detectors and RSU. With minor changes to the code, data from probe vehicles and crowd-sources can be used as well.The algorithm includes a number of criteria that narrow the choice of likely causes of the rapid drop in speed both spatially and temporally. The results achieved suggest high success rate in minimizing false alarms and improving detection rate under applicable traffic conditions.A Matlab-based test bed was developed for testing models, and simulated incidents were used for conducting additional tests on the predictive capability of the algorithm/model. The results are in line with those obtained from archived actual incident data.It is expected that the use of the algorithm and its constituent model will contribute to reduced delay, and improved safety (e.g. reduction of secondary collisions).
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 | 0.007 | 0.023 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.005 | 0.001 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".