Real-Time Prediction of Arterial Roadway Travel Times Using Data Collected by Bluetooth Detectors
Bibliographic record
Abstract
Bluetooth detectors are gaining in popularity as a cost-effective technology for acquiring travel time data. The sensors, which identify and record the unique media access control address of Bluetooth-enabled devices, can measure travel time when a device passes through the detection zone of two consecutive Bluetooth detectors. As with other automatic vehicle identification technologies (e.g., toll tags, automatic license plate recognition systems), there is a time lag because the travel time cannot be acquired until the vehicle has passed the downstream detector location. The increasing desire for accurate and timely traveler information and the desire for proactive traffic control present a need for accurate prediction of near-future travel times along roadway corridors. A significant body of literature has focused on this problem for freeways, but little effort has been directed toward signalized arterials. This paper presents a data-driven model for predicting near-future travel times on signalized arterials in real time by using data acquired from Bluetooth detectors. The model uses the k nearest neighbor pattern recognition technique to identify historical data from which an understanding of the near-future traffic patterns can be extracted. Unlike previous efforts, an objective approach was used to determine the variables to include in the k nearest neighbor feature vector and the optimal model parameters. The calibrated model was evaluated through application to a set of field data obtained from Bluetooth detectors deployed on a signalized arterial. The model provides performance improvements of approximately 20% over a benchmark model.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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 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".