Advanced Traffic Signal Control Using Bluetooth Detectors
Bibliographic record
Abstract
Traditionally signal timing plans are developed for expected traffic demands at an intersection. This approach generally offers the best operation for typical conditions. However, when variation in the traffic demand occurs, the signal timing plan developed for typical conditions may not be adequate resulting in significant congestion and delay. There have been many techniques developed to address these variations and they fall into one of two categories: (1) if the variations follow a consistent temporal pattern, then a set of fixed-time signal timing plans can be developed, each for a specific time of the day; (2) if the variations cannot be predicted a priori, then a system that measures traffic demands and alters signal timings in real-time is desired. This research focuses on improving the latter approach with a novel application of Bluetooth detector data. \nConventional traffic responsive plan selection (TRPS) systems rely extensively on traffic sensors (typically loop detectors or equivalent) to operate, which are costly to install and maintain, and provide information about traffic only at the points which they are installed. This thesis explores the use of Bluetooth detectors as an alternative data source for TRPS due to their ease of installation and capability to provide information over an area rather than at a single point. \nThis research consists of simulated and field traffic data associated with Bluetooth detectors. The field and simulated traffic data were from a section of Hespeler Road in Cambridge Ontario, bounded by Ontario Highway 401 to the north and Highway 8 to the south. The study corridor is approximately 5.0 kilometres long, and consists of 14 signalized intersections. \nIn order to determine the potential of Bluetooth detectors as a data source, several measures of performance were considered for use in a Bluetooth-based system. The viability of each one was assessed in microsimulation experiments, and it was found that Bluetooth travel time was the most accurate at identifying true traffic conditions. \nOn the basis of the simulation results a field pilot study was designed. Bluetooth detectors and conventional traffic detectors were installed at study intersections along the Hespeler Road corridor to measure real traffic conditions. From these measurements an algorithm was developed to determine when traffic conditions varied from the expected conditions. \nThe final stage of the research evaluated the proposed algorithm using a controlled simulation environment with known atypical traffic patterns. It was found that the algorithm was capable of identifying the atypical conditions that were simulated based on field conditions. \nThe key findings of this research are that (1) Bluetooth detectors are able to provide measured travel times from individual vehicles with sufficient accuracy, and with sufficient sample sizes, that the aggregated travel time information can be used to identify the traffic conditions at a signalized intersections; and (2) these measurements can be used instead of data from conventional traffic detectors, to determine when to switch from time of day fixed time traffic signal control to TRPS control.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".