Method for Detection and Classification of Turning Movements in Intersections Using Bluetooth Low-Energy Signals
Bibliographic record
Abstract
The study purpose is the development of a method for detection and classification of turning movements in intersections using Bluetooth Low-Energy signals emitted from turning vehicles. The method was developed to be applicable for areas in which the distances between the adjacent intersections are short. It utilizes the time profiles of the received signal strength indicator (RSSI) for signals emitted by transmitters mounted on moving vehicles. The signals are collected by an array of signal scanners carefully located on the intersection approaches and corners. Turning movements are classified by comparing signature points of the RSSI–time profiles and their occurrence moments. Effort was made to examine the accuracy and functionality of the method in six field experiments covering line-of-sight and non-line-of-sight signal transmission paths, different speeds, and motion-stop situations. The overall accuracy of the method in the experiments was 94.2%, demonstrating its functionality in different situations. Nevertheless, the results indicated that there are factors affecting the performance of the method. The presence of obstacles in the transmission paths of signals and increasing the vehicle speed reduced the accuracy, but intermittent motion at low speeds did not have negative impacts on the outcomes. It was found that a certain condition is required to achieve satisfactory accuracy in the determination of turning movements by the proposed method. The installation location of the signal scanners, road geometry, and vehicle speeds should provide a signal detection distance of less than 10 m on the intersection approaches when vehicles pass in front of the scanners. This is to ensure that at those moments, there are signals transmitted from the range with distinct RSSI values and appropriate for the identification of the turning movements.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".