Development and Testing of a Real-Time WiFi-Bluetooth System for Pedestrian Network Monitoring, Classification, and Data Extrapolation
Bibliographic record
Abstract
A real-time pedestrian monitoring system provides information about traffic flow, speeds, travel times, and time spent in areas or transportation facilities of interest. This is useful in travel information systems and crowd management strategies, as well as in planning and emergencies in public spaces, such as airports, parks, malls, and university campuses. While there are technologies that can obtain count data for non-motorized transportation at specific locations, most technologies cannot provide origin-destination information, trip paths, travel times, or time spent. To overcome these shortcomings, some studies have explored the use of Bluetooth (BT) sensors to capture the unique media access control (MAC) addresses of mobile devices carried by pedestrians. However, this collection method may suffer from low-detection rates. As an alternative, collecting MAC data from WiFi signals has emerged. The objective of this paper is three-fold: 1) develop and evaluate the performance of an integrated WiFi-BT system to monitor pedestrian-cyclists activity traffic; 2) develop and validate a classification method for differentiating pedestrians from bicycles; and 3) propose a simple extrapolation method that combines counts and MAC data. Among other results, relatively high detection rates were obtained for the developed WiFi system in comparison with BT sensors. In addition, high correlation between estimated and ground truth speeds and low classification errors are observed. Finally, the extrapolated WiFi counts and ground truth counts were found to be highly correlated. These results demonstrate the feasibility of the proposed system and methods to estimate travel times (speeds), to classify bicycle-pedestrian WiFi signals, and to extrapolate pedestrian MAC counts.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".