Data-Driven Prediction System of Dynamic People-Flow in Large Urban Network Using Cellular Probe Data
Bibliographic record
Abstract
Cellular probe data, which is collected by cellular network operators, has emerged as a critical data source for human-trace inference in large-scale urban areas. However, because cellular probe data of individual mobile phone users is temporally and spatially sparse (unlike GPS data), few studies predicted people-flow using cellular probe data in real-time. In addition, it is hard to validate the prediction method at a large scale. This paper proposed a data-driven method for dynamic people-flow prediction, which contains four models. The first model is a cellular probe data preprocessing module, which removes the inaccurate and duplicated records of cellular data. The second module is a grid-based data transformation and data integration module, which is proposed to integrate multiple data sources, including transportation network data, point-of-interest data, and people movement inferred from real-time cellular probe data. The third module is a trip-chain based human-daily-trajectory generation module, which provides the base dataset for data-driven model validation. The fourth module is for dynamic people-flow prediction, which is developed based on an online inferring machine-learning model (random forest). The feasibility of dynamic people-flow prediction using real-time cellular probe data is investigated. The experimental result shows that the proposed people-flow prediction system could provide prediction precision of 76.8% and 70% for outbound and inbound people, respectively. This is much higher than the single-feature model, which provides prediction precision around 50%.
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 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".