A Modified Latent Dirichlet Allocation Topic Approach for Driving Style Exploration Using Large-Scale Ride-Hailing GPS Data
Bibliographic record
Abstract
Driving style identification is of vital importance for intelligent driving system design and urban traffic management. This study aims to identify and analyze driving styles using large‐scale ride‐hailing GPS data taking different time periods, traffic, and weather conditions into account. The large‐scale GPS data are collected and preprocessed, and then, the k‐means clustering is implemented to acquire driving behavior. The modified latent Dirichlet allocation topic approach is applied to extract the driving states as the latent variables behind driving behaviors and finally recognize driving styles. The results show that driving styles are composed of five driving states with different probability combinations. Different driving styles in different situations are further analyzed and compared. When considering the impact of peak periods on the driving style, it indicates that styles tend to be conservative in the morning peak, free and dispersed in the evening peak, and diverse in the off‐peak hours. While comparing styles regarding the influence of workdays, drivers act more cautiously and conservatively on weekdays but freer on weekends without the pressure of peak hours. The weather factor is also explored and rainy days are verified to be the resistance of driving so that most drivers become cautious and conservative. Finally, two aberrant driving styles are discovered and countermeasures are suggested to improve traffic safety.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| 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".