Identification of Road Network Intersection Types from Vehicle Telemetry Data Using a Convolutional Neural Network
Bibliographic record
Abstract
GPS trajectories collected from automotive telematics for insurance purposes go beyond being a collection of points on the map. They are in fact a powerful data source that we can use to extract map and road network properties. While the location of road junctions is readily available, the information about the traffic control element regulating the intersection is typically unknown. However, this information would be helpful, e.g., for contextualizing a driver’s behavior. Our focus is to use a map-matched GPS OBD-dongle dataset provided by a Canadian insurance company to classify intersections into three classes according to the type of traffic control element present: traffic light, stop sign, or no sign. We design a convolutional neural network (CNN) for classifying intersections. The network takes as entries, for a defined number of trips, the speed and the acceleration profiles over each segment of one meter on a window around the intersection. Our method outperforms two other competing approaches, achieving 99% overall accuracy. Furthermore, our CNN model can infer the three classes even with as few as 25 trips.
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) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 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 | 0.001 |
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".