Travel Time Estimation in an Urban Network Using Sparse Probe Vehicle Data and Historical Travel Time Relationships
Bibliographic record
Abstract
This research proposes an approach to provide travel time estimates on a network using data from part of the network only. This applies to the problem of having a small sample of probes that do not cover an entire network. The method makes use of sparse probe vehicle data along with travel time correlation between neighbor links. By developing travel time relationships between neighbor links, a relatively small sample of probes can be used to estimate travel times on part of the network and then the developed relationships can be used to extend travel time estimation to the whole network. In practice, to apply this approach, historical travel time data need to be first collected for the entire network to develop the required travel time relationships. To investigate and test the method, a microsimulation model for downtown Vancouver was developed using VISSIM. The model was updated and modified according to recent network changes then turned into a dynamic-based model. Travel time data were generated using five demand levels and two hours of simulation. Travel times were obtained from 25 segments in the same direction. Correlation matrices between all travel time segments were developed for different aggregation intervals. The correlation was found to increase when the aggregation period increases. As well, high travel time correlation was found for consecutive links and nearby parallel links. A correlation threshold was selected and used to define a set of “neighbors” for each link. Statistical models were then developed to relate link travel time with the neighbors’ travel times. The models were validated using two simulation runs for two different demand levels. Error measurements indicated a good fit of the developed models. Simple weighting schemes were used to fuse estimates of different models to enhance the travel time estimation. The Mean Absolute Percentage Error (MAPE) of travel time estimates ranged between 1.91% and 9.48% for the applied weighting schemes. The method should prove useful to estimate travel time on links that does not have vehicle probes based on historical travel time correlations.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".