Generation of Mobility Patterns for Private Vehicles using Multi-headed Sequence Generative Adversarial Networks
Bibliographic record
Abstract
Effective transport planning strategies seek to improve the urban transportation systems by addressing traffic congestion problems, identifying emission hotspots, incentivizing public transit to discourage private vehicle usage and adoption of electric vehicles. Strategy planners and policy makers are increasingly relying on new emerging methods such as full population scaled agent-based macroscopic transport simulation models to study the interaction between mobility patterns of the commuters and their impact on the transportation systems. This is because the behavioural changes in daily travelling patterns of commuters play a major role in predicting the future travel demand for the development of a robust and reliable urban transportation system. Traditionally, household travel surveys have been conducted periodically to understand the current travel behaviour and plan for the future development. However, it is impossible for traditional surveys to sample a large majority of the daily commuter trips, particularly for private vehicles and therefore in its raw form, it cannot be used in a full sample agent-based simulation. In this paper, we use the household travel survey data from Singapore to generate the synthetic mobility patterns for the complete population of private vehicle users that is capable of preserving the data privacy whilst retaining the statistical features of the original data. This is accomplished by employing a multi-headed gated recurrent unit (GRU) based generative model that enables the generation of synthetic mobility patterns that provide a suitable representation of the real mobility patterns of the larger set of commuters. We define and utilize two accuracy evaluation metrics that quantify the quality of the generated synthetic mobility trips. Our experimental results have shown that we are able to capture 90% of the correctness of the original mobility dataset of private vehicle users.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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 teacher head, 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".