Bibliographic record
Abstract
Trip demand prediction is an integral part of intelligent transportation systems.It is concerned with estimating future trip demand based on past observations.An accurate forecasting model can help with the efficient reallocation of vehicle resources to better meet travel demands, which can benefit many transportation services.The prediction process is a challenging task due to the complex and dynamic spatio-temporal correlations of trip data.Recent advances in deep learning-based methods have inspired researchers to apply them to traffic forecasting tasks.Some of these methods use Convolution Neural Networks to model the spatio-temporal dependencies in trip data by representing trip data as 2D grids.Other methods utilize the natural graph structure of transportation networks and apply Graph Convolution Networks to model the propagation effects between graph nodes.However, these techniques impose certain spatial constraints on the data that do not represent real-world conditions or do not account for a changing and expanding transportation network structure.To address these limitations, we develop a method, entitled CityNet, that learns the demographic, socio-economic and land-use features of city regions to perform trip demand prediction.Specifically, our model first predicts the number of incoming and outgoing trips to all city regions and then utilizes these values to estimate the trip demand between region pairs.The experimental results show that our model achieves a minimum of 56% improvement in error rate compared to several time-series forecasting techniques and neural network methods, as well as a 15% improvement compared to two variants of our proposed model.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".