A methodology for scheduling within‐day roadway work zones using deep neural networks and active learning
Bibliographic record
Abstract
City infrastructure agencies routinely implement road projects that address various elements of urban infrastructure. The majority of these projects are short-term in nature (e.g., utility repair), as they are completed in a few hours within 8:00 a.m. to 5:00 p.m. of a workday. The implementation of these projects during working hours, in spite of the inconvenience imposed on road users, helps the agency avoid extra labor costs associated with nonregular working hours. Careful scheduling of these projects can prevent unduly increased travel delays (road users’ interest) while keeping project costs low (the agency's interest). This study presents a bi-level framework for scheduling short-term urban road projects that analyzes the implicit tradeoffs between the two stakeholders’ interests. The upper-level model establishes the optimal schedule considering the project characteristics, such as cost and duration. The lower-level model captures the dynamic user equilibrium conditions that yield the road users’ path and departure time choices. The bi-level model is a mixed-integer program with nonlinear constraints. Recognizing the relatively low efficiency of traditional solution methods, this paper proposes a deep-neural-network-ensemble-assisted active learning (DN2EA2L) algorithm and adopts a fixed-point algorithm for solving the bi-level model. The numerical experiment uses the Sioux Falls network to demonstrate the efficiency of the DN2EA2L, compared to conventional metaheuristic methods. It is shown that travel time increases due to the project implementation during the peak hours can outweigh the agency's saving in wage costs. Further, it is shown that a significant reduction in the road users’ value of time enables the agency to schedule more projects during regular working hours.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 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".