Traffic Management System Based on Deep Learning Techniques at Signalized Intersection: The Case of Antalya
Bibliographic record
Abstract
This study was conducted to ensure traffic continuity at an adaptive signalized intersection by developing a SUMO‐based digital twin of the Heybe Intersection in Antalya, using real traffic data obtained from the Antalya Traffic Control Center (covering 165 days of observations). To address potential sensor failure scenarios, a solution integrating traffic forecasting and reinforcement learning was developed. After applying data cleaning techniques, multiple deep learning models were trained to forecast traffic volumes, and their outputs were used to generate an origin‐destination (O/D) matrix that served as input to a Deep Q‐Learning (DQL) control model. Three scenarios were evaluated in the simulation: (i) baseline adaptive signal control under normal operating conditions, (ii) the existing system under sensor failure reverting to a fixed‐time plan, and (iii) the proposed DQL‐based intersection management. Results demonstrated that, under sensor failure conditions, the DQL‐based system achieved substantial improvements compared to the fixed‐time baseline: the average delay was reduced by 61.3%, the average speed increased by 134.6%, and the level of service improved from E to B. These findings highlight the potential of integrating forecasting models with DQL to enhance the resilience of smart intersections against sensor malfunctions.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| 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 | 0.000 |
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".