Intelligent Traffic Light Optimization System Using Convolutional Neural Networks for Historic City Centers in Complex Scenarios
Bibliographic record
Abstract
Historic urban centers present a paradigmatic challenge in modern traffic management, characterized by narrow streets originally conceived for carriage and pedestrian circulation.This infrastructural incompatibility generates critical congestion, exacerbated in developing countries where fixed-time traffic signal systems predominate, lacking adaptive capacity and generating substantial inefficiencies of temporal, energy, and fuel resources.We developed a convolutional neural network model based on a customized You Only Look Once version 8 architecture for vehicle detection and classification.The model implements advanced temporal filtering to reduce false positives, vehicle tracking for unique counting, and a comprehensive 13stage traffic signal optimization algorithm that correlates detected vehicular density with cycle times.The system maintains operational robustness under adverse conditions, including precipitation, cloudiness, shadows cast by colonial mansions, vehicular occlusion phenomena, and luminous glare.Implementation was evaluated through video recordings from the Historic Center of Ayacucho, using strategically positioned cameras to determine vehicular density at various time periods.The model, trained for 126 epochs with Early Stopping on 3,000 images, achieves 88.7% precision, recall of 0.832/0.834(validation/evaluation), establishing a robust solution for urban heritage contexts.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| 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".