Research and design of illegal driving behavior detection model based on deep learning
Bibliographic record
Abstract
The rapid development of transportation systems and the growing number of vehicles on roads have significantly increased traffic-related risks, especially due to illegal driving behaviors such as speeding, distracted driving, and unauthorized lane changes. These behaviors not only disrupt traffic flow but also contribute to severe accidents, property damage, and fatalities. Traditional traffic monitoring techniques, such as radar-based systems and manual surveillance, are inadequate to address these complex challenges due to their dependency on predefined rules and limited scalability. This research introduces a robust illegal driving behavior detection model built on the principles of deep learning. By combining convolutional neural networks (CNNs) for spatial feature extraction and long short-term memory (LSTM) networks for temporal analysis, the proposed model captures complex driving patterns from traffic video data. A large-scale dataset featuring diverse driving scenarios and behaviors was used to train and validate the model, achieving a remarkable accuracy of 95%. The study not only demonstrates the potential of deep learning in traffic law enforcement but also highlights its advantages in scalability, automation, and real-time decision-making. This paper provides valuable insights for researchers and policymakers aiming to implement intelligent traffic management systems.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| 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".