Fatigue Driving Detection Based on Very Deep Convolutional Network with Continuous Learning Strategy
Bibliographic record
Abstract
Fatigue driving is an important factor leading to traffic accidents so driver fatigue detection is crucial for improving road safety. The prevailing learning-based fatigue driving detection methods have the defect of lacking continuous learning ability resulting in low accuracy in unlearned situations. In this paper, we propose a very deep convolutional network with a continuous learning (CL-VDCN) strategy to achieve fatigue driving detection. To enhance the network performance in unlearned situations, a new sampling strategy, a replay buffer-based weight updating strategy, and a dynamic learning rate are proposed to enable the convolutional neural network with continuous learning ability. Experiments on the YAWDD dataset show that the proposed model outperforms comparison methods, achieving a classification accuracy of 92.82% in the test. Additionally, the model maintains high detection accuracy and robustness under different lighting conditions, with a classification accuracy of 87.08% across various brightness levels. The experimental results demonstrate the CL-VDCN model’s superior performance in terms of detection accuracy, robustness, and continuous learning capabilities.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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".