A Novel Approach to Detect Driver Drowsiness Using Transfer Learning and Hybrid Features
Bibliographic record
Abstract
Abstract In worldwide, drowsiness is one of the prevalent reasons to cause accident. Statistics show that fatigued drivers are a major factor in causing many accidents. According to studies by the National Sleep Foundation, 20% of drivers feel sleepy to some extent while driving. Deep learning-based methods are the most recent ones that researchers have used to analyse videos and detect tiredness. Convolution neural networks utilizes extracted face features like yawning, eye flashing and head movements to detect exhaustion and sleepiness. Incorporating modified InceptionV3, VGG16, ResNet50, DenseNet201 and MobileNetV2 architecture over Driver Drowsiness Dataset to propose an ensemble deep learning model. Feature extraction was done using these models. The global max pooling layer is used to improve spatial robustness and dropout approach was included in these models to avoid overfitting on training data. Finally, Sigmoid classifier is used to classify positive (drowsy) or a negative (nondrowsy) result. These models outputs are given to a proposed ensemble algorithm. This model outperforms the alternative strategy with respect to performance metrics. The suggested ensemble framework performs better in identifying driver drowsiness than existing state-of-the-art techniques on basis of accuracy.
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 | 0.001 |
| 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 | 0.001 |
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".