An Efficient Driver Drowsiness Detection Approach Using Various Combinations of Physiological Signals
Bibliographic record
Abstract
Drowsiness, though often perceived as a minor issue, poses a significant risk to road safety and work in high-stakes environments. Each year, it leads to severe accidents, resulting in substantial human and economic losses. To address this risk, detection systems have been developed, relying either on behavioral and environmental analysis (non-intrusive approaches) or physiological signal acquisition (intrusive approaches). However, existing systems face limitations in terms of accuracy, speed, and adaptability to individual variations. In this context, this study aims to enhance drowsiness detection by leveraging physiological signals for earlier and more reliable identification of driver alertness levels. The specific objectives are: (1) to identify the most relevant physiological indicators of drowsiness, (2) to determine the optimal sensor configuration for improved system accuracy, and (3) to compare different signal transformation techniques, particularly scalograms and spectrograms, to assess their effectiveness within an optimized detection pipeline. To achieve these objectives, the DROZY dataset — the only available dataset combining simultaneous recordings of drivers’ physiological signals and behavioral data — was used for model training and evaluation. The methodological approach integrates advanced signal preprocessing, optimized feature extraction and selection, and machine learning models, including pre-trained neural networks (VGG-16 and ResNet-50) and feature importance selection techniques, namely the Light Gradient Boosting Machine (LGBM). Experimental results demonstrate a maximum accuracy of 93.75%, validating the effectiveness of the proposed pipeline. By fully leveraging physiological signals and optimizing their processing, this study contributes to advancing drowsiness detection systems, ultimately enhancing driver safety in real-world conditions.
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 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".