Research on driver fatigue detection via feature fusion
Bibliographic record
Abstract
Existing train driver fatigue detection methods typically rely on the measurement of drivers’ biological signals. However, these methods often utilize a single biosignal and fail to consider the potential interconnections between different biosignals. Moreover, most biosignal detection methods focus primarily on extracting features from individual biosignals while neglecting the intrinsic relationship between the signals themselves and fatigue. To address these limitations, we propose an integrated approach that combines photoplethysmographic (PPG) and electrodermal activity (EDA) signals to enhance the accuracy of driver fatigue detection. Specifically, we employ a convolutional neural network (CNN) to fuse these two signals at the data layer, thereby achieving multimodal fusion for fatigue detection. Our results demonstrate that when the two signals, captured over a 5 min time window, are fused in parallel at the data layer and fed into the CNN model, the detection accuracy reaches 95.83%. These findings suggest that the integration of PPG and EDA signals through CNN-based multimodal fusion can significantly improve the reliability of fatigue detection. The outcomes of this study have important implications for the development of robust fatigue detection methods for train drivers, which could ultimately enhance rail traffic safety.
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 | 0.001 | 0.003 |
| 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 | 0.001 | 0.002 |
| 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".