Integrated Multimodal System for Real-Time Driver Fatigue Detection and Cognitive Load Assessment
Bibliographic record
Abstract
As human drivers' roles diminish with higher levels of driving automation (SAE L2-L4), understanding driver engagement and fatigue is crucial for improving safety. We developed an integrated hardware and software system to analyze driver interaction with automated vehicles, with a particular focus on cognitive load and fatigue assessment. The system includes three submodules; namely the Driver Behavior Measurement (DBM), Vehicle Dynamics Measurement (VDM), and the Driver Physiological Measurement (DPM). The DBM module uses electro-optical (EO) and infrared (IR) camera to track a number of facial features such as eye aspect ratio (EAR), mouth aspect ratio (MAR), pupil circularity (PUC), and mouth to eye aspect ratio (MOE). Although determining these metrics from images of the driver’s face in conditions such as low light or with sunglasses is challenging, the paper showed that fusion of EO and IR image analysis produces robust performance. The VDM module utilizes an Inertial Measurement Unit (IMU) to provide vehicular motion data such as speed, acceleration, braking and yaw rate to aid detection of fatigue-related irregularities. A wearable heart rate monitor was used in the DPM module to track driver heart rate as an indicator of stress and fatigue. Data from these modules is fused and processed using a previously published CNN-LSTM model, achieving 90.1% accuracy in detecting fatigue in preliminary tests performed with one driver. The test results show that the system is robust, scalable, and suitable for large-scale studies on driver engagement with highly automated vehicles.
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 | 0.000 |
| Bibliometrics | 0.001 | 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 | 0.000 |
| Insufficient payload (model declined to judge) | 0.010 | 0.004 |
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".