Driver State Classification: Identifying High Cognitive Load and Drowsiness Through Driver Performance and Physiology
Bibliographic record
Abstract
This study investigates the effect of high cognitive load and drowsiness on driving performance (speed, lane position, steering wheel movement) and driver physiology (cardiac activity, skin conductance) and uses these measures in classifying high cognitive load, alert, and drowsy driver states. A within subject driving simulator experiment was conducted with twenty-seven participants (14 females, mean age: 36.7). High cognitive load was induced via the n-back task (1-back, 2-back), a commonly used auditory-verbal recall task. Drowsiness was induced by monotonous driving (i.e., extended periods of low cognitive load), and was rated by trained observers. Mixed linear models were used to analyze the differences between the driver states, while machine learning models were used for multi-class classification. Compared to alert driving with no additional cognitive load, high cognitive load was associated with greater physiological arousal and speed variation and reduced speed and standard deviation of lane position (SDLP). Drowsiness was associated with lower physiological arousal and increased speed, SDLP, and standard deviation of steering wheel angle. Tree-based ensemble models (i.e., random forest, XGBoost) performed the best in classification. With simple features such as the average and SD, high cognitive load, drowsiness, and alert states were classified with up to 76% average accuracy. These measures could differentiate high cognitive load states with around 85% AUC and drowsiness with around 79% AUC within one model. These findings can help in the selection of metrics for driver monitoring systems that can differentiate driver cognitive overload and underload and inform the design of real-time intervention systems.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".