0635 Vigilance Observations - Learning from Nighttime Driving Behaviours
Bibliographic record
Abstract
Changes in vigilance are characteristic features of sleepless or sleep-deprived individuals. To standardize vigilance assessments, we reviewed videos of nighttime drivers with a structured rating system and investigated ratings of student observers. Nighttime driving videos of 60 adult volunteers recorded between 2 and 4 AM were provided by the Institute for Sleep-Wake-Research (ISWF, Vienna) and the Austrian Automobile Club (OEAMTC). Two 4.5-minute video recordings of 14 participants, after 30 and 90 minutes of driving, were analyzed. (A) Six observers rated participants using the Karolinska Sleepiness Scale (KSS); ratings were compared with drivers’ self-ratings. (B) Open-ended and pictogram-based behaviours were annotated (O-a; P-a) and separated into (i) task-oriented (i.e. driving); (ii) non-task oriented (i.e. non-driving); and (iii) posture-oriented (e.g. stretching) behaviours. (C) Timing of (earlier versus later) videos were predicted. (D) Four videos were reviewed with a Delphi consensus process, determining to what extent pictograms could support analyses. (A) KSS participant and observer ratings for the earlier (means, 3.0 vs. 4.25) and later recordings (mean, 6.5 vs. 6.1) were comparable, but not significant. (B) O-a and P-a revealed changes between the three behaviour categories as night progressed: task-oriented behaviours decreased; non-task oriented behaviours increased; and posture-oriented behaviours did not change. (C) However, observers failed to predict the timing of the two videos. (D) Discussions identified missing characteristic pictograms (e.g. self-stimulation) to inform future design. Although the KSS ratings corresponded and a change in task versus non-task oriented behaviours was detected, observers failed to correctly predict the timing of the videos. Causes of this discrepancy were explored and now self-stimulating behaviours and fluency of movements are being investigated. BC Children’s Hospital Research Institute and Foundation.
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) | 0.005 | 0.003 |
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; both teacher heads agree on what is shown here.
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".