The Importance of Validating Sleep Behavior Models for Fatigue Management Software in Military Aviation
Bibliographic record
Abstract
INTRODUCTION: The propensity for air mobility missions to exhaust aircrews is strongly dependent on operational tempo. Most flying is performed during periods of low to moderate operational tempo, but a major flight safety risk can emerge when operational tempo becomes very high. This risk can be managed by software tools that contain fatigue and sleep behavior modeling, but optimization/validation of the model using the specific target population is required to ensure that the modeled predictions are accurate. The goal of the study was to validate the sleep behavior model settings for a fatigue modeling tool that is used within the RCAF, the Fatigue Avoidance Scheduling Tool, taking into account the organizational requirements for pre- and postflight routines, especially within the Air Mobility force. MATERIALS AND METHODS: Four Royal Canadian Air Force Air Mobility Squadrons from Canadian Forces Base Trenton took part in this trial over a 3-month period (May 3 to August 21, 2016). All 22 missions of the trial included long-range transmeridian flights. All members of the participating aircrew wore wrist actigraphs to measure their sleep. We compared cognitive effectiveness modeling scenarios (preharmonization) based on the SAFTE-FAST sleep behavior model with its default settings against cognitive effectiveness modeling scenarios based on actigraphically-measured sleep. The measured sleep was then harmonized against the predicted sleep to optimize accuracy of the sleep behavior algorithm. During the harmonization process, the "Autosleep" prediction settings were optimized to match the actigraphically-measured sleep timings. RESULTS: Prior to the harmonization effort, the sleep behavior algorithm overpredicted the sleep obtained by CAF Aircrews. The most significant adjustment to the sleep behavior model was the increase in commute time to account for briefing, flight planning, debriefing, and postflight activities. Following harmonization, the sleep behavior model provided nearly perfect estimates of overall fatigue risk against missions modeled with actigraphically-measured sleep. For both measured and predicted sleep, most of the time in flight was in a low-fatigue, high-cognitive effectiveness state (90%-95% cognitive effectiveness). CONCLUSIONS: Current Fatigue Risk Management Systems require accurate fatigue and sleep behavior modeling, which can only be achieved by studying specific target populations to determine their culture of work/rest routines, and optimizing sleep behavior model settings accordingly.
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 | 0.007 | 0.031 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".