Validation of Vigilance Decline Capability in A Simulated Test Environment: A Preliminary Step Towards Neuroadaptive Control
DOI: 10.54941/ahfe1004737
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study addresses the critical need for robust data collection methods to develop neuroadaptive systems capable of detecting vigilance decline in safety-sensitive tasks like driving. Sustained attention is essential for operational efficiency and safety, yet prolonged monotonous tasks lead to fatigue, slower reaction times, and increased error rates. To create effective AI-driven neuroadaptive monitoring tools, researchers require validated environments that reliably induce hypovigilance. This paper presents a preliminary validation of a simulated driving testbed designed to trigger vigilance decline, serving as a foundational step toward building real-time detection models. The experimental design involved 32 participants (aged 18–35) who completed a 60-minute simulated driving task in a monotonous environment using the BeamNG.tech simulator. The scenario featured low traffic, sunny weather, and alternating green and desert biomes to minimize external stimulation. Participants performed a secondary visual attention task involving billboard detection and self-reported moments of vigilance loss by pressing a steering wheel button. The study employed a multimodal measurement approach, collecting subjective data via the Karolinska Sleepiness Scale (KSS) and Stanford Sleepiness Scale (SSS), behavioral data via the Psychomotor Vigilance Task (PVT), and neurophysiological data using EEG, ECG, EDA, eye tracking, and facial analysis. However, this report focuses exclusively on validating the testbed’s efficacy using KSS, SSS, and PVT metrics, comparing baseline measurements taken before the drive to post-drive assessments. The results confirmed that the simulated environment successfully induced significant vigilance decline. Subjective sleepiness scores increased markedly: mean KSS scores rose from 4.3 (“rather alert”) to 6.1 (“some signs of sleepiness”), and SSS scores increased from 2.7 (“able to concentrate”) to 4.1 (“somewhat foggy”), both with large effect sizes (Cohen’s d = 0.98 and 1.15, respectively). Behavioral performance also deteriorated, with PVT mean reaction times increasing significantly from 258 ms to 279 ms (p < 0.0001) and response speed decreasing. Participants reported their first instance of vigilance loss within an average of 18 minutes, with over 70% of these initial lapses occurring during the monotonous desert biome segment. The study concludes that a one-hour monotonous drive in a low-cost simulator is sufficient to induce measurable vigilance decline, validating the testbed for future research. This finding is significant because it establishes a reliable, ecologically valid method for generating the high-quality multimodal data necessary to train neuroadaptive prediction models. By confirming the testbed’s ability to trigger hypovigilance, the research paves the way for developing non-invasive, real-time monitoring systems that can detect cognitive fatigue and implement countermeasures to enhance safety in aviation, driving, and other critical operational domains.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-08-09 |
| archive | success | canonical_url | — | — | 1 | 2026-08-09 |
| extract | success | cached | — | — | 3 | 2026-08-10 |
| clean | success | clean | — | — | 1 | 2026-08-09 |
| chunk | success | chunk | — | — | 1 | 2026-08-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-08-09 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 2 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 11 | 2026-08-11 |
| verify | success | — | — | — | 2 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- vigilance
- drowsiness detection algorithms
- drowsiness
- workload measurement
- sustained attention vigilance
- neuro workload indices
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: physiological data
- Methodological Resource: validation psychometrics, tool software