Development of Game-Like System Using Active Behavior Input for Wakefulness-Keeping Support in Driving
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the challenge of developing a drowsy driving prevention system that is both effective and acceptable to drivers. Existing systems often suffer from false alarms that annoy users or fail to actively promote wakefulness. The authors propose a Wakefulness-Keeping Support System (WKSS) designed to satisfy three criteria: precise drowsiness detection, warnings that minimize annoyance from false alarms, and mechanisms that encourage active behavior to maintain alertness. The system integrates a Heart Rate Variability (HRV)-based Drowsiness Detection System (DDS) with an Active Game System (AGS). When drowsiness is detected, the AGS prompts the driver to engage in specific active behaviors—either head gestures or speech—to "attack" a virtual lion, thereby stimulating the autonomic nervous system and maintaining wakefulness without the negative perception associated with traditional alarms. The study employed a driving simulator experiment with 32 participants divided into four groups: AGS-Body (head gesture input), AGS-Voice (speech input), Passive Alarm (standard beep), and Non-alarm (control). Participants drove on a monotonous night-time course for 50 minutes after a drowsiness-inducing period. The DDS utilized a wearable sensor to monitor RR intervals, applying Multivariate Statistical Process Control (MSPC) to detect anomalies indicative of drowsiness. The AGS used Microsoft Kinect v2 to recognize inputs. Measurements included subjective drowsiness via the Karolinska Sleepiness Scale (KSS), physiological metrics (normalized LF and HF power, LF/HF ratio), and driving safety indicators such as Steering Entropy (SE) and Standard Deviation of Lane Position (SDLP). Results indicated no significant difference in subjective drowsiness (KSS) across the four groups for the entire cohort. However, for participants who were not initially drowsy, the AGS-Body group showed significantly lower KSS scores at the end of the drive compared to the Non-alarm group, suggesting a wakefulness-keeping effect. Physiological data revealed that the AGS-Body group maintained higher High Frequency (HF) power, indicative of parasympathetic activity, compared to the AGS-Voice group. Crucially, driving safety metrics (SE and SDLP) showed no significant differences between groups, indicating that the active behaviors required by the AGS did not impair driving performance. Subjective evaluations confirmed that participants found the AGS enjoyable and less annoying than passive alarms, even when false alarms occurred. The study concludes that the WKSS, particularly the AGS-Body variant, effectively supports driver wakefulness without compromising driving safety or user acceptance. By replacing intrusive alarms with an engaging game-like interaction, the system mitigates the annoyance of false positives while promoting active wakefulness maintenance. The findings suggest that manual responses (head gestures) may be more suitable for wakefulness-keeping during driving than verbal responses, likely due to differences in cognitive resource utilization. This approach offers a viable path toward more user-friendly drowsy driving prevention systems that contribute to reducing traffic accidents.
Key finding
The proposed wakefulness-keeping support system using active game inputs was found to be less annoying and more enjoyable for drivers compared to traditional passive alarms, while maintaining comparable levels of subjective wakefulness and driving safety.
Methodology
simulator
Sample size: 32
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. Discovered via author_sweep_intake on 2026-05-28.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | author_sweep | — | — | 2 | 2026-05-28 |
| archive | success | unpaywall | — | — | 2 | 2026-06-04 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-04 |
| chunk | success | chunk | — | — | 1 | 2026-06-04 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-04 |
| enrich | success | — | — | — | 1 | 2026-05-28 |
| promote | success | — | — | — | 1 | 2026-06-04 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- drowsiness detection algorithms
- drowsiness
- workload measurement
- vigilance
- sleep deprivation
- in vehicle coaching
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: tool software
- Theoretical Contribution: computational model