Estimation of mental workload during automobile driving based on eye-movement measurement with a visible light camera
DOI: 10.1299/transjsme.19-00326
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 need for objective, real-time estimation of mental workload (MWL) during automobile driving to enhance safety, particularly in the context of distracted driving and the transition to automated driving systems. While subjective assessments and physiological signals like heart rate or EEG are common, they are either impractical for continuous use or require intrusive equipment. The authors propose using eye-movement parameters measured via a non-intrusive, low-cost visible light camera as a viable alternative to traditional infrared eye-tracking systems. The experimental design involved twelve participants (six males, six females) performing a primary driving task on a simulator while simultaneously engaging in a secondary N-back task to manipulate cognitive load. The N-back task had five levels: none, 0-back, 1-back, 2-back, and 3-back, with difficulty increasing as N increased. Using a visible light camera, the researchers measured gaze angles, head angles, and blink frequency. From these raw data, they derived several parameters, including eyeball rotation angles (calculated by subtracting head angle from gaze angle) and the sharing rate of head movement (the ratio of head movement to total gaze movement). Subjective MWL was assessed using the NASA-TLX Adaptive Weighted Workload (AWWL) score after each condition. The results demonstrated that subjective MWL increased monotonically with the difficulty of the N-back task. Statistical analysis revealed significant effects of task difficulty on the standard deviations (SDs) of horizontal and vertical gaze angles, the SD of horizontal eyeball rotation angle, the horizontal sharing rate of head movement, and blink frequency. Notably, the SD of horizontal eyeball rotation angle and blink frequency showed large effect sizes. Logistic regression analysis identified the SD of horizontal eyeball rotation angle and blink frequency as the most significant predictors for distinguishing between low (none) and high (3-back) MWL conditions. The resulting regression model achieved an area under the curve (AUC) of 0.822, indicating relatively high discrimination ability. Specifically, lower horizontal eyeball rotation variability and higher blink frequency were associated with higher mental workload. The significance of this work lies in validating visible light cameras as a practical, non-intrusive tool for monitoring driver cognitive load. By identifying specific eye-movement parameters—particularly horizontal eyeball rotation variability and blink rate—that correlate strongly with MWL, the study provides a foundation for developing real-time driver monitoring systems. These systems could alert drivers or adjust vehicle automation levels based on cognitive state, thereby reducing accidents caused by distraction or excessive workload. The authors note that further research is needed to account for varying traffic conditions and road types.
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 |
| enrich | success | semantic_scholar | — | — | 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 | — | — | 10 | 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.
- workload measurement
- mental demand
- gaze based attention detection
- useful field of view
- visual occlusion
- peripheral attention
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: theory or model