Estimation of mental workload during automobile driving based on the measurement of eye and head movement
DOI: 10.1299/jsmedsd.2019.29.1405
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 quantitative estimation of mental workload (MWL) during automobile driving to prevent inattentive driving and enhance safety. While physiological signals like heart rate and brain waves are commonly used for MWL assessment, they require intrusive equipment. Eye movement tracking offers a non-contact alternative, but existing methods often rely on expensive infrared systems susceptible to sunlight interference. This research investigates whether visible-light camera-based measurements of eye and head movements can effectively estimate MWL, aiming to develop a low-cost, practical estimation model. The experiment involved twelve students (six males, six females) performing a driving task on a simulator while simultaneously completing an N-back secondary task to manipulate cognitive load. Five conditions were tested: no secondary task (None), 0-back, 1-back, 2-back, and 3-back. A visible-light image sensor measured gaze angles, head angles, and blink frequency at approximately 10 Hz. From these raw data, the researchers calculated eyeball rotation angles and the "sharing rate of head movement," defined as the ratio of head movement to gaze movement. Subjective MWL was assessed using the Adaptive Weighted Workload (AWWL) score from the NASA-TLX questionnaire. Statistical analyses included two-way ANOVA to identify significant parameters and logistic regression to build a prediction model distinguishing between low (None) and high (3-back) workload conditions. Results indicated that subjective MWL increased monotonically with N-back difficulty, while task accuracy decreased. ANOVA revealed statistically significant effects of task difficulty on the standard deviations (SDs) of horizontal and vertical gaze angles, SD of horizontal eyeball rotation angle, horizontal head movement sharing rate, and blink frequency. Specifically, higher workload correlated with reduced variability in horizontal gaze and eyeball rotation, increased blink frequency, and an initial rise in head movement sharing rate. Logistic regression analysis identified the SD of horizontal eyeball rotation angle and blink frequency as the most significant predictors. The resulting model achieved an Area Under the Curve (AUC) of 0.882, with an optimal threshold yielding a true positive rate of 0.917 and a false positive rate of 0.083. The study concludes that visible-light camera-based eye and head movement metrics, particularly horizontal eyeball rotation variability and blink frequency, are effective indicators for estimating driver mental workload. The high predictive accuracy of the logistic regression model suggests that non-intrusive, low-cost eye-tracking systems can reliably distinguish between low and high cognitive load states. This approach offers a viable solution for real-time monitoring of driver attention, potentially supporting the development of advanced driver assistance systems that mitigate risks associated with cognitive overload.
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 | failed | — | — | — | 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.
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, behavioral performance data
- Theoretical Contribution: theory or model