Assessment of mental workload based on multi-physiological signals
DOI: 10.3233/thc-209008
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 challenge of accurately assessing mental workload in human-machine systems, where high cognitive demands can lead to operator error and safety incidents. While subjective and performance-based measures exist, they suffer from individual bias or task-specific limitations. Physiological signals like electroencephalography (EEG) and electrocardiography (ECG) offer continuous, direct measurement but have yielded mixed results in isolation. The research aims to establish a comprehensive evaluation model by combining multi-physiological signals to overcome the limitations of single-indicator approaches. The experiment involved 20 healthy male subjects performing visual instrument-monitoring tasks at three difficulty levels: low, medium, and high. Task difficulty was manipulated by varying the number of information sources to monitor. EEG signals were recorded using a 32-channel system, focusing on Frontal, Central, Parietal, and Occipital regions, while ECG data were collected via a wearable patch. Signal processing included Independent Component Analysis for EEG artifact removal and Wavelet Packet Transform for rhythm analysis. ECG signals underwent time, frequency, and nonlinear domain analyses. Subjective workload was rated using a 10-point scale, and performance was measured by reaction time and accuracy. Results confirmed that task difficulty significantly increased subjective workload scores, reaction times, and decreased accuracy. EEG analysis revealed that increased workload caused significant decreases in theta and alpha energy in specific regions, while beta energy increased in Frontal and Occipital areas. Notably, the Occipital region showed the most sensitive changes, including significant shifts in alpha/theta ratios and wavelet packet entropy. ECG parameters indicated that Mean RR, RMSSD, HF_norm, and Sample Entropy decreased with higher workload, whereas LF_norm and the LF/HF ratio increased, reflecting shifts in autonomic nervous system activity. To create a robust classification model, the researchers selected eight EEG indicators from the Occipital region and six ECG indicators. Principal Component Analysis (PCA) reduced the dimensionality of this 14-feature set to five principal components. These features were input into a Support Vector Machine (SVM) classifier. Among tested kernel functions, the Radial Basis Kernel achieved the best training accuracy of 92.2%. The final model demonstrated an 80% classification accuracy in distinguishing between low, medium, and high mental workload levels. The study concludes that fusing EEG and ECG data via PCA and SVM provides an effective method for monitoring mental workload, though further validation is needed for other task types and online implementation.
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 | semantic_scholar | — | — | 6 | 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 | partial | — | — | — | 2 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified_with_issues.
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
- Methodological Resource: metric or index
- Theoretical Contribution: theory or model