Related Experiment Video
Updated: Dec 22, 2025
10:45
A Community-based Stress Management Program: Using Wearable Devices to Assess Whole Body Physiological Responses in Non-laboratory Settings
Published on: January 22, 2018
8.0K
Assessment of mental workload based on multi-physiological signals
Xiaoli Fan1, Chaoyi Zhao1, Xin Zhang1
1SAMR Key Laboratory of Human Factors and Ergonomics, China National Institute of Standardization, Beijing, 100191, China.
Summary
This study monitored electroencephalography (EEG) and electrocardiogram (ECG) to assess mental workload during visual tasks. Findings show physiological changes correlate with workload, enabling effective mental workload monitoring.
Area of Science:
- Neuroscience
- Human Factors Engineering
- Biomedical Engineering
Background:
- Mental workload is a significant factor contributing to human errors in critical situations like road accidents.
- Understanding and quantifying mental workload is crucial for preventing adverse incidents.
Purpose of the Study:
- To investigate the impact of varying mental workload levels on electroencephalographic (EEG) and electrocardiogram (ECG) signals.
- To develop a comprehensive evaluation model for mental workload based on physiological responses.
Main Methods:
- Induced three distinct mental workload levels using visual monitoring tasks of increasing difficulty with 20 healthy subjects.
- Recorded and analyzed EEG parameters (θ, α, β energy, ratios) and ECG parameters (Mean RR, RMSSD, HF_norm, SampEn, LF_norm, LF/HF).
- Applied Principal Component Analysis (PCA) and Support Vector Machine (SVM) for feature extraction and classification.
Main Results:
- Subjective scores, reaction time, and accuracy confirmed successful workload induction.
- Significant changes in EEG (e.g., decreased θ and α energy, increased β energy) and ECG (e.g., decreased Mean RR, increased LF/HF) were observed with increasing workload.
- An SVM classification model achieved 80% accuracy in mental workload assessment.
Conclusions:
- Physiological signals (EEG and ECG) effectively reflect mental workload levels.
- The developed algorithm and model demonstrate potential for real-time mental workload monitoring.
