Robust PPG-Based Mental Workload Assessment System Using Wearable Devices.
IEEE Journal of Biomedical and Health Informatics
|December 28, 2021
Summary
This study introduces a new method to improve mental workload (MW) assessment using photoplethysmogram (PPG) signals from wearables. By removing signal artifacts, it enables more reliable and accurate MW evaluation, comparable to traditional ECG methods.
Area of Science:
- Biomedical Engineering
- Wearable Technology
- Physiological Signal Processing
Background:
- Heart rate variability (HRV) is a key indicator for assessing mental workload (MW).
- Photoplethysmogram (PPG) from wearables offers a convenient alternative to ECG for daily MW monitoring.
- PPG signals are susceptible to artifacts, leading to invalid Inter-beat Intervals (IBIs) and hindering reliable MW assessment.
Purpose of the Study:
- To develop and validate a robust pre- and post-processing technique for PPG-based HRV analysis.
- To mitigate the impact of signal artifacts on MW assessment accuracy.
- To enhance the reliability and sustainability of wearable MW monitoring systems.
Main Methods:
- Proposed a novel technique combining outlier removal and uncertainty estimation for PPG signal processing.
- Applied the method to process Inter-beat Interval (IBI) data derived from PPG signals.
- Validated the approach using two open datasets (CLAS and MAUS).
Main Results:
- The proposed method significantly improved the accuracy of MW assessment (from 66.7% to 74.2%).
- It also reduced inter-user variance in MW assessment (from 11.3% to 10.8%).
- Performance was comparable to established ECG-based MW assessment systems.
Conclusions:
- The developed technique effectively addresses PPG signal artifacts, enabling accurate HRV feature extraction.
- This approach enhances the reliability of wearable devices for continuous mental workload monitoring.
- The findings support the use of PPG-based systems for practical, daily MW assessment.
