The Impacts of Temporal Variation and Individual Differences in Driver Cognitive Workload on ECG-Based Detection

Area of Science:

• Human-Computer Interaction
• Biomedical Engineering
• Cognitive Science

Background:

• Monitoring driver cognitive workload is crucial for preventing errors in human-machine systems.
• Cognitive workload fluctuates over time and varies significantly between individuals.

Purpose of the Study:

• To investigate the robustness of driver cognitive workload detection using electrocardiogram (ECG).
• To assess the impact of temporal variation and individual differences on ECG-based workload detection.

Main Methods:

• A driving simulation study was conducted with four experimental conditions.
• Heart rate (HR) and heart rate variability (HRV) were analyzed across two 1-hour blocks.
• Random forests were used to classify cognitive workload based on HR and HRV data.

Main Results:

• Significant differences in HR and HRV were observed between repeated blocks, indicating temporal variation in cognitive workload.
• Classification performance improved significantly across blocks and individuals after normalizing HR and HRV by their respective baselines.

Conclusions:

• Temporal variation and individual differences in cognitive workload impact ECG-based detection.
• Normalization techniques using appropriate baselines can effectively compensate for these variations, enhancing detection accuracy.