Human-Automation Interaction and Safety

This study evaluates two time-series foundation models for cognitive workload classification from eye-tracking data, showing better generalization to unseen individuals than task-specific models.

This study examines how pupil dynamics reflect compensatory control after cognitive demand and their relation to motor performance.

This paper identifies neural markers of trust dynamics in human-AI interactions using EEG, showing how confidence and feedback processing influence trust ratings.

This study investigates the neurophysiological effects of texting while driving under different working-memory loads, finding altered reaction times, gaze behavior, and brain activity patterns.

The paper assesses physiological signals to predict cognitive states, finding that pupil size change is the most reliable biomarker for workload, urgency, and mind wandering.

The paper uses eye-movement data in virtual driving to analyze human behavior through information-theoretic measures, finding that system-level information flow correlates stronger with performance than individual metrics.

This study identifies physiological correlates of mental workload variations in ATC tasks and shows neurometrics can inform adaptive systems.

This study uses pupillometry to measure mental effort in cognitive tasks, showing that automatic tasks can become more demanding with experimental manipulation and that effort peaks early in trials.

This study investigates how task load affects performance using EEG, GSR, and eye-tracking data, finding that EEG and GSR best predict task performance.