Use of wearable physiological sensors to predict cognitive workload in a visuospatial learning task

Abstract

BACKGROUND: Increased cognitive workload, sometimes known as mental strain or mental effort, has been associated with reduced performance. OBJECTIVE: The use of physiological monitoring was investigated to predict cognitive workload and performance. METHODS: Twenty-one participants completed a 10-minute seated rest, a visuospatial learning task modeled after crane operation, and the Stroop test, an assessment that measures cognitive interference. Heart rate, heart rate variability, electrodermal activity, skin temperature, and electromyographic activity were collected. RESULTS: It was found that participants’ ability to learn the simulated crane operation task was inversely correlated with self-reported frustration. Significant changes were also found in physiological metrics in the simulation with respect to rest, including an increase in heart rate, electrodermal activity, and trapezius muscle activity; heart rate and muscle activity were also correlated with simulation performance. The relationship between physiological measures and self-reported workload was modeled and it was found that muscle activity and high frequency power, a measure of heart rate variability, were significantly associated with the workload reported. CONCLUSIONS: The findings support the use of physiological monitoring to inform real time decision making (e.g., identifying individuals at risk of injury) or training decisions (e.g., by identifying individuals that may benefit from additional training even when no errors are observed).