Dynamic difficulty using brain metrics of workload

Abstract

Dynamic difficulty adjustments can be used in humancomputer systems in order to improve user engagement and performance. In this paper, we use functional near-infrared spectroscopy (fNIRS) to obtain passive brain sensing data and detect extended periods of boredom or overload. From these physiological signals, we can adapt a simulation in order to optimize workload in real-time, which allows the system to better fit the task to the user from moment to moment. To demonstrate this idea, we ran a laboratory study in which participants performed path planning for multiple unmanned aerial vehicles (UAVs) in a simulation. Based on their state, we varied the difficulty of the task by adding or removing UAVs and found that we were able to decrease errors by 35% over a baseline condition. Our results show that we can use fNIRS brain sensing to detect task difficulty in real-time and construct an interface that improves user performance through dynamic difficulty adjustment.

Examining the Reliability of Using fNIRS in Realistic HCI Settings for Spatial and Verbal Tasks

“…Afergan et al [1] demonstrated the ability to distinguish between different workload states (Sensitivity) during a UAV simulation task. Additionally, the study identified workload changes over time (Bandwidth).…”

Real-time Prediction of User Performance based on Pupillary Assessment via Eye-Tracking

“…For example, Csíkszentmihályi (1975) introduced "flow" as a key concept in performance motivation. The flow mental state means a zone in which the user intrinsically performs an action in a feeling of energized focus and full attentional involvement that leads to a moderate level of mental effort (Afergan et al, 2014). Because of the positive relationship between intrinsic motivation and mental effort, pupillometry researchers have found that pupils enlarge when people view interesting stimuli.…”

Dynamic Workload Adjustments in Human-Machine Systems Based on GSR Features

“…GSR data were also tested by the Boosting algorith m with Haar-like features for cognitive load classifications . Furthermo re, Afergan et al [7] used functional near-infrared spectroscopy (fNIRS) to detect task difficulty and optimize workload with a dynamic adaptation. Ho wever, few research es use GSR features to index cognitive load dynamically in an adaptive feedback loop.…”