Closed-Loop Extracranial Activation using Reinforcement-learning (CLEAR)

High workloads and operational pressures can degrade human analysts’ cognitive performance, jeopardizing their ability to carry out mission-critical tasks. To maximize the potential of human analysts, a method is required to enhance performance across a broad array of human analysts, tasks, and contexts. Real-time evaluation of cognitive state and novel technologies for closed-loop feedback control of non-invasive brain stimulation can provide reliable and effective augmentation of dynamic brain information processing capacities (dBIPC). Assessments of electrical and hemodynamic brain activity, combined with behavioral measures, can evaluate state and optimize performance using stimulation. Charles River Analytics conducted a Phase I effort to demonstrate the feasibility of a system for Closed-Loop Extracranial Activation using Reinforcement Learning (CLEAR), a hardware agnostic, closed-loop system that monitors, detects, and safely manages individual stimulation parameters using reinforcement learning with flexible reward and policy mechanisms. Based on our successful Phase I results, we now propose a Phase II effort to refine and demonstrate CLEAR. CLEAR combines real-time electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) to unobtrusively assess cognitive state. CLEAR uses reinforcement learning techniques to optimize stimulation parameters, delivering targeted modulation to reliably enhance performance for extended periods.