ABSTRACT
Fatigue is a known contributor to open water accidents, decreased operational efficiency, and poor Warfighter health. Real-time feedback of the Warfighters cognitive state will allow for increased awareness of capabilities/limitations and adaptable decision making based on Warfighter readiness. The Fatigue Detection/Prediction using Machine Learning (ML) and Wearable Technology project aimed to develop a ML algorithm capable of detecting changes in the Parasympathetic Nervous System (PNS) that are indicative of cognitive fatigue using a Commercial Off-The-Shelf (COTS) wrist-worn device. A biometric dataset of 30 participants (including some active duty personnel) performing quantifiable vigilance tasking was collected and annotated with operator performance metrics and cognitive load. Variations of the Mackworth clock, a vigilance task widely used in psychometric studies to quantify cognitive engagement and fatigue, was used to generate quantitative operator performance metrics and discrete cognitive load states. ML models were trained and validated on the annotated biometric dataset to: 1) regress operator task performance accuracies, and 2) classify cognitive load/task difficulty. A trained Convolution Neural Network (CNN) regression model was able to predict Mackworth Clock task performance accuracy to within a mean absolute error of 2.5 percent. Additionally, a separate CNN classifier model achieved binary task-type classification accuracies of 86.5 percent, with different type tasks corresponding to a higher vs. lower cognitive load. The next phase of this Research and Development (R and D) effort will include additional testing events with Navy-relevant tasking (i.e., ship navigation, track management, and other watch standing tasks) with a participant pool of only active duty personnel.