Training Machines to Recognize Neural Correlates of Team and Team Member Uncertainty

Abstract

Every human decision has its origins in uncertainty. Despite its ubiquity, and theoretical understandings, there are few ways of dynamically tracking moment-by-moment uncertainties. Knowing when a team or one of its members was beginning to experience uncertainty would provide a basis for assessment-intervention loops enabling machines to better support human activities. In this paper we describe efforts to train machines to recognize neural correlates of team and team member uncertainty.

Second-by-second symbolic representations of EEG power were created from each team member and quantitative estimates of their neurodynamic information were calculated from the Shannon entropy of the symbol streams. Neurodynamic information was isolated from thirty-one 70-127s segments where speech indicated surprise or uncertainty by team members. The first 70s of these segments were classified by self-organizing artificial neural networks to provide profiles of the onset of uncertainty.

The thirty-one segments were classified into six artificial neural network categories based on dynamic profiles and the levels of neurodynamic information. The categories were sufficiently distinct to suggest that alternative forms of feedback could be developed for each category.

The results suggest that computer machines can be taught to recognize the onset, and possibly predict the duration of uncertainty in humans performing complex tasks. The ability of machines to recognize neurodynamic correlates of uncertainty provide the potential for developing real-time feedback and scaffolding for teams and team members performing in complex task environments.