Eye Tracking and Autonomic Nervous System Responses. A Machine Learning Approach to Understanding Cognitive Stress

Cognitive and emotional load in the course of increasing the complexity of tasks leads to the activation of various parts of the autonomic nervous system (ANS) and can be accompanied by an increase in the efficiency of problem solving. An increase in cognitive load under the condition of high motivation is a stress factor and is expressed in a different reaction of the sympathetic and parasympathetic links in response to the load. This study explored the ANS reactions by measuring the pupil size of 61 healthy sub-clinical volunteers in response to the gradually increasing complexity of tasks. The experiment included 3 blocks of a combined visual search and 1-back task with six levels of difficulty. K-mean clustering method was used for the analysis. An increase in the complexity of the task from the first to the sixth level led to different dynamics of the pupil size in the three clustered groups. In one group, an intense high switchability and an active reaction with a large amplitude of changes were visible, in the second group the dynamics of changes was minimal, and a third intermediate group was also identified. Our results highlight individual differences in the reaction of the sympathetic and parasympathetic branches of ANS under cognitive workload depending on biometric and psychometric parameters.