A Dynamic Process Model for Predicting Workload in an Air Traffic Controller Task

We present a dynamic process model for workload, developed according to a conducted experiment, which recorded the pupil dilation during an air traffic controller simulation. We describe how we built such a dynamic system based on the collected data. Logged events that happened in our simulation were used as system input and the recorded pupil dilation as output. Afterwards, we used the MATLAB system identification toolbox to identify the transfer function between input and output. The identified model is validated with a validation data set that has been excluded from the identification process. Results show that we are able to explain nearly 50% of the variance of the recorded pupil dilation data in the air traffic controller simulation. Moreover, the model explains some contrary results of the statistical analysis from our experiment.