This research studied 2 classifiers to determine their ability to discriminate among 4 levels of mental workload during a simulated air traffic control task using psychophysiological measures. Data from 7 air traffic controllers was used to train and test artificial neural network (ANN) and stepwise discriminant classifiers. When the 2 task difficulty manipulations were tested separately, the percentage correct classifications were between 84-88%. Feature reduction using saliency analysis for the ANNs resulted in a mean of 90% correct classification accuracy. Considering the data as a 2-class problem, acceptable load vs. overload, resulted in almost perfect classification accuracies, with mean percentage correct of 98%. In applied situations, the most important distinction among operator functional states would be to detect mental overload situations. These results suggest that psychophysiological data is capable of such discriminations with high levels of new and modified systems and adaptive aiding.
Abstract