摘要：Automated classification of a human functional state is an important problem, with applicationsincluding stress resistance evaluation, supervision over operators of criticalinfrastructure, teaching and phobia therapy. Such classification is particularly efficientin systems for teaching and phobia therapy that include a virtual reality module, andprovide the capability for dynamic adjustment of task complexity.In this paper, a method for automated real-time binary classification of human functionalstates (calm wakefulness vs. stress) based on discrete wavelet transform of EEGdata is considered. It is shown that an individual tuning stage of the classification algorithm— a stage that allows the involvement of certain information on individual peculiaritiesin the classification, using very short individual learning samples, significantlyincreases classification reliability. The experimental study that proved this assertion wasbased on a specialized scenario in which individuals solved the task of detecting objectswith given properties in a dynamic set of flying objects.
