Vladimir V. Galatenko

L. S. Vygotsky in his famous methodological essay “The historical meaning of psychological crisis” (1928) emphasized the importance of studying any psychological process or state as a “whole” — that is, as characterized from the subjective and objective sides at the same time. This position is fully relevant for studying the human functional states (FSes). Today the objective psychophysiological diagnostics of human FSes in activities associated with a high risk of technological disasters (in nuclear-power plants, transportation, the chemical industry) are extremely relevant and socially important. This article reviews some new psychophysiological methods of FS assessment that are being developed in Russia and abroad and discusses different aspects of developing integral psychophysiological FS assessment. The emphasis is on distant methods of FS diagnostics: the bioradiolocation method, laser Doppler vibrometry, eye tracking, audio and video recordings, infrared thermography. The possibilities and limitations of the most popular emotion atlases — the Facial Affect Scoring Technique (FAST) and the Facial Action Coding System (FACS) — in developing distant visual-range and infrared-range systems for automated classification of facial expressions are analyzed. A special section of the article concentrates on the problem of constructing an integral psychophysiological FS index. Mathematical algorithms that provide a partition of FS indicators into different FS types are based on various methods of machine learning. We propose the vector approach for construction of complex estimations of the human FSes.

Automated classification of a human functional state is an important problem, with applications including stress resistance evaluation, supervision over operators of critical infrastructure, teaching and phobia therapy. Such classification is particularly efficient in systems for teaching and phobia therapy that include a virtual reality module, and provide the capability for dynamic adjustment of task complexity.

In this paper, a method for automated real-time binary classification of human functional states (calm wakefulness vs. stress) based on discrete wavelet transform of EEG data 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 peculiarities in the classification, using very short individual learning samples, significantly increases classification reliability. The experimental study that proved this assertion was based on a specialized scenario in which individuals solved the task of detecting objects with given properties in a dynamic set of flying objects.