[108] An intelligent system to support condition monitoring for activities of operators of complex technical systems
L S Kuravsky and G A Yuryev Moscow State University of Psychology and Education, Computer Science Faculty, 29 Sretenka Street, Moscow 127051, Russia. Email: l.s.kuravsky@gmail.com / g.a.yuryev@gmail.com
An approach to support condition monitoring for activities of operators of complex technical systems is presented. It is based on comparisons of current exercises with activity database patterns in the wavelet representation metric associated with observed parameters, as well as on probabilistic assessments of skill class recognition using sample distribution functions of exercise distances to cluster centres in a scaling space, and Bayesian likelihood estimations with the aid of probabilistic profile of staying within activity parameter ranges. Capabilities and usage scenarios of the intelligent system for flight analysis (ISFA) implementing the given techniques are under consideration. Keywords: operators of complex technical systems, discrete wavelet transform, skill class recognition, principal component analysis, multi-dimensional scaling, cluster analysis.
