Real-time analysis and conditionally optimal filtering of processes in nonlinear stochastic systems (survey) (Q1106175)

This survey is based on the works of the authors; it covers problems of real-time statistical analysis and filtering of processes in nonlinear stochastic systems described by differential, difference mixed differential-difference and integrodifferential equations. Special attention is devoted to real-time state and parameter estimation methods. Wide acceptance of the methods described in this survey is conditioned on the development of special software for statistical analysis of such systems and for the design of conditionally optimal filters. Tentative steps have been made in the direction of automatic generation of the equations for the probability characteristics from the given system equations.