Parameter Estimation of Systems Described by the Relation with Noisy Observations

Jerzy Świątek (Wroclaw University of Technology, Poland)

Abstract: In this paper the problem of parameter estimation of an input-output system is discussed. It is assumed that the system is described by the relation known with accuracy to some parameters. The possible noisy observations of system are described. The estimation algorithm based on maximum likelihood method is proposed. The presented approach is illustrated by analytical examples.

Keywords: input-output system, knowledge representation, parameter estimation, relational systems, system identification

Categories: H.2.1, I.2.11, I.2.4