Gauss-Markov model formulation for the estimation of time-varying signals and systems
K.M. Malladi, R. V. Raja Kumar, K. Veerabhadra Rao · 2002
A Gauss-Markov model is formulated to estimate the model of a nonstationary signal. The nonstationary signal is represented by a time-varying AR model. The time-varying parameters of the model are modeled as stochastic processes. A unified method for the optimal estimation of both the time-varying parameters and their corresponding stochastic model parameters is presented in this work. This method utilises the proposed Gauss-Markov model for the estimation process through the extended Kalman filter (EKF).