Title :
Recursive filtering and smoothing for reciprocal Gaussian processes with Dirichlet boundary conditions
Author :
Baccarelli, E. ; Cusani, R.
Author_Institution :
INFOCOM Dept., Rome Univ., Italy
fDate :
3/1/1998 12:00:00 AM
Abstract :
The minimum mean square error (MMSE) estimation problem for a discrete-index reciprocal Gaussian process impaired by additive white Gaussian noise is completely solved in the general case of noisily observed Dirichlet random boundary conditions. Finite sets of recursive equations are obtained for the computation of the filtered sequence and of the fixed-point, fixed-interval, and fixed-lag smoothed sequences. Recursive expressions are also given for the MMSE performance of the presented estimators. Simulation results confirm the validity of the performance analysis
Keywords :
Gaussian noise; Gaussian processes; least mean squares methods; random processes; recursive estimation; sequences; smoothing methods; white noise; Dirichlet random boundary conditions; MMSE estimation problem; MMSE performance; additive white Gaussian noise; discrete-index reciprocal Gaussian process; filtered sequence; fixed-interval sequence; fixed-lag smoothed sequence; fixed-point sequence; minimum mean square error; performance analysis; recursive equation; recursive expressions; recursive filtering; simulation results; Additive white noise; Boundary conditions; Equations; Estimation error; Filtering; Gaussian noise; Gaussian processes; Mean square error methods; Recursive estimation; Smoothing methods;
Journal_Title :
Signal Processing, IEEE Transactions on
