DocumentCode :
3079871
Title :
Smoother implementations for discrete-time Gaussian reciprocal processes
Author :
Greene, Calvin D. ; Levy, Bernard C.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., California Univ., Davis, CA, USA
fYear :
1990
fDate :
5-7 Dec 1990
Firstpage :
837
Abstract :
The smoothing problem for discrete-time Gaussian reciprocal processes is examined. In this case, the smoother takes the form of a second-order two-point boundary-value nearest-neighbor model. This smoother is non-causal, but admits causal implementations which extend the two-filter and Rauch-Tung-Striebel smoothing formulas of Gauss-Markov processes. A multirate implementations based on a block cyclic reduction method is also described
Keywords :
Markov processes; boundary-value problems; filtering and prediction theory; signal processing; Gauss-Markov processes; Rauch-Tung-Striebel; block cyclic reduction; boundary-value nearest-neighbor model; discrete-time Gaussian reciprocal processes; filtering; smoothing; Boundary conditions; Covariance matrix; Equations; Gaussian processes; Integrated circuit modeling; Markov processes; Noise measurement; Recursive estimation; Sampling methods; Smoothing methods;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Decision and Control, 1990., Proceedings of the 29th IEEE Conference on
Conference_Location :
Honolulu, HI
Type :
conf
DOI :
10.1109/CDC.1990.203706
Filename :
203706
Link To Document :
بازگشت