Title :
The fixed-interval smoother for continuous-time processes
Author :
Wall, J.E. ; Willsky, A.S. ; Sandell, N.T.
Author_Institution :
Honeywell, S&RC, Minneapolis, MI
Abstract :
A "first principles" argument is used to obtain the Mayne-Fraser two-filter smoother. The built-in asymmetry of the Mayne-Fraser smoother is pointed out, and it is shown how the asymmetry may be removed. Reversed-time Markov models play a key role here in forming a state estimate from future observations.
Keywords :
Bayesian methods; Kalman filters; Maximum likelihood estimation; Random variables; State estimation; Steady-state; Yield estimation;
Conference_Titel :
Decision and Control including the Symposium on Adaptive Processes, 1980 19th IEEE Conference on
Conference_Location :
Albuquerque, NM, USA
DOI :
10.1109/CDC.1980.271822
