Abstract
An algorithm is described for the standard fixed-interval smoothing problem in which the system is linear, time-varying, and discrete-time. The smoother is shown to be a dual version of the Bryson-Frazier smoother. The algorithm is less attractive in its numerical implementation than the original version, because it involves inversion of the state transition matrix. However, the mechanization of the new algorithm allows the smoothed estimate or error covariance to be readily updated in response to a change in the initial statistics.
| Original language | English |
|---|---|
| Title of host publication | SICE 89 Proc 28th SICE Annu Conf |
| Publisher | Publ by IEEE |
| Pages | 1103-1106 |
| Number of pages | 4 |
| Publication status | Published - 1989 |
| Externally published | Yes |
| Event | SICE '89: Proceedings of the 28th SICE Annual Conference Volume 2 (of 2) - Tokyo, Jpn Duration: Jul 25 1989 → Jul 27 1989 |
Other
| Other | SICE '89: Proceedings of the 28th SICE Annual Conference Volume 2 (of 2) |
|---|---|
| City | Tokyo, Jpn |
| Period | 7/25/89 → 7/27/89 |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
A new fixed-interval smoothing algorithm. / Watanabe, Keigo.
SICE 89 Proc 28th SICE Annu Conf. Publ by IEEE, 1989. p. 1103-1106.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A new fixed-interval smoothing algorithm
AU - Watanabe, Keigo
PY - 1989
Y1 - 1989
N2 - An algorithm is described for the standard fixed-interval smoothing problem in which the system is linear, time-varying, and discrete-time. The smoother is shown to be a dual version of the Bryson-Frazier smoother. The algorithm is less attractive in its numerical implementation than the original version, because it involves inversion of the state transition matrix. However, the mechanization of the new algorithm allows the smoothed estimate or error covariance to be readily updated in response to a change in the initial statistics.
AB - An algorithm is described for the standard fixed-interval smoothing problem in which the system is linear, time-varying, and discrete-time. The smoother is shown to be a dual version of the Bryson-Frazier smoother. The algorithm is less attractive in its numerical implementation than the original version, because it involves inversion of the state transition matrix. However, the mechanization of the new algorithm allows the smoothed estimate or error covariance to be readily updated in response to a change in the initial statistics.
UR - http://www.scopus.com/inward/record.url?scp=0024894443&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0024894443&partnerID=8YFLogxK
M3 - Conference contribution
SP - 1103
EP - 1106
BT - SICE 89 Proc 28th SICE Annu Conf
PB - Publ by IEEE
ER -