Title :
Recursive methods for estimating multiple missing values of a multivariate stationary process
Author :
Bondon, Pascal ; Ruiz, Diego P. ; Gallego, Antolino
Author_Institution :
Lab. des Signaux et Syst., CNRS, Gif-sur-Yvette, France
Abstract :
Existing methods for estimating linearly s future values of a m-variate stationary random process using a record of p vectors from the past consist in first solving the one-step prediction problem and then all the h-step prediction problems for 2⩽h⩽s independently. When the Levinson (1947) algorithm is used, each prediction problem is solved with a numerical complexity proportional to p2. We propose new methods to solve the h-step prediction problems for h⩾2 with a numerical complexity proportional to p
Keywords :
computational complexity; prediction theory; random processes; recursive estimation; signal processing; Levinson algorithm; multiple missing values estimation; multivariate stationary process; numerical complexity; prediction problems; recursive methods; signal processing; stationary random process; vectors; Bonding; Geophysical signal processing; Geophysics; Hilbert space; Predictive models; Random processes; Recursive estimation; Signal analysis; Signal processing algorithms; Space stations;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.681699