Title :
Iterative signal-order and noise estimation for multivariate data
Author :
Lee, J. ; Staelin, D.H.
Author_Institution :
Res. Lab. of Electron., MIT, Cambridge, MA, USA
fDate :
1/18/2001 12:00:00 AM
Abstract :
The iterative order and noise (ION) estimation algorithm estimates the signal order of multivariate data, e.g. using a scree plot, and the unknown noise variances, e.g. using the expectation-maximisation (EM) algorithm. These estimates improve principal component analyses, linear regression, and Wiener filtering
Keywords :
Wiener filters; filtering theory; iterative methods; principal component analysis; signal resolution; Wiener filtering; expectation-maximisation algorithm; iterative signal-order estimation; linear regression; multivariate data; noise estimation; principal component analyses; scree plot; unknown noise variances;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20010101
