Title :
Canonical coordinates and the geometry of inference, rate, and capacity
Author :
Scharf, Louis L. ; Mullis, Clifford T.
Author_Institution :
Dept. of Electr. & Comput. Eng., Colorado Univ., Boulder, CO, USA
fDate :
3/1/2000 12:00:00 AM
Abstract :
Canonical correlations measure the cosines of principal angles between random vectors. These cosines multiplicatively decompose concentration ellipses for second-order filtering and additively decompose the information rate for the Gaussian channel. More over, they establish a geometrical connection between error covariance, error rate, information rate, and principal angles. There is a limit to how small these angles can be made, and this limit determines the channel capacity
Keywords :
Gaussian channels; channel capacity; correlation methods; covariance matrices; filtering theory; Gaussian channel; canonical coordinates; capacity; channel capacity; concentration ellipse decomposition; cosines; covariance matrix; error covariance; error rate; inference geometry; information rate; principal angles; random vectors; second-order filtering; second-order inference; Channel capacity; Coordinate measuring machines; Error analysis; Estimation theory; Gaussian channels; Geometry; Helium; Information filtering; Information filters; Information rates;
Journal_Title :
Signal Processing, IEEE Transactions on
