This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: EE 562a Homework Set 4 Due Monday 26 February 2007 1 (The following welldefined problems come from different sources, and the notation used may vary. Don’t let that bother you!) 1. Let x ( u ) and y ( u ) be random vectors that are related to each other by the equation y ( u ) = Gx ( u ) , where G and the mean vector and covariance matrix of x ( u ) are given by G = 6 2 3 0 1 6 2 3 0 1 6 2 0 0 1 6 m x = K x = I . (a) What is the LMMSE estimator of x ( u, 3) x ( u, 4) from the observation x ( u, 1) x ( u, 2) ? (b) What is the LMMSE estimator of y ( u ) based on the observation of x ( u, 1) x ( u, 2) ? (c) Now let’s consider a more general problem. Let ˆ w ( u ) be a LMMSE estimate of w ( u ) that has been constructed from an observation of v ( u ). Suppose that z ( u ) = Hw ( u ). How is the LMMSE estimate ˆ z ( u ) of z ( u ) from an observation of v ( u ), related to ˆ w ( u )? (d) You can use the results of (c) to check your solution to (b). Indicate how v ( u ), w ( u ), and z ( u ) can be equated with the components of the problem in (a) and (b) in order to accomplish this check....
View
Full Document
 Spring '07
 ToddBrun
 Probability theory, LMMSE, random vectors, LMMSE estimate

Click to edit the document details