SET-THEORETIC SIGNAL RESTORATION USING AN ERROR IN VARIABLES CRITERION

In this correspondence, the restoration of a signal degraded bg a stoc hastic impulse response is formulated as a problem with uncertainties in both the measurements and the impulse response, The method of total least squares, and variants thereof, are effective techniques for sol ving this class of problems. However, unlike set theoretic estimation schemes. these methods do not allow the incorporation of other a prior i information in the estimate, in this correspondence, two new sets mo tivated hy total least squares are introduced for set theoretic estima tion, The convexity of these sets is established and the projection op erators onto these sets are given, Through simulations, the advantages of the new technique over conventional and older set theoretic scheme s for restoration are demonstrated.