SEQUENCE ESTIMATION IN THE PRESENCE OF RANDOM PARAMETERS VIA THE EM ALGORITHM

The expectation-maximization (EM) algorithm was first introduced in th e statistics literature as an iterative procedure that under some cond itions produces maximum-likelihood (ML) parameter estimates, In this p aper we investigate the application of the EM algorithm to sequence es timation in the presence of random disturbances and additive white Gau ssian noise, As examples of the use of the EM algorithm, we look at th e random-phase and fading channels, and show that a formulation of the sequence estimation problem based on the EM algorithm can provide a m eans of obtaining ML sequence estimates, a task that has been previous ly too complex to perform.