Sequence Estimation over Linearly-Constrained Random Channels

This paper presents a new approach using EM (Expectation-Maximization) algorithms for ML (maximum likelihood) sequence estimation over unknown ISI (inter-symbol interference) channels with linearly–constrained random channel coefficients which may be fast time-varying. By using the EM formulation to marginalize over the underlying channel coefficient distribution, maximum-likelihood estimates of the transmitted sequence are obtained. The EM algorithms are shown to perform better, in terms of BER, than existing algorithms which perform jointly-optimal sequence and channel estimation, or which do not take into account fast time-varying channel effects.