Blind identification of sparse channels and symbol detection via the EM algorithm
Gerasimos Mileounis, N. Kalouptsidis, Behtash Babadi, Vahid Tarokh · 2011
In this paper, we address the problem of blind identification of sparse channels. For this purpose, the Expectation-Maximization is modified to accommodate channel sparsity. The resulting algorithm is applicable for linear and nonlinear channels. Computer simulations on various channel set ups illustrate that the proposed algorithm achieves performance close to the genie-aided estimator.