A modified expectation maximization algorithm for maximum likelihood direction-of-arrival estimation
Yifeng Zhou, J.P.Y. Lee · 2002
In this paper a modified expectation maximization (EM) algorithm is proposed for maximum likelihood estimation of direction-of-arrival (DOA). It is based on the expectation, conditional maximization (ECM) algorithm. In the modified algorithm, the M-step is replaced by a sequence of conditional maximization steps which either conditionally maximizes the expectation of the complete data or the actual likelihood. The modified EM algorithm is computationally efficient, and yields a faster convergence rate than the EM algorithm. Computer simulations are used to demonstrate the performance and effectiveness of the proposed algorithm.