A Fast Signal Subspace Tracking Algorithm Based on a Subspace Information Criterion

In this paper, we present a new algorithm for tracking the signal subspace recursively. It is based on a new interpretation of the signal subspace. We introduce a novel information criterion for signal subspace estimation. We show that the solution of the proposed constrained optimization problem results the signal subspace. In addition, we introduce three adaptive algorithms which can be used for real time implementation of the signal subspace tracking. The computational complexity of the proposed signal subspace tracking algorithms are O(nr) which is much less than the direct computation of singular value decomposition or even some algorithms. To reduce the computational complexity, a fast alternative algorithm is proposed. The complexity of the latter algorithm is O(nr) which makes it feasible in real time applications. Simulation results in the direction of arrival (DOA) tracking context depict excellent performance of the proposed algorithms.