Subspace estimation and tracking using enhanced versions of Oja's algorithm

Abstract

We present two normalized versions of the Oja (1992) algorithm (NOja and NOOja) which can be used for the estimation of minor (noise) and principal (signal) subspaces of a vector sequence. The new algorithms offer, as compared to Oja, a faster convergence, a better orthogonality and numerical stability with a slight increase in computational complexity. These algorithms can find many applications, in particular, in wireless communications.