An Affine Projection Algorithm with Periodically Evolved Update Interval

Abstract

We propose a novel affine projection algorithm (APA) that updates the weights intermittently. While the conventional APA updates the weights at each time instant, the proposed APA performs an intermittent update of the weights through dynamically adjusting the update interval. The adjustment of the update interval is accomplished by comparing the squared output error with a threshold derived from the steady-state mean-squared error. Experimental results show that the proposed algorithm has improved performance in terms of its convergence rate and steady-state error while reducing the number of updates.