A New Affine Projection Algorithm and Its Statistical Behavior

An Affine projection algorithm with Direction error (AP-DE) is presented by redefining the iteration error. Under a measurement-noise-free condition, the iteration error is directly caused by the direction vector. A statistical analysis model is used to analyze the AP-DE algorithm. Deterministic recursive equations for the mean weight error and for the Mean-square error (MSE) in iteration direction are derived. We also analyze the stability of MSE in iteration direction and the optimal step-size for the AP-DE algorithm. Simulation results are provided to corroborate the analytical theory.