Comparison of Adaptive Filtering Algorithms Based on Time Varying Weighting Factor

Abstract

In this paper, a Leaky Time Varying Mean Mixed Norm Adaptive algorithm is proposed. The weight drift issue is overcome by minimizing the function defining weighted sum of the LMS and LMF cost functions along with the leakage factor. The weighting factor is applied in time varying environment and made to adapt itself so as to emphasize one cost function over the other based on closeness to the optimum value. The proposed algorithm results are compared with the conventional algorithms and the obtained results show an improvement over the convergence.