Performance analysis of various LMS adaptive filtering algorithms

摘要

Adaptive signal processing is extensively used as an area of research from few decades. There are various kinds of adaptive filtering algorithms are available in the literature which are used for different purposes. The work presented in this paper focused mainly on the performance analysis of various versions of most popular LMS (Least Mean Square) adaptive filtering algorithm when it is operated in unknown environment and deciding which algorithm has better performance in terms of minimum mean square error (MSE). From, the experimental results, it is observed that, when a same random input, random noise and desired response are considered for the different algorithms, with variable step size parameter and variable no. of filter taps, it very difficult to form a concrete decision on it, but in broader sense we can say that the performance of LMS sign sign algorithm for M = 2 and NLMS/Complex NLMS algorithm for higher value of M is found to be better in terms of mean square value of error when operated in an unknown situation.