Adaptive noise cancellation: a practical study of the least-mean square (LMS) over recursive least-square (RLS) algorithm

This paper analyses two types noise cancellation algorithms (i.e. the least-mean square (LMS) algorithm and the recursive least-squares (RLS) algorithm) and tries to outlines their strengths and their weaknesses. We have implemented these algorithms in a "semi-hardware" fashion, using a microphone, two loudspeakers and a Sound Blaster sound card and the data from this hardware is processed via software. This "semi-hardware" approach allows us to determine the practicality and effectiveness of these two algorithms in handling real-life situations. The results are encouraging as they are similar to the theoretical results. It also proves that the algorithms do work and that they. are capable of solving real-life problems.