J. Sanubari (Indonesia)
Variable Step Size, Adaptive filter, Convex step size.
In this paper, a new cost function for improving the perfor mance of the least mean square (LMS) method is proposed. The proposed cost function is convex. The first derivative of the proposed cost function is continue. The prove of the convexity of the function is pre sented. The theoretical study of the convergence charac teristic shows that lower error and faster convergence can be obtained by using the proposed function. The proposed function provide large weighting factor when the error is small. On the hand, when the error is large, a small weight ing factor is applied. By doing so, the effect of the noise can be reduced. The simulation results show that indeed we can lower final error and faster convergence when small is applied than that of large as in the conventional LMS.
Important Links:
Go Back
